[go: up one dir, main page]

WO2012099163A1 - Procédé de création de données d'informations de cellule - Google Patents

Procédé de création de données d'informations de cellule Download PDF

Info

Publication number
WO2012099163A1
WO2012099163A1 PCT/JP2012/050958 JP2012050958W WO2012099163A1 WO 2012099163 A1 WO2012099163 A1 WO 2012099163A1 JP 2012050958 W JP2012050958 W JP 2012050958W WO 2012099163 A1 WO2012099163 A1 WO 2012099163A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
cell
unit
image data
attribute information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2012/050958
Other languages
English (en)
Japanese (ja)
Inventor
博文 塩野
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nikon Corp
Original Assignee
Nikon Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nikon Corp filed Critical Nikon Corp
Publication of WO2012099163A1 publication Critical patent/WO2012099163A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • C—CHEMISTRY; METALLURGY
    • C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
    • C12M—APPARATUS FOR ENZYMOLOGY OR MICROBIOLOGY; APPARATUS FOR CULTURING MICROORGANISMS FOR PRODUCING BIOMASS, FOR GROWING CELLS OR FOR OBTAINING FERMENTATION OR METABOLIC PRODUCTS, i.e. BIOREACTORS OR FERMENTERS
    • C12M41/00—Means for regulation, monitoring, measurement or control, e.g. flow regulation
    • C12M41/46—Means for regulation, monitoring, measurement or control, e.g. flow regulation of cellular or enzymatic activity or functionality, e.g. cell viability
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
    • G06V20/695—Preprocessing, e.g. image segmentation

Definitions

  • the present invention relates to a method for creating cell information data, a cell information evaluation method, a cell information provision method, a cell information evaluation device, a cell information provision device, a cell information evaluation program, and a cell information provision program.
  • Patent Document 1 when a morphological feature amount of a cell is input, a cell illustration or cell image corresponding to the morphological feature amount of the cell input from the database is searched.
  • An image search system that displays an illustration or a cell image on a display unit is disclosed.
  • the present invention has been made in view of the above problems, and it is possible for a third party to add cell attribute information and to determine whether the user can trust the added cell attribute information. It is an object to provide an apparatus, a method, and a program.
  • a cell information data creation method in which a cell information data creation device including a storage unit creates cell information data in which cell image data and the cell attribute information are associated with each other, A step of classifying the cells into one of a plurality of classes based on the morphological features of the cells extracted from the image data of the cells; An evaluation unit evaluating the attribute information of the cell based on attribute information corresponding to the classified class; An image registration unit associates the evaluation information obtained by the step of evaluating, the image data of the cell and the attribute information of the cell, and stores them in the storage unit; A method for creating cell information data.
  • the step of evaluating the attribute information of the cell includes: Of the attribute information of the cells stored in the storage unit, the attribute information of cells having morphological features classified into the same class as the cell class classified by the classification unit is read from the storage unit Steps, A distribution information acquisition unit, from at least a plurality of attribute information read from the storage unit, to acquire distribution information related to the read attribute information based on the difference in content; (1) The method includes the step of evaluating the attribute information of the cells classified by the classification unit from the relationship between the attribute information of the cells classified by the classification unit and the distribution information acquired by the distribution information acquisition unit.
  • the step of acquiring the distribution information of the attribute information by the distribution information acquisition unit Obtaining distribution information from the attribute information of the cells stored in the plurality of storage units having morphological features that are classified into the same class as the class of cells classified by the classification unit,
  • the step of evaluating the attribute information of the cells includes the cells classified by the classification unit with respect to the attribute information of the plurality of cells classified into the same class based on the distribution information acquired from the distribution information acquisition unit.
  • the content of the plurality of attribute information is numerical information representing one of the cell culture conditions, The cell according to (3), wherein the degree of similarity of the attribute information is evaluated based on the degree of frequency distribution indicating the frequency for each numerical value based on the numerical information based on how far away from the numerical value that is the highest or higher than a predetermined frequency. How to create information data.
  • the evaluation unit evaluates the attribute information based on the image data of the cells classified by the classification unit and the user identification information for identifying the user or the user organization that provided the cell attribute information.
  • the method for creating cell information data according to any one of (1) to (4) above, wherein: (6) obtaining the image data and attribute information of cells in the image data via the input unit; An extracting unit extracting the morphological feature of the cell from the image data acquired via the input unit; Have The classifying step classifies the cell into any of a plurality of classes based on the morphological feature amount of the cell extracted in the step of the classification unit extracting the morphological feature amount of the cell, The evaluating step evaluates the attribute information of the cells in the image data acquired by the evaluation unit via the input unit based on the attribute information classified into the same class stored in the storage unit.
  • the storing step stores the image data and the cell attribute information acquired via the input unit in the storage unit in accordance with the evaluation in the evaluating step (1) to (5)
  • the method for creating cell information data according to any one of the above.
  • the input determination unit includes a step of determining whether or not the input unit has received a code indicating that the source of information indicating the culture condition of the cell is a culture device
  • the evaluating step is the method for creating cell information data according to (6), wherein the evaluation unit corrects the evaluation information based on a result determined by the input determination unit.
  • (9) a step of classifying the cell into any of a plurality of classes based on the morphological feature of the cell extracted from the image data of the cell;
  • An information reading unit stores a plurality of stored image data in which cells are copied, and attribute information of the cells in the stored image data corresponding to each of the stored image data, from the storage unit that stores at least the classification unit Reading out attribute information of cells having morphological features that are classified into the same class as the classified class of cells;
  • the evaluation unit evaluates the attribute information of the cells classified by the classification unit from at least the plurality of attribute information read from the storage unit and the attribute information of the cells classified by the classification unit; A method for evaluating cell information.
  • the step of evaluating the attribute information of the cells in the image data includes: The step of reading out the attribute information of the cell having the morphological feature amount classified into the same class as the class of the cell classified by the classification unit from the attribute information of the cell stored in the storage unit from the storage unit When, A distribution information acquisition unit, from at least a plurality of attribute information read from the storage unit, to acquire the distribution information of the attribute information of the same class based on the difference between the contents; From the relationship between the attribute information of the cells classified by the classification unit and the distribution information acquired by the distribution information acquisition unit, evaluating the attribute information of the cells classified by the classification unit;
  • the cell information evaluation method according to the above (9), comprising: (11) obtaining the attribute information of the image data and the cells in the image data via the input unit; An extracting unit extracting the morphological feature of the cell from the image data acquired via the input unit; Have The classifying step classifies the cell into any of a plurality of classes based on the morphological feature amount of the cell extracted in the step of the classification
  • the cell information evaluation method according to (10) above. (12)
  • the attribute information is further evaluated by the evaluation unit based on user identification information for identifying a user or a user organization that provided the image input by the input unit.
  • the consideration calculation unit may include consideration information that is information indicating a value of the consideration to the provider who provided the image data based on the evaluation information obtained based on the result of the evaluation performed by the evaluation unit.
  • a cell information providing method executed by a cell information providing apparatus including a storage unit that holds data, The registration unit stores the image data evaluated by the cell information evaluation method according to any one of (9) to (12) in the storage unit, and information indicating a class of cells in the image data; A registration procedure for associating and storing the attribute information of the cells in the image data in the storage unit; A classification method creation unit reads a plurality of the image data stored in the storage unit, and performs a classification method based on each morphological feature amount of the cells in the plurality of image data read from the storage unit.
  • the classification method creation procedure to create The search image data classification unit classifies the cells in the newly input image data into a predetermined class according to the classification method created by the classification method creation unit, and An attribute information acquisition unit that acquires attribute information corresponding to the class classified in the classification procedure from the storage unit; A method for providing cell information.
  • the image data evaluated by the cell information evaluation method according to any one of (9) to (12) is stored in the storage unit in association with the evaluation information of the image data
  • the classification method creation procedure when creating the classification method by the classification method creation unit, image data based on evaluation information of attribute information corresponding to the image data among image data stored in the storage unit A cell information providing method of creating a classification method using the selected image data.
  • a cell information evaluation apparatus that evaluates cell attribute information in the image data from image data in which cells are imaged and cell attribute information in the image data, a plurality of memories in which the cells are imaged
  • a storage unit that stores at least image data and attribute information of cells in the stored image data corresponding to each of the stored image data;
  • a classification unit for classifying the cell into any of a plurality of classes based on the morphological feature of the cell extracted from the stored image data; Read the attribute information of the same class of cells and the class when classified by the classification unit from the storage unit, The distribution information is acquired based on at least the difference between the attribute information read from the storage unit, and the cells in the image data are obtained from the relationship with the attribute information of the cells classified by the classification unit with respect to the distribution information.
  • An evaluation unit that evaluates the attribute information of A cell information evaluation apparatus comprising: (17) The evaluation unit further evaluates the image or the attribute information based on user identification information for identifying a user or a user organization that provided the image input by the input unit.
  • the storage unit further holds the evaluation information of the attribute information and the cell class for the image data, and the image data classified by the classification unit and the cells imaged in the image data
  • the cell information evaluation apparatus according to any one of (16) to (18), wherein the attribute information, the evaluation information of the attribute information, and the cell class obtained as a result of separation by the classification unit are stored.
  • a storage unit for storing data, image data evaluated by the cell information evaluation apparatus according to (19) above is stored in the storage unit, information indicating a class of cells in the image data, and the image A registration unit that associates and stores the attribute information of the cells in the data in the storage unit;
  • a classification method creating unit that reads out the image data stored in the storage unit and creates a classification method based on the morphological feature amount of each of the cells in the image data;
  • a search image data classification unit that classifies cells imaged in the image data acquired by the searcher information input unit into a corresponding class;
  • Attribute information acquisition unit that acquires attribute information corresponding to information indicating the class classified by the search image data classification unit from a storage unit, and outputs the acquired cell attribute information;
  • a cell information providing apparatus comprising: (21) In the storage unit, the image data evaluated by the cell information evaluation apparatus according to (19) is
  • the output unit further includes a provision information selection unit that selects image data or attribute information of cells to be output based on evaluation information of attribute information corresponding to the attribute information among the read attribute information.
  • the cell information providing apparatus according to (20).
  • a searcher information input unit for receiving searcher identification information for identifying a searcher;
  • a payment amount information acquisition unit for acquiring amount information indicating an amount paid by the searcher based on the searcher identification information;
  • the provision information selection unit selects image data or attribute information of a cell to be output according to the amount information acquired by the payment amount information acquisition unit.
  • a cell information evaluation apparatus comprising: stored image data in which at least a plurality of cells are imaged; and a storage unit in which attribute information of cells imaged in the stored image data is stored in association with the stored image data
  • the evaluation unit obtains distribution information based on a difference in content of at least a plurality of attribute information read from the storage unit, and the cell attribute information copied to the image data for the distribution information From the relationship, a third step of evaluating the attribute information of the cells in the image data input to the input unit; Cell information evaluation program to execute.
  • a computer of a cell information providing device including a storage unit that holds data
  • Image data evaluated by executing the cell information evaluation program according to (24) is stored in the storage unit, information indicating a class of cells in the image data, and attributes of the cells in the image data
  • a registration step of associating and storing information in the storage unit Searcher information input step for acquiring search information including image data in which cells to be searched are imaged;
  • a search image data classification step for classifying cells imaged in the image data acquired by the searcher information input unit into a corresponding class;
  • Attribute information acquisition step for acquiring attribute information corresponding to information indicating the class classified in the search image data classification step from the storage unit, and outputting the acquired cell attribute information;
  • a cell information evaluation apparatus that evaluates cell attribute
  • An evaluation unit that evaluates the attribute information of A cell information evaluation apparatus comprising: (27) The morphological feature amount of the cell is extracted from image data obtained by imaging a target cell in a computer installed outside the cell information evaluation apparatus, and is transmitted to the classification unit of the cell information evaluation apparatus.
  • the cell information evaluation apparatus according to (26) above.
  • a cell information providing apparatus comprising: a searcher information input unit that receives at least image data in which cells are imaged and searcher identification information that identifies a searcher; and the cell information evaluation apparatus according to (16) above.
  • a searcher information input unit that receives at least image data in which cells are imaged and searcher identification information that identifies a searcher
  • the cell information evaluation apparatus according to (16) above.
  • the computer As the first step of acquiring the amount information indicating the amount paid by the searcher based on the searcher identification information, the evaluation information obtained from the cell information evaluation apparatus, and the payment amount information acquisition unit
  • FIG. 1 is a functional block diagram of a cell information evaluation apparatus according to an embodiment of the present invention.
  • the cell information evaluation apparatus 1 includes a storage unit 10, an input unit 20, an identification information generation unit 21, an attribute information reading unit 31, an evaluation unit 32, a price calculation unit 33, an image registration unit 34, and information reading. Part 35.
  • the storage unit 10 includes a cell information storage unit 11 and a user information storage unit 15.
  • the cell information storage unit 11 stores an image storage unit 13 that stores image data obtained by photographing cells, an attribute information storage unit 12 that stores representative attribute information for each class when the cells are classified from the image, For each image data, the image data file name and attribute information, identification information assigned to each class, and all data storage unit 14 for storing attribute information evaluation information are provided.
  • image data attribute information of cells imaged in the image data, and the like in the storage unit 10
  • they are recorded under the control of the image registration unit 34 via the image registration unit 34.
  • the attribute information storage unit 12 stores a class id, identification information for identifying a cell, and cell attribute information in association with each other.
  • the class id is an ID unique to the class into which the cell is classified.
  • FIG. 2 is an example of a table in which the class id, identification information, and attribute information stored in the attribute information storage unit 12 are associated with each other.
  • the class id and identification information will be described in detail later, but these are codes assigned to the cells captured in the image based on the result of classification from the form of the cells captured in the image. .
  • the class id and the identification information are associated one-to-one.
  • the attribute information is also associated with the identification information on a one-to-one basis in FIG.
  • the cell attribute information includes the cell type id allocated for each cell type estimated from the cell shape information, a representative value indicating the cell activity, and a representative value indicating the cell quality.
  • Value representative value of culture time (hour), and typical culture conditions (medium, serum, additive) id are stored.
  • attribute information is based on the premise that all attribute information items are input when image data is input to the input unit. However, according to the present invention, it is not necessary to input all such attribute information. Only the information that the user wants to communicate needs to be input.
  • some essential input items may be defined. In that case, at least when cells are classified according to morphological information, essential input items may be set to such an extent that it can be understood how the characteristics of the cells differ for each classification.
  • the value indicating the degree of cell activity is represented by an integer from 0 to 100, and the greater the value, the higher the cell activity.
  • the value indicating the cell activity is, for example, a value calculated based on the oxygen consumption of the cell. The higher the oxygen consumption of the cell, the higher the activity of the cell.
  • the value indicating the cell quality is represented by an integer from 0 to 100, and the larger the value, the higher the cell quality.
  • the value indicating the quality of the cell is, for example, a value calculated based on the cell growth rate with respect to the culture time. The higher the cell growth rate with respect to the previous culture time, the higher the cell quality value.
  • the attribute information of the cell is not limited to the above, information indicating the origin of the cell (eg, human, mouse, etc.), information indicating the site of the cell (eg, liver, epidermis, nerve, etc.), culture conditions (temperature, atmosphere, groundwork) , Medium, serum, additives, etc.), information indicating the purpose of the culture, information indicating the presence or absence of successful cases for each purpose, information indicating the function of the cell, information indicating the culture method, handling of the cell It may include information indicating a method, prediction regarding future cells, authenticity of cells, and the like.
  • the information indicating the purpose of the culture is, for example, the purpose of induction into specific cells (cancer cells) or the purpose of differentiation into specific cells (bone cells).
  • Future cell prediction is, for example, future cell differentiation prediction or cell division frequency prediction. Even with the same cell, if the remaining number of possible divisions changes, there is a slight difference in the morphological feature amount of the cell. Therefore, the morphological feature amount is extracted and the difference between the morphological feature amounts is extracted. In addition, the number of remaining divisions can be included in the attribute information corresponding to different class ids and identification information.
  • the authenticity of a cell is, for example, whether or not a cell of a specific cell type obtained is really that cell type. Thereby, the cell information evaluation apparatus 1 can determine from the morphological information of the cell whether the purchased ES cell (Embryonic Stem cells) is really an ES cell.
  • FIG. 3 is a diagram for explaining an example of identification information.
  • the identification information is information including information indicating the cell type.
  • the identification information includes, as an example, an id indicating one of the cell attribute information, a value indicating the cell activity, a culture time [h], a value indicating the cell quality, and a serial number. It is comprised using numbers.
  • the serial number is a unique number assigned to a cell having the same cell type, cell activity, and cell quality to identify each cell. For example, even if the cell type, activity, and quality are the same, if the culture conditions have changed slightly, and there is a slight difference in the morphology of the cell, it can be handled by changing this serial number. . In particular, even if the cells are in the same site, the morphology may be slightly different for each individual cell. When you want to identify this slight difference in form, you can differentiate by changing the serial number.
  • the identification information may include other attribute information. This identification information has a field that holds the item in each record in any of the image storage unit 13, the attribute information storage unit 12, and the all data storage unit 14. In this embodiment, the identification information The corresponding record can be acquired from each storage unit based on the above. Note that a record is one of the units constituting a database and means one data item.
  • the attribute information storage unit 12 has the following database structure.
  • FIG. 4 is an example of a table in which the cell type id and the cell type stored in the attribute information storage unit 12 are associated with each other.
  • the cell type id and the cell type are associated one to one.
  • the attribute information storage unit 12 is assumed as a relational database, and the cell type is referred to from the cell type id.
  • a relational database refers to a database in which a plurality of different data are combined using key data such as an id number.
  • FIG. 5 is an example of a table in which the culture condition id, temperature, medium type, serum, and additive id stored in the attribute information storage unit 12 are associated with each other.
  • cell culture conditions temperature, medium type, serum, additive id
  • FIG. 5 is an example of a table in which the culture condition id, temperature, medium type, serum, and additive id stored in the attribute information storage unit 12 are associated with each other.
  • cell culture conditions temperature, medium type, serum, additive id
  • FIG. 6 is an example of a table in which the additive id stored in the attribute information storage unit 12 is associated with the presence or absence of each additive.
  • the presence or absence of each additive for example, glutamine, pyruvic acid, HEPES (2- [4- (2-Hydroxyethyl) -1-piperazinyl] ethanesulfonic acid)
  • the attribute information storage unit 12 holds the representative value of each attribute item for each piece of identification information as shown in FIG. 2, while the contents as shown in FIG. 4, FIG. 5, and FIG. Have a relationship built.
  • the image storage unit 13 In the image storage unit 13, one or more pieces of image data can be associated with one piece of identification information and the relationship can be recorded.
  • image data In order to specify image data, an image id to which a unique value is assigned for each image data and an image file path name are associated with each other.
  • FIG. 7 illustrates a database table stored in the image storage unit 13.
  • This table is an attribute indicating the certainty of the image id, the image file path name, the identification information, and the attribute information input together when the image data is input, stored in the image storage unit 13.
  • the information evaluation information forms one record.
  • the image id, the image file path name, and the evaluation information of the attribute information when the image data is input are associated one-to-one.
  • One or more image data files are associated with one piece of identification information.
  • An image data file is also stored in the image storage unit 13.
  • the evaluation information of the attribute information is a value from 0 to 10 that represents the evaluation of the attribute information. The higher the value, the higher the evaluation of the attribute information.
  • the all data storage unit 14 is based on the image of the cells input to the input unit 20, the attribute information input together with the input of the image, the evaluation information of the attribute information, and the image Identification information is associated and stored. All the data input to the input unit 20 is stored in the all data storage unit 14, and identification information allocated based on the image data is stored in association with it.
  • the all data storage unit 14 also stores image data stored in advance when the present cell information evaluation apparatus is constructed, cell attribute information captured in the image data, attribute information evaluation information, and identification information. .
  • FIG. 8 is a diagram illustrating an example of a table in which the image id, the identification information, all the attribute information, and the attribute information evaluation information stored in the all data storage unit 14 are associated with each other. In the table of FIG. 8, cell type id and culture condition id are shown as an example of attribute information, but other attribute information is also included.
  • the user information storage unit 15 In the user information storage unit 15, a user id assigned to each user for identifying the user and technique capability information indicating the capability of the user's cell handling technique are stored in association with each other. ing.
  • FIG. 9 is a diagram showing an example of a table in which the user id stored in the user information storage unit 15 is associated with the technique ability information.
  • the user id is a unique number assigned to each user.
  • the skill ability information is a value from 1 to 10, and the larger the value, the higher the skill of the technique.
  • the input unit 20 receives information input by the user terminal 50 via the communication network 40.
  • the information input by the input unit 20 changes the destination depending on the type of information.
  • the image data in which the cells are photographed is supplied to the extraction unit 23 and the image registration unit 34 described later.
  • the cell attribute information input together with the image data is supplied to the evaluation unit 32 and the image registration unit 34.
  • the user identification information is supplied to the evaluation unit 32.
  • identification information is assigned to the image data supplied to the extraction unit 23 by the identification information generation unit 21.
  • the identification information generation unit 21 includes a class identification information storage unit 22, an extraction unit 23, a classification unit 24, and a classification reference generation unit 25.
  • the image data supplied to the identification information generation unit 21 is first input to the extraction unit 23.
  • the image data is binarized with a certain luminance value to generate a binarized image.
  • Object (target) recognition is performed from the generated binarized image, and after performing predetermined noise removal processing, cell object extraction is performed.
  • the classification unit 24 extracts a plurality of morphological feature amounts described below from the extracted cell objects, and selects a class of input image data according to the morphological feature amounts.
  • the output form from the classification unit 24 is output as a class id.
  • the method by which the classification unit 24 selects a class from the morphological features is performed based on the classification criteria stored in the class identification information storage unit 22.
  • the class identification information storage unit 22 stores the class id, the identification information, and the range of the morphological feature amount of the cell indicating the reference for classification in association with each other.
  • the classification unit 24 classifies the cells captured in the image data over a plurality of layers while changing the reference items to be sequentially classified. Specifically, the classification unit 24 classifies cell objects using the classification tree shown in FIG. FIG. 12 is an example of a classification tree used when the classification unit 24 classifies cells into classes. The classification unit 24 uses this classification tree to compare the morphological feature amount of each item of the cell object supplied from the extraction unit 23 with each condition of the constructed classification tree, thereby capturing the image data. Cells are classified into a predetermined class. Cells having similar morphological features are classified into one class classified by this classification tree by the classification unit 24. As an example of setting the classification tree, for example, the method disclosed in US Pat. No. 4,097,845, US Pat. No. 4,125,828, or the like may be used.
  • the class id is uniquely determined to be 1 when the cell round is 70 or more and less than 90, the cell area is 50 or more and less than 150, and the total length of the cell is 10 or more and less than 30. Has been.
  • a branch of the classification tree represents each class, and a unique class id is assigned to each class.
  • the range of the morphological feature amount of the cell indicating the classification criterion is generated by the classification criterion generation unit 25 based on the attribute information stored in the all data storage unit 14 and the image data stored in the image storage unit 13. Is done.
  • the classification reference generation unit 25 uses the image data to which the same identification information is assigned, and sets a threshold value for each piece of morphological information from the morphological feature amounts of the cells captured by the image data.
  • each record of the image storage unit 13 includes attribute information evaluation information.
  • the attribute information evaluation information will be described in detail later, but it is preferable that the classification reference for creating the classification tree is created only with a value higher than a certain value of the attribute information evaluation information.
  • the classification reference generation unit 25 sets a threshold value for the evaluation information stored together with the file path name of each image in the image storage unit 13, and selects only image data having a better evaluation than the threshold value. To generate a standard for classification. Thereby, since the classification tree is always set in a state in which new image data is reflected, a highly accurate classification tree can be obtained.
  • FIG. 10 is a diagram showing an example of a table of class ids, identification information, and morphological feature amounts of cells stored in the class identification information storage unit 22.
  • the class id and the identification information are associated with each other on a one-to-one basis, and the class id and the combination of the morphological feature quantities of the cells are associated on a one-to-one basis.
  • the morphological feature amount of the cell is, for example, the roundness of the cell, the area of the cell, and the total length of the cell, and is calculated by a method described later.
  • the classification unit 24 performs classification based on the classification criteria stored in the class identification information storage unit 22. However, in some cases, image data of cells that do not belong to either case may be input. In this case, if there is a class id that is close to any classification criterion of the morphological feature quantity item, the class id may be assigned. Alternatively, a new class id may be generated and assigned. In this case, the classification unit 24 refers to the class identification information storage unit 22 and generates a class id that does not exist in the class identification information storage unit 22. The classification unit 24 inputs the morphological feature amount of the cell to which the new class is assigned to each item of the morphological feature amount of the cell using the classification reference.
  • the class identification information storage unit 22 determines whether or not to newly generate a class id by setting a threshold for the difference between the classification standard of each item and the morphological feature of the input image cell. Also good.
  • FIG. 11 is a diagram for explaining each morphological feature amount of a cell.
  • the morphological feature amount of the cell is, for example, as follows.
  • the morphological feature amount of the cell is extracted by the extraction unit 23.
  • “Total area” is a value indicating the area of the cell of interest.
  • the extraction unit 23 can obtain the value of “Total area” based on the number of pixels in the cell area of interest.
  • Hole area is a value indicating the area of the Hole in the cell of interest.
  • Hole refers to a portion where the brightness of the image in the cell is equal to or greater than a threshold value due to contrast (a portion that is close to white in phase difference observation).
  • a threshold value due to contrast (a portion that is close to white in phase difference observation).
  • stained lysosomes of intracellular organelles are detected as Hole.
  • a cell nucleus and other organelles can be detected as Hole.
  • the extraction unit 23 may detect a group of pixels in which the luminance value in the cell is equal to or greater than a threshold value as a Hole, and obtain a “Hole area” value based on the number of pixels of the Hole.
  • “Perimeter” is a value indicating the length of the outer periphery of the cell of interest.
  • the extraction unit 23 can acquire the value of “Perimeter” by contour tracking processing when extracting cells.
  • “Width” is a value indicating the length of the cell of interest in the horizontal direction (X direction) of the image.
  • “Height” is a value indicating the length of the cell of interest in the image vertical direction (Y direction).
  • Length is a value indicating the maximum value (the total length of the cell) among the lines crossing the cell of interest.
  • “Breadth” is a value indicating the maximum value (the lateral width of the cell) among the lines orthogonal to “Length”.
  • “Fiber Length” (see (i) of FIG. 11) is a value indicating the length when the target cell is assumed to be pseudo linear.
  • the extraction unit 23 obtains the value of “Fiber Length” by the following equation (1).
  • Fiber Breath (see (j) of FIG. 11) is a value indicating a width (length in a direction orthogonal to Fiber Length) when the cell of interest is assumed to be pseudo linear.
  • the extraction unit 23 calculates the value of “Fiber Breath” according to the following equation (2).
  • Shape Factor (see (k) of FIG. 11) is a value indicating the circularity (roundness of the cell) of the cell of interest.
  • the extraction unit 23 obtains the value of “Shape Factor” by the following equation (3).
  • Inner radius is a value indicating the radius of the inscribed circle of the cell of interest.
  • Outer radius is a value indicating the radius of the circumscribed circle of the cell of interest.
  • “Mean radius” is a value indicating an average distance between all the points constituting the outline of the cell of interest and its centroid point.
  • “Equivalent radius” is a value indicating the radius of a circle having the same area as the cell of interest. The morphological feature amount of the “Equivalent radius” indicates the size when the cell of interest is virtually approximated to a circle.
  • the class id supplied from the classification unit 24 is supplied to the attribute information reading unit 31 and the image registration unit 34.
  • the attribute information reading unit 31 reads representative attribute information associated with the identification information with reference to the class id from the attribute information storage unit 12 together with the identification information, and evaluates the read identification information and attribute information. To supply.
  • the evaluation unit 32 Based on the identification information supplied from the attribute information reading unit 31, the evaluation unit 32 reads attribute information corresponding to the identification information from the all data storage unit 14. Based on a predetermined calculation method, the attribute information input for the image input to the input unit 20 and the cells captured in the image is evaluated.
  • evaluation information is generated based on two calculation methods. The two calculation methods will be described. As a first calculation method, the evaluation unit 32 compares the attribute information provided with the same identification information read from the all data storage unit 14 with the attribute information supplied to the input unit 20, and Evaluation information is calculated. Specifically, for example, the evaluation unit 32 calculates the evaluation information E for the attribute information input to the input unit 20 using the following equation (4).
  • w i is a weight (value from 0 to 1) of the i-th attribute information
  • S i is a score (value from 0 to 10) of the i-th attribute information
  • N is attribute information.
  • the weight w i of the attribute information can be set in advance by the user. For example, the priority order of the weights is determined according to the type of user research. Further, a default value is set in the apparatus, and the weight is determined by the default value unless changed by the user. w i shall meet the following formula (5).
  • the evaluation unit 32 reads the attribute information input together with the images classified into the same identification information from the all data storage unit 14, and normalizes the maximum frequency for each value for each attribute information. Calculate the frequency. The frequency is totaled for each value of arbitrary attribute information to obtain a frequency distribution. The evaluation unit 32 uses a value obtained by multiplying the normalized frequency by 10 as a score.
  • the evaluation unit 32 extracts the normalized frequency of the input value from the normalized frequency distribution using the value of the predetermined attribute information currently input as the input value.
  • the evaluation unit 32 calculates a score by multiplying the extracted normalized frequency by 10.
  • FIG. 13A is a diagram showing a normalized frequency distribution (score distribution) of activity.
  • the horizontal axis is the activity, and the vertical axis is the normalized frequency or score.
  • the normalized frequency distribution of the activity is a distribution in which the normalized frequency is 1 when the activity is 5. Assuming that the activity is 5 among the attribute information of the input image currently input from the outside, the evaluation unit 32 calculates 1 as a normalized frequency from the frequency distribution shown in FIG. 10 is output.
  • FIG. 13B is a diagram showing a normalized frequency distribution (score distribution) of quality.
  • the horizontal axis is quality, and the vertical axis is normalized frequency or score.
  • the normalized frequency distribution of the quality is a distribution in which the normalized frequency becomes 1 when the quality is 8. If the quality is 7 among the attribute information of the input target image, the evaluation unit 32 calculates 0.5 as the normalized frequency from the frequency distribution shown in FIG. Output. In this way, the score varies depending on the normalized frequency distribution.
  • the activity weight w 1 is set to 0.8
  • the quality weight w 2 is set to 0.2.
  • the evaluation unit 32 creates a frequency distribution in which the numerical value of the same identification information is a variable for each item in a plurality of attribute information items, and the attribute information input to the input unit 20 has a high frequency. Add a score that increases or decreases for each item depending on whether it is small or not. Thereby, the obtained score is calculated as evaluation information of attribute information.
  • the evaluation unit 32 assigns a weighting element to each item of attribute information, and calculates evaluation information E based on the product of the score given by the frequency distribution and the weighting element.
  • the score can be calculated using the same method for attribute information other than numerical data.
  • the culture condition id shown in FIG. 5 is set on the horizontal axis, and the frequency is set for each culture condition id. It is preferable to create a frequency distribution so that culture conditions id are close to each other with similar culture conditions. This is not limited to id, and for example, the type of serum may be set on the horizontal axis.
  • the present invention is not limited to the frequency distribution as shown in FIG. 13 showing the frequency distribution, and a known deviation value calculation method may be used.
  • the evaluation information is also stored in the all data storage unit 14 for each image data.
  • the frequency may be weighted when the frequency distribution is created according to the level of the evaluation information. For example, if the numerical value of the evaluation information is 10, the frequency may be increased by 1. If the numerical value of the evaluation information is 1, the frequency may be increased by 0.1.
  • all records input to the entire data storage unit 14 may be adopted, or the frequency distribution may be created including the attribute information input to the input unit 20.
  • the attribute information input to the input unit 20 is included in the attribute information of the same class held by the cell information evaluation apparatus 1.
  • the evaluation information may be determined by determining whether it is included in a set having a high frequency of.
  • the evaluation unit 32 reads out the skill information corresponding to the user identification information supplied from the input unit from the user information storage unit 15.
  • the evaluation unit 32 sets the evaluation information to a higher value as the value of the read technique ability information is higher.
  • the user identification information is not limited to a user who has input an image or attribute information into the input unit.
  • the user identification information may be assigned to each institution such as a research organization.
  • the evaluation unit 32 may calculate the evaluation information of the input image or the input attribute information by combining the first method and the second method. Specifically, for example, the evaluation unit 32 multiplies the evaluation information calculated by the first method by a first predetermined weight and adds the second predetermined value to the evaluation information calculated by the second method. A value obtained by multiplying the weights and adding them may be calculated as new evaluation information.
  • the evaluation unit 32 supplies the calculated evaluation information to the consideration calculation unit 33 and the image registration unit 34.
  • the evaluation unit 32 outputs the attribute information supplied from the attribute information reading unit 31 and the calculated evaluation information to the outside.
  • the attribute information is changed by changing the representative attribute information corresponding to the identification information.
  • the modified attribute data can be written in the information storage unit 12.
  • the identification information is also corrected with the change of the attribute information.
  • correction is performed simultaneously on records in which the same identification information is recorded.
  • the consideration calculation unit 33 calculates the amount of consideration based on the evaluation information supplied from the evaluation unit 32.
  • the consideration calculation unit 33 is a consideration information (information indicating the amount of consideration) obtained by multiplying the evaluation information (for example, an integer from 0 to 10) by a predetermined number (for example, 10). For example, it is calculated as 0 to 100 [yen].
  • the consideration calculation unit 33 outputs the consideration information to the outside. Thereby, the amount of consideration is paid to the user who has input the image of the image of the cell and the attribute information of the cell thereafter.
  • a user or an institution that has provided an image of a new cell that cannot be classified by an existing classification tree and its attribute information, it may be set so as to pay a separately defined amount of compensation, regardless of the method described above.
  • the image registration unit 34 stores the image data supplied from the input unit 20 in the image storage unit 13 in association with the attribute information read by the attribute information reading unit 31 based on the information classified by the classification unit 24. .
  • the image registration unit 34 associates the file path name indicating the location where the input image is stored, the identification information supplied from the classification reference generation unit 25, and the evaluation information supplied from the evaluation unit 32. And stored in the image storage unit 13.
  • the image registration unit 34 also includes a file path name indicating the location where the input image is stored, the attribute information supplied from the input unit, the identification information supplied from the classification reference generation unit 25, and the evaluation unit 32.
  • the supplied evaluation information is associated with and stored in all data storage unit 14.
  • the information reading unit 35 may read an image associated with the identification information supplied from the classification unit 24 from the image storage unit 13 and output the read image and evaluation information of attribute information of the image to the outside. At this time, when the consideration information is outputted to the outside, it may be outputted together.
  • the information reading unit 35 reads identification information corresponding to the attribute information supplied from the input unit 20 from the attribute information storage unit 12.
  • the information reading unit 35 reads the image corresponding to the read identification information and the evaluation information of the attribute information of the image from the image storage unit 13.
  • the information reading unit 35 outputs the read image and the evaluation information of the attribute information of the image to the outside.
  • the cell information providing apparatus 101 uses some of the functional blocks of the cell information evaluation apparatus 1 described above to determine what cells are from the input image or which attribute information about the input cells. It is a device that provides the searcher with what kind of cell is supposed to be.
  • the cell information providing apparatus 101 is an apparatus that calculates an amount to be paid by a searcher when searching for information about cells.
  • FIG. 16 is a functional block diagram of the cell information providing apparatus 101 according to an embodiment of the present invention.
  • the cell information providing apparatus 101 includes a cell information evaluation apparatus 1 described with reference to FIGS. 1 to 15, a searcher information input unit 102, a cell information reading unit (classification method creation unit) 103, and a payment amount information acquisition unit. 104, provided information selection unit 105, and amount storage unit 106.
  • the searcher information input unit 102 receives a target image supplied from the user terminal 120 via the communication network 110 and searcher identification information for identifying the searcher.
  • the searcher information input unit 102 supplies the target image to the cell information reading unit 103.
  • the cell information providing apparatus 101 in addition to specifying the type of cell captured in the image data from the image data, inputs attribute information and outputs image data of cells that match or are similar to the attribute information. Alternatively, it is assumed that attribute information not input to the searcher information input unit 102 is output. Here, a case where image data is input to the searcher information input unit 102 will be described. Further, the searcher information input unit 102 supplies the searcher identification information to the payment amount information acquisition unit 104.
  • the cell information evaluation apparatus 1 receives user identification information. These pieces of information are input into the cell information evaluation apparatus 1 by the input unit 20 like the cell information evaluation apparatus 1 described above.
  • the input image data input to the searcher information input unit 102 is input to the identification information generation unit 21 of the cell information evaluation apparatus 1.
  • the identification information generation unit 21 generates a classification reference from the storage unit 10 based on the image data and the identification information in which the image data is classified, and generates a classification tree.
  • the identification information of the image data input to the searcher information input unit is output from the classification unit 24 to the information reading unit 35.
  • the information reading unit 35 acquires representative attribute information corresponding to the identification information from the attribute information storage unit 12.
  • the image data of the same identification information and the evaluation information of the attribute information are acquired from the image storage unit 13.
  • attribute information corresponding to the image data acquired from the image storage unit 13 is acquired from the entire data storage unit 14. These pieces of information are output to the provision information selection unit 105.
  • the searcher identification information input to the searcher information input unit 102 is input to the payment amount information acquisition unit 104.
  • the payment amount information acquisition unit 104 calculates amount information charged to the searcher according to the searcher identification information.
  • the billing amount can be acquired by referring to the amount storage unit 106 based on the searcher identification information input to the payment amount information acquisition unit 104.
  • searcher identification information, searcher category, and amount information are stored in a one-to-one correspondence.
  • the category of the searcher indicates, for example, a pharmaceutical company, a doctor, a researcher, a student, and the like.
  • the amount information is information indicating the amount of money required when a searcher determined according to the user's category acquires attribute information or an image of cells.
  • FIG. 17 is an example of a table in which the searcher identification information, the searcher category, and the amount information stored in the amount storage unit 106 are associated with each other.
  • a category and amount information are associated with each searcher identification information.
  • amount information (here, 0 to 1000 [yen] as a search fee) is determined according to the category of the searcher.
  • the amount of money may be a usage fee for a certain period (such as one month or one year), or may be used per time.
  • the payment amount information acquisition unit 104 reads, from the amount storage unit 106, amount information indicating the amount to be paid by the searcher corresponding to the searcher identification information supplied from the searcher information input unit 102.
  • the payment amount information acquisition unit 104 supplies the read amount information to the provision information selection unit 105.
  • the provided information selection unit 105 includes attribute information supplied from the cell information evaluation device 1 according to the evaluation information supplied from the cell information evaluation device 1 and the amount information supplied from the payment amount information acquisition unit 104. Select attribute information to be provided to the searcher.
  • the provided information selection unit 105 is supplied when the supplied amount information is smaller than a predetermined threshold (for example, 300) (for example, the category in FIG. 17 corresponds to the case of a researcher).
  • a predetermined threshold for example, 300
  • the supplied amount information is within a predetermined range (for example, 300 or more and 700 or less) (for example, the category in FIG. 17 corresponds to the case of a doctor)
  • the supplied attribute information (cell type, culture method, Only the attribute information of “cell type” and “cultivation method” of the attribute information with the highest evaluation information value is sent to the searcher. Select as provided information.
  • the supplied amount information is larger than a predetermined threshold (for example, 700) (for example, when the category in FIG. 17 is a pharmaceutical company) (for example, when the category in FIG. 17 is a pharmaceutical company)
  • a predetermined threshold for example, 700
  • the supplied attribute information (cell type, culture method, culture condition)
  • the attribute information of all items is selected as information to be provided to the searcher.
  • the provided information selection unit 105 supplies the selected attribute information and the evaluation information image of the attribute information to the user terminal 120 via the communication network 110.
  • the provision information selection unit 105 supplies the selected image and the evaluation information image of the image to the user terminal 120 via the communication network 110.
  • the provision information selection unit 105 supplies the amount information to the accounting server 160 via the communication network 150.
  • the billing server 160 means a server used in, for example, a credit card settlement or a billing system for a mobile phone.
  • the payment amount information acquisition unit 104 may select necessary attribute information by the searcher, and calculate the amount information according to the selected attribute information. In that case, the amount information may be changed according to the type of attribute information.
  • attribute information can be input from the user terminal 120 to the searcher information input unit 102, and a detailed image having attribute information corresponding to or close to the attribute information can be provided.
  • the searcher information input unit 102 receives attribute information and searcher identification information for identifying a searcher from the user terminal 120 via the communication network 110, and supplies them to the cell information evaluation apparatus 1. Further, the searcher information input unit 102 supplies the searcher identification information to the payment amount information acquisition unit 104.
  • the attribute information to be searched is supplied to the information reading unit 35 in the cell information evaluation device 1 through the input unit 20.
  • the information reading unit 35 acquires identification information to which the corresponding or similar attribute information is assigned from the attribute information storage unit 12. At this time, the information reading unit 35 acquires representative attribute information of the identification information.
  • the information reading unit 35 acquires image data of the same identification information from the image storage unit 13. Furthermore, attribute information and evaluation information of the same identification information are acquired from all the data storage units 14.
  • the cell information evaluation apparatus 1 supplies the image data acquired by the information reading unit 35, its attribute information, and evaluation information to the provision information selection unit 105.
  • the provided information selection unit 105 receives a plurality of cells supplied from the cell information evaluation device 1 according to the evaluation information supplied from the cell information evaluation device 1 and the amount information supplied from the payment amount information acquisition unit 104. An image in which cells to be provided to the searcher are captured is selected from the captured time-series images.
  • the provided information selection unit 105 is supplied when the supplied amount information is smaller than a predetermined threshold (for example, 300) (for example, the category in FIG. 17 corresponds to the case of a researcher).
  • a predetermined threshold for example, 300
  • the time-series image having the highest evaluation information value and the image at the beginning of culture is selected.
  • a time-series image in which a plurality of supplied cells are imaged when the supplied amount information is within a predetermined range (for example, 300 or more and 700 or less) (for example, the category in FIG. 17 corresponds to the case of a doctor), a time-series image in which a plurality of supplied cells are imaged. Among them, a time-series image having the highest evaluation information value, and an image at the beginning of culture and an image after differentiation induction are selected.
  • a predetermined range for example, 300 or more and 700 or less
  • the provided information selection unit 105 captures images of a plurality of supplied cells. Among the time series images thus selected, all of the time series images having the highest evaluation information values are selected.
  • the category of the searcher stored in the money amount storage unit 106 may be set separately for each individual instead of by occupation or affiliation.
  • the stored items may hold the presence / absence of an option contract, the number of times cell information is provided to the cell information evaluation apparatus 1, and the like.
  • all attribute information stored in all data storage unit 14 or the number of items providing attribute information may be increased or decreased.
  • FIG. 20 is a block configuration diagram of a cell information providing apparatus 200 that is a modification of the cell information providing apparatus.
  • the cell information providing apparatus 200 includes a searcher information input unit 102b, a storage unit 201, a registration unit 202, a classification method creation unit 203, a classification unit 204, and an attribute information acquisition unit 205.
  • the searcher information input unit 102b acquires search information that is search information transmitted by the user terminal 220 via the communication network 210 and includes image data in which cells to be searched are captured.
  • the registration unit 202 stores the image data evaluated by the cell information evaluation device 1 outside the device itself in the storage unit, information indicating the class of the cell in the image data, and the attribute of the cell in the image data The information is stored in the storage unit 201 in association with the information. In addition, the registration unit 202 causes the storage unit 201 to store the image data evaluated by the cell information evaluation device 1 outside the device itself in association with the evaluation information of the image data.
  • the classification method creation unit 203 reads a plurality of image data stored in the storage unit 201, and creates a classification method based on each morphological feature amount of the cells in the plurality of image data read from the storage unit 201.
  • the classification method creation unit 203 selects image data based on the evaluation information of the attribute information corresponding to the image data from the image data stored in the storage unit 201, and the selected method is selected.
  • a classification method is created using the obtained image data. Specifically, for example, the classification method creation unit 203 selects, from among the image data stored in the storage unit 201, image data whose attribute information evaluation information corresponding to the image data is higher than a predetermined value.
  • a classification method is created using the selected image data.
  • the classification method creation unit 203 creates a classification method using attribute information having high evaluation information, so that the classification accuracy is increased by the created classification method, and a cell in newly input image data is determined in advance. It is possible to improve the accuracy of classification when classifying into classes.
  • the search image data classification unit 204 selects a predetermined cell in the image data (newly input image data) acquired by the searcher information input unit 102b in accordance with the classification method created by the classification method creation unit 203. Classify into classes.
  • the attribute information acquisition unit 205 reads from the storage unit 201 the attribute information corresponding to the class classified by the search image data classification unit 204 that classifies the cells in the newly input image data, and the read attribute information To the outside.
  • a part or all of the functions of the cell information evaluation apparatus 1, the cell information providing apparatus 101, or the cell information providing apparatus 200 according to the present embodiment may be realized by a computer.
  • a cell information evaluation program or a cell information providing program for realizing the function is recorded on a computer-readable recording medium, and the cell information search program or cell information registration program recorded on the recording medium is stored in the computer system.
  • the “computer system” includes an OS (Operating System) and peripheral hardware.
  • the “computer-readable recording medium” refers to a portable recording medium such as a flexible disk, a magneto-optical disk, an optical disk, and a memory card, and a storage device such as a hard disk built in the computer system.
  • the “computer-readable recording medium” dynamically holds a program for a short time like a communication line when transmitting a program via a network such as the Internet or a communication line such as a telephone line.
  • it may include a program that holds a program for a certain period of time, such as a volatile memory inside a computer system serving as a server or a client.
  • the above-described program may realize a part of the above-described function, and may further realize the above-described function by a combination with a program already recorded in the computer system.
  • the extraction processing of the morphological feature amount of the image data of the target cell is performed by the image data input unit 20 and the extraction unit 23. That is, the cell morphological feature amount extraction processing is performed by the cell information evaluation apparatus 1.
  • the present invention is not limited to this, and the morphological feature amount extraction processing of the image data of the target cell is executed in the user's personal computer, and the morphological feature amount data is converted into the classification unit of the cell information evaluation apparatus 1. 24 may be transmitted.
  • data is transmitted to the cell information evaluation apparatus 1 installed outside using the Internet.
  • FIG. 14 is a flowchart showing a flow of processing in which the cell information evaluation apparatus 1 calculates a value by evaluating input attribute information.
  • the input unit 20 receives an input image and attribute information supplied from the user terminal 50 via the communication network 40 (step S101), supplies the input image to the extraction unit 23, and receives the attribute information from the evaluation unit. 32.
  • the extraction unit 23 calculates the morphological feature amount of the cell captured in the input image based on the input image supplied from the input unit 20 (step S102), and calculates the calculated morphological feature amount. Supplied to the classification unit 24.
  • the classifying unit 24 classifies the class based on the morphological feature amount supplied from the extracting unit 23, and outputs the class id assigned to the class to the attribute information reading unit 31 (step S103).
  • the attribute information reading unit 31 reads the attribute information corresponding to the class id supplied from the classification unit 24 from the attribute information storage unit (step S104). The attribute information reading unit 31 supplies the read attribute information to the evaluation unit 32.
  • the evaluation unit 32 calculates the evaluation information A of the attribute information based on the attribute information supplied from the input unit 20 and the attribute information supplied from the attribute information reading unit 31 (step S105).
  • the evaluation unit 32 supplies the calculated evaluation information A to the consideration calculation unit 33.
  • the consideration calculation unit 33 calculates the consideration information based on the evaluation information A supplied from the evaluation unit 32 (step S106).
  • the consideration calculation unit 33 supplies the calculated consideration information to the outside.
  • the image registration unit 34 causes the storage unit 10 to store the input image and the attribute information supplied to the input unit 20 together with the input image and the evaluation information. Above, the process of this flowchart is complete
  • the cell information evaluation apparatus 1 can create a classification tree reflecting the latest information by creating a new classification tree each time using the information in the storage unit 10 as the number of data increases. it can. Further, the input attribute information is evaluated, and evaluation information is allocated to each attribute information, so that the user can know whether the attribute information can be trusted based on the evaluation information. The higher the evaluation information of the input cell attribute information is, the higher the amount of consideration paid to the user is. Therefore, there is a high possibility that attribute information with a high evaluation will be input, and the result is stored in the storage unit 10. Can improve the quality of data.
  • the evaluation unit 32 may calculate the evaluation information B of the input image by a method similar to the method of calculating the evaluation information A of the attribute information. Specifically, for example, the evaluation unit 32 reads the image data stored in the image storage unit 13 having the same identification information as the cell identification information of the input image, reads the morphological feature, The distribution of the characteristic features is calculated. The evaluation unit 32 calculates the evaluation information B based on the position occupied by the morphological feature amount supplied from the extraction unit 23 on the distribution of the calculated morphological feature amount, and calculates the calculated evaluation information B as a consideration. To the unit 33. In that case, the consideration calculation unit 33 calculates the consideration information based on the evaluation information B supplied from the evaluation unit 32.
  • the evaluation unit 32 may determine evaluation information by an attribute information acquisition method.
  • the input determination unit (not shown) is attribute information from log information of an automatic culture apparatus that is capable of capturing an image of a cultured cell that is an automatic culture apparatus connected to each user terminal 50 by the user terminal 50. Among them, information indicating cell culture conditions (culture temperature, culture time, medium replacement cycle during culture, etc.) is acquired, and it is determined whether or not information indicating the culture conditions is transmitted to the apparatus.
  • the input determination unit determines whether or not the input unit 20 has received a code indicating that the information source indicating the cell culture conditions is the culture device. Thereby, the input determination part can determine whether the information which shows the culture condition of a cell is the information input artificially.
  • the evaluation unit 32 capable of transmitting information to the input determination unit performs evaluation of attribute information based on the result determined by the input determination unit, with respect to the attribute information evaluation information calculated as described above. to correct. Specifically, the evaluation unit 32 corrects the evaluation information to a lower level when the attribute information input artificially using a browser or the like is large, and the user terminal directly acquires the log information of the automatic culture apparatus. If the information is supplied to the input unit 20, the evaluation information is corrected to a higher level. By doing so, it is possible to avoid erroneous input of attribute information due to human error.
  • the automatic culture apparatus stores at least one piece of information indicating cell culture conditions (culture temperature, culture time, medium exchange cycle during culture, etc.) at predetermined time intervals. It may be stored in the unit or output to the outside of the automatic culture apparatus.
  • FIG. 15 is a flowchart showing a flow of a process in which the cell information evaluation apparatus 1 calculates a value from evaluation information of an image or attribute information corresponding to user skill information.
  • the input unit 20 receives user identification information, an image, and attribute information supplied from the user terminal 50 via the communication network 40 (step S201), and supplies the user identification information to the evaluation unit 32.
  • the evaluation unit 32 reads out the technique capability information corresponding to the user identification information supplied from the input unit 20 from the user information storage unit 15 (step S202).
  • the evaluation unit 32 calculates the evaluation information C of the image or attribute information supplied to the input unit 20 based on the read skill information (step S203).
  • the evaluation unit 32 supplies the calculated evaluation information C to the consideration calculation unit 33.
  • the consideration calculation unit 33 calculates consideration information based on the evaluation information C supplied from the evaluation unit 32 (step S204).
  • the consideration calculation unit 33 supplies the calculated consideration information to the outside.
  • the process of this flowchart is complete
  • the higher the technique capability information the higher the billing amount. Therefore, it is easy to collect data of people with high procedure ability.
  • the consideration calculation unit 33 may calculate the consideration information based on the evaluation information A, the evaluation information B, and the evaluation information C described above.
  • the consideration calculation unit 33 may calculate the consideration information based on any two of the evaluation information A, the evaluation information B, and the evaluation information C.
  • the cell information evaluation apparatus 1 is input based on the cell attribute information or the user identification information.
  • Image data or cell attribute information can be evaluated, and based on the evaluation, consideration can be calculated for a user who has provided the image data and cell attribute information.
  • the storage unit 10 of the cell information evaluation device 1 is inside the cell information evaluation device 1, the storage unit 10 may be outside the cell information evaluation device 1 without being limited thereto.
  • a communication unit may be provided in the storage unit 10 and connected to the cell information evaluation apparatus 1 via the communication unit.
  • the classification reference generation unit 25, the attribute information reading unit 31, the information reading unit 35, and the image registration unit 34 of the identification information generation unit 21 may be connected to the storage unit 10 through communication means.
  • the connection form may be either wireless or wired.
  • the cell information evaluation apparatus 1 Although this embodiment demonstrated the example implement
  • the cell information search system may be realized as a whole by using a separate storage device and the other parts as search devices. Further, in the present embodiment, the example in which the cell information evaluation apparatus 1 evaluates input image data or cell attribute information has been described. However, the present embodiment is not limited to evaluating image data or cell attribute information.
  • the cell information evaluation device 1 may be realized as a cell information data creation device that creates cell information data in which cell image data and cell attribute information are associated with each other.
  • FIG. 18 is a flowchart showing a flow of processing for selecting attribute information provided to the user by the cell information providing apparatus 101.
  • the searcher information input unit 102 receives the target image and user identification information supplied from the user terminal 120 via the communication network 110 (step S301).
  • the searcher information input unit 102 supplies the target image to the cell information evaluation apparatus 1. Further, the searcher information input unit 102 supplies the user identification information to the payment amount information acquisition unit 104.
  • the cell information evaluation apparatus 1 calculates identification information from the target image supplied from the searcher information input unit 102 (step S302). Next, the cell information evaluation apparatus 1 reads out the attribute information and the evaluation information of the attribute information from the calculated identification information, and supplies the read attribute information and the evaluation information of the attribute information to the provision information selection unit 105 (step) S303).
  • the payment amount information acquisition unit 104 reads the amount information corresponding to the user identification information supplied from the searcher information input unit 102 from the amount storage unit 106 and supplies the amount information to the provision information selection unit 105. (Step S304).
  • the provision information selection unit 105 supplies from the cell information reading unit 103 based on the amount information supplied from the payment amount information acquisition unit 104 and the evaluation information of the attribute information supplied from the cell information reading unit 103.
  • attribute information to be provided to the searcher is selected (step S305).
  • the provided information selection unit 105 supplies attribute information and evaluation information of the attribute information to the user terminal 120 via the communication network 110.
  • the user can obtain attribute information necessary for the user. Further, the user can determine whether or not the attribute information can be trusted based on the evaluation information of the attribute information.
  • FIG. 19 is a flowchart showing a flow of processing for selecting an image provided to the user by the cell information providing apparatus 101.
  • the cell information providing apparatus 101 does not have to be configured as a separate member such as a circuit block as shown in FIG. 16.
  • the function as shown in FIG. 19 is switched by a processing device whose function is switched by time division such as a CPU.
  • cell information provision may be realized.
  • the searcher information input unit 102 receives attribute information and user identification information supplied from the user terminal 120 via the communication network 110 (step S401).
  • the searcher information input unit 102 supplies the attribute information to the cell information evaluation apparatus 1. Further, the searcher information input unit 102 supplies the user identification information to the payment amount information acquisition unit 104.
  • the cell information evaluation apparatus 1 calculates identification information from the attribute information supplied from the searcher information input unit 102 (step S402).
  • the cell information evaluation apparatus 1 reads a plurality of images in which cells are imaged from the calculated identification information and the evaluation information of the images, and sends the read images and the evaluation information of the images to the cell information reading unit 103. Supply (step S403).
  • the cell information reading unit 103 supplies the plurality of images supplied from the cell information evaluation apparatus 1 and the evaluation information of the images to the provision information selection unit 105.
  • the payment amount information acquisition unit 104 reads the amount information corresponding to the user identification information supplied from the searcher information input unit 102 from the amount storage unit 106 and supplies the amount information to the provision information selection unit 105. (Step S404).
  • the provision information selection unit 105 receives the evaluation information supplied from the cell information evaluation device 1 and the payment amount information acquisition unit. In accordance with the amount information supplied from 104, an image in which cells to be provided to a searcher are imaged is selected from images in which cells supplied from the cell information evaluation apparatus 1 are imaged (step S405).
  • the provided information selection unit 105 supplies an image and evaluation information of the image via the communication network 110. Above, the process of this flowchart is complete
  • the user can obtain the necessary images. Further, the user can determine whether or not the image can be trusted based on the evaluation information of the image.
  • the cell information providing apparatus 101 receives the evaluation information of the attribute information corresponding to the target image, and the amount information according to the user identification information.
  • the attribute information to be provided to the searcher can be selected based on the above.
  • the cell information providing apparatus 101 receives the evaluation information of the image obtained by capturing the cell corresponding to the attribute information and the amount corresponding to the user identification information. Based on the information, an image in which cells to be provided to a searcher are imaged can be selected from images in which a plurality of cells are imaged.
  • the cell information evaluation apparatus 1 is disclosed as one functional block of the cell information providing apparatus 101.
  • the present invention is not limited to such a form, and the searcher of the cell information providing apparatus 101
  • the information input unit 102 and the provision information selection unit 105 may be provided with a communication unit, and the provision information selection unit 105 may acquire necessary information via the communication unit with the cell information evaluation apparatus 1.
  • the necessary information may be obtained from the cell information evaluation apparatus 1 only based on the amount information of the payment amount information acquisition unit 104 and provided to the user terminal.
  • the cell information evaluation apparatus 1 of the cell information provision apparatus 101 is provided inside the cell information provision apparatus 101.
  • the present invention is not limited to this, and the cell information evaluation apparatus 1 is separated from the cell information provision apparatus 101.
  • the cell information providing system may be realized as a whole by using the separate cell information evaluation apparatus 1 as a separate device and the other parts as the providing apparatus.
  • FIG. 21 is a flowchart showing a flow of processing in which the cell information providing apparatus 200, which is a modification of the cell information providing apparatus, outputs attribute information from the input search information.
  • the registration unit 202 stores image data and attribute information corresponding to the image data in the storage unit 201 (step S501).
  • the classification method creation unit 203 creates a classification method based on the image data stored in the storage unit 201 and attribute information associated with the image data (step S502).
  • the searcher information input unit 102b acquires search information input from the user terminal via the communication network 210 (step S503).
  • the search image data classification unit 204 classifies the cells in the image data acquired as search information from the user terminal into classes according to the created classification method (step S504).
  • the attribute information acquisition unit 205 reads the attribute information corresponding to the class from the storage unit 201, and outputs the read attribute information to the outside of the own device (step S505). Above, the process of this flowchart is complete
  • the search image data classification unit 204 has created a classification method before the searcher information input unit 102b acquires search information.
  • the searcher information input unit 102b is not limited to this.
  • the search image data classifying unit 204 may create a classification method after acquiring.
  • the cell information providing apparatus 200 can classify the cells in the image data input from the outside into a predetermined class and acquire attribute information corresponding to the classified class. . Thereby, since the cell information providing apparatus 200 can acquire the attribute information of the cell imaged in the image from the image data, the user of the cell information providing apparatus 200 can activate the activity of the cell imaged in the image. Attribute information such as degree and quality can be obtained.
  • the cell information evaluation device 1 has been described as being outside the cell information provision device 200, but the cell information evaluation device 1 may be inside the cell information provision device 200.
  • the cell information providing apparatus 200 includes a searcher information input unit 102, a payment amount information acquisition unit 104, a provision information selection unit 105, and an amount storage unit 106 included in the cell information provision apparatus 101 illustrated in FIG. May be provided. Accordingly, the provision information selection unit 105 selects the image data or attribute information of the cell to be output according to the amount information acquired by the payment amount information acquisition unit 104. The cell image data or attribute information provided to the searcher can be changed according to the amount to be paid.
  • evaluation information corresponding to the amount information acquired by the provision information selection unit 105 and the payment amount information acquisition unit 104 is calculated, and cell image data or attribute information corresponding to the calculated evaluation information is stored from the storage unit 201.
  • the read image data or attribute information of the read cells may be output to the outside.
  • the cell information providing apparatus 200 can provide the searcher with image data or attribute information of a cell having a higher evaluation as the amount paid by the searcher is higher.
  • a third party adds cell attribute information, and allows a user to determine whether or not the added cell attribute information is reliable.

Landscapes

  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Zoology (AREA)
  • Wood Science & Technology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Biomedical Technology (AREA)
  • Organic Chemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Microbiology (AREA)
  • Biotechnology (AREA)
  • Cell Biology (AREA)
  • Biochemistry (AREA)
  • General Engineering & Computer Science (AREA)
  • Analytical Chemistry (AREA)
  • Genetics & Genomics (AREA)
  • Sustainable Development (AREA)
  • Molecular Biology (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

La présente invention porte sur un dispositif d'évaluation d'informations de cellule qui comprend une unité d'entrée (20), une unité de stockage d'informations d'attribut (12), une unité de catégorisation (24), une unité de lecture d'informations d'attribut (31) et une unité d'évaluation (32). Une image prise d'une cellule et des informations d'attribut pour la cellule dans ladite image sont appliquées en entrée à l'unité d'entrée. L'unité de stockage d'informations d'attribut stocke les éléments suivants en association les uns avec les autres : des classes dans lesquelles des cellules sont catégorisées; et des informations d'attribut pour lesdites cellules. L'unité de catégorisation catégorise la cellule dans l'image prise en une classe sur la base de quantités de caractéristiques morphologiques pour ladite cellule, lesdites quantités de caractéristiques morphologiques étant extraites de la morphologie de ladite cellule. Dans l'unité de stockage d'informations d'attribut (12), l'unité de lecture d'informations d'attribut lit des informations d'attribut pour une image prise d'une cellule catégorisée dans la même classe que la cellule susmentionnée. L'unité d'évaluation évalue soit les informations d'attribut soit l'image appliquée en entrée à l'unité d'entrée (20) par comparaison des informations d'attribut lues aux informations d'attribut appliquées en entrée à l'unité d'entrée (20).
PCT/JP2012/050958 2011-01-19 2012-01-18 Procédé de création de données d'informations de cellule Ceased WO2012099163A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2011008894 2011-01-19
JP2011-008894 2011-04-18

Publications (1)

Publication Number Publication Date
WO2012099163A1 true WO2012099163A1 (fr) 2012-07-26

Family

ID=46515785

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2012/050958 Ceased WO2012099163A1 (fr) 2011-01-19 2012-01-18 Procédé de création de données d'informations de cellule

Country Status (1)

Country Link
WO (1) WO2012099163A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106661529A (zh) * 2014-04-15 2017-05-10 奥林巴斯株式会社 细胞观察信息处理系统、细胞观察信息处理方法、细胞观察信息处理程序、细胞观察信息处理系统具有的记录部和细胞观察信息处理系统具有的装置
CN112292445A (zh) * 2018-06-13 2021-01-29 富士胶片株式会社 信息处理装置、导出方法及导出程序

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006349533A (ja) * 2005-06-16 2006-12-28 Olympus Corp 画像処理装置および画像処理プログラム
JP2008064534A (ja) * 2006-09-06 2008-03-21 Olympus Corp 細胞画像処理装置および細胞画像処理方法
WO2010098105A1 (fr) * 2009-02-26 2010-09-02 国立大学法人名古屋大学 Dispositif d'évaluation d'un état d'incubation, procédé d'évaluation d'un état d'incubation, incubateur et programme

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006349533A (ja) * 2005-06-16 2006-12-28 Olympus Corp 画像処理装置および画像処理プログラム
JP2008064534A (ja) * 2006-09-06 2008-03-21 Olympus Corp 細胞画像処理装置および細胞画像処理方法
WO2010098105A1 (fr) * 2009-02-26 2010-09-02 国立大学法人名古屋大学 Dispositif d'évaluation d'un état d'incubation, procédé d'évaluation d'un état d'incubation, incubateur et programme

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
SATORU NISHIMURA ET AL.: "Decision Tree Induction from Numeric Data Stream", FIT2009, DAI 8 KAI FORUM ON INFORMATION TECHNOLOGY KOEN RONBUNSHU, vol. 2, 20 August 2009 (2009-08-20), pages 75 - 82 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106661529A (zh) * 2014-04-15 2017-05-10 奥林巴斯株式会社 细胞观察信息处理系统、细胞观察信息处理方法、细胞观察信息处理程序、细胞观察信息处理系统具有的记录部和细胞观察信息处理系统具有的装置
EP3133146A4 (fr) * 2014-04-15 2017-12-27 Olympus Corporation Système de traitement d'informations d'observation de cellules, procédé de traitement d'informations d'observation de cellules, programme de traitement d'informations d'observation de cellules, unité d'enregistrement disposée dans le système de traitement d'informations d'observation de cellules, et dispositif disposé dans le système de traitement d'informations d'observation de cellules
CN112292445A (zh) * 2018-06-13 2021-01-29 富士胶片株式会社 信息处理装置、导出方法及导出程序

Similar Documents

Publication Publication Date Title
US9436695B2 (en) Dynamically expiring crowd-sourced content
JP5795650B2 (ja) 顔認識
US20230146563A1 (en) Automated image processing and insight presentation
US8255392B2 (en) Real time data collection system and method
CN102959551A (zh) 图像处理装置
US20190050814A1 (en) Generation of user profile from source code
KR20210082113A (ko) 시계열 데이터의 이중 학습 장치의 동작 방법
US11688096B2 (en) Use of image sensors to query real world for geo-reference information
WO2020006834A1 (fr) Procédé de recommandation d'institution financière, équipement, support d'informations et dispositif
JP2009217562A (ja) 関連文書提示システム及びプログラム
US10255348B2 (en) Information managing device, information managing method, and non-transitory recording medium
CN112463859B (zh) 基于大数据和业务分析的用户数据处理方法及服务器
CN109102324B (zh) 模型训练方法、基于模型的红包物料铺设预测方法及装置
WO2012099163A1 (fr) Procédé de création de données d'informations de cellule
US9451155B2 (en) Depth-segmenting peak tracking autofocus
WO2012099005A1 (fr) Procédé de création de données d'informations de cellule
JP4518168B2 (ja) 関連文書提示システム及びプログラム
US9767579B2 (en) Information processing apparatus, information processing method, and non-transitory computer readable medium
KR100827845B1 (ko) 인물 태그 제공 장치 및 방법
US20200311771A1 (en) Information processing device, information processing method, and program recording medium
CN115760172A (zh) 一种客户偏好确定方法、装置、设备以及存储介质
JP6958952B2 (ja) マスター顔画像の登録装置、登録方法、プログラム、および記録媒体
CN116797936B (zh) 基于手机信令数据的城市功能区域检测方法
CN117009628B (zh) 内容推荐方法、装置、设备、存储介质及程序产品
CN109919811A (zh) 基于大数据的保险代理人培养方案生成方法及相关设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 12736251

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 12736251

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: JP