JP2005160502A - Image diagnosis support apparatus - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image diagnosis support apparatus efficiently diagnosing a medical image and reducing a burden of a medical personnel. <P>SOLUTION: The medical image is inputted along with incidental information. This image diagnosis support apparatus stores example sentences explaining the medical image corresponding to the incidental information of the medical image and automatically selects an example sentence from the example sentences based on the inputted incidental information. This support apparatus detects a lesion part on the inputted medical image, applies its characteristics to the selected sentence, and creates a report of the medical image. This apparatus allows the medical personnel to compile the created example sentences and report, and uses the past report of the patient to efficiently and appropriately perform the image diagnosis and reduce the burden of the medical personnel. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

  The present invention relates to an image diagnosis support apparatus that supports image diagnosis performed by medical personnel such as doctors.

  Conventionally, medical diagnosis such as doctors observes medical images and makes diagnosis, and makes findings and reports, etc., but in recent years medical technology has advanced and social infrastructure has been improved Along with this, the number and importance of diagnoses have increased, and the burden on healthcare professionals has increased.

  For this reason, a technique for supporting image diagnosis by allowing the image display state at the time of finding data creation to be reproduced later has been proposed (see, for example, Patent Document 1).

In addition, a diagnosis support apparatus that detects and displays a lesion from a medical image has been proposed (see, for example, Patent Document 2). The diagnosis support apparatus described in Patent Document 2 intends to support report creation by medical staff by displaying feature quantities such as the position and size of lesion candidates extracted from images together with a report template. is there.
JP 2003-33327 A JP 2001-273364 A

  However, the conventional techniques as shown in Patent Document 1 and Patent Document 2 cannot sufficiently reduce the burden on medical personnel. For example, in the technique disclosed in Patent Document 1, all the findings must be created by the work of a healthcare professional only by reproducing the image display state. In the technique disclosed in Patent Document 2, the feature amount of a lesion detected from a medical image and a template of a report are displayed. However, there are many items to be examined and input by medical staff, and it takes time to create a report. It takes time and effort. With such a technique, as described above, the importance of image diagnosis is increasing, and the number of cases is increasing today, and the burden on medical staff becomes large.

  The present invention has been made in view of the above circumstances, and an object thereof is to provide an image diagnosis support apparatus that efficiently performs medical image diagnosis and reduces the burden on a medical worker.

  In order to achieve the above object, an image diagnosis support apparatus according to claim 1 describes means for inputting a medical image together with supplementary information, detection means for detecting a lesioned part in the input medical image, and the medical image. A plurality of example sentence storage means stored in association with the supplementary information of the medical image, a means for automatically selecting an example sentence corresponding to the input supplementary information from the stored example sentences, and the detection A means for creating a report of the inputted medical image by applying the feature of the lesioned part to the selected example sentence, and a means for a user to edit the created report.

  In the image diagnosis support apparatus according to claim 1, since a report can be created with less work by detecting a lesioned part of a medical image and applying the detection result to a pre-stored example sentence, a medical worker can efficiently perform image diagnosis. Can be done and the burden is reduced.

  The example sentence includes information such as the size, position, shape, and pixel value of the lesion. Further, the incidental information input together with the medical image includes the type of the imaging device, the site, the examination date and time, patient identification information, and the like.

  The image diagnosis support apparatus according to claim 2 further includes means for setting a region of interest in the input medical image based on a user instruction input in the image diagnosis support apparatus according to claim 1, wherein the detection means It is characterized by detecting a lesion in the set region of interest.

  In the diagnostic imaging support apparatus according to the second aspect, a report can be quickly created by processing the region of interest set by the user.

  An image diagnosis support apparatus according to a third aspect is the image diagnosis support apparatus according to the first or second aspect, further comprising means for editing the stored example sentence.

  In the image diagnosis support apparatus according to the third aspect, the image diagnosis can be performed more efficiently by editing the example sentence according to the type of medical image, the incidental condition, the item necessary for the report, the arrangement thereof, and the like.

  The diagnostic imaging support apparatus according to claim 4 further includes means for accumulating the created report for each patient in the diagnostic imaging support apparatus according to any one of claims 1 to 3, wherein the creating means includes: The feature of the detected lesion is applied to the accumulated report.

  In the image diagnosis support apparatus according to the fourth aspect, by using the past report of the patient, a report suitable for the disease name and symptom of the patient can be quickly created, and the image diagnosis can be performed more efficiently.

  According to the image diagnosis support apparatus according to the present invention, it is possible to efficiently perform medical image diagnosis and reduce the burden on the medical staff.

  Hereinafter, preferred embodiments of an image diagnosis support apparatus according to the present invention will be described in detail with reference to the accompanying drawings.

  FIG. 1 shows a configuration of an image diagnosis support system 10 according to the present embodiment. The image diagnosis support system 10 is configured by connecting a CT apparatus 50, an MRI apparatus 52, and an X-ray apparatus 54 that capture medical images to the image diagnosis support apparatus 20 via a network 60.

  The diagnostic imaging support apparatus 20 is an embodiment of the diagnostic imaging support apparatus of the present invention, and the control unit 30 controls each component shown below.

  The display unit 22 inputs and displays medical images taken by apparatuses such as the CT apparatus 50, the MRI apparatus 52, and the X-ray apparatus 54, and displays report example sentences and created reports. The user can set a ROI (Region Of Interest) for the medical image displayed on the display unit 22 via the report editing unit 28, and can edit the created report. The report editing unit 28 is configured by a device such as a keyboard and a mouse.

  The display position detection unit 24 detects the number, position, and size of the ROI set by the user in the medical image. The report example sentence generation unit 26 performs processing such as lesion detection and report generation for the ROI detected by the display position detection unit 24 (described later).

  In the storage unit 32, medical images are stored together with accompanying information (type of imaging device, part, examination date, patient identification information, etc.). A plurality of example sentences of the report are stored in association with the accompanying information, and past reports for each patient are accumulated. The example sentences can be edited in accordance with the type of medical image, incidental conditions, report output items, arrangement, and the like, thereby making it possible to efficiently create a report.

  FIG. 2A shows details of the report example sentence generation unit 26. The report example sentence generation unit includes an ROI extraction processing unit 34, a measurement processing unit 36, a word generation unit 38, and a layout processing unit 40. As shown in the example of FIG. The word corresponding to each item indicating the feature of the lesion in the example sentence is set.

  Next, a report creation process in the image diagnosis support system 10 will be described. FIG. 3 shows a processing flow.

  First, in step 100, a medical image is input together with incidental information and displayed on the display unit 22. As the medical image, an image captured by the CT apparatus 50, the MRI apparatus 52, the X-ray apparatus 54, or the like may be input, or an image stored in the storage unit 32 may be input. Input of medical images and incidental information (type of imaging device, site, examination date and time, patient identification information, etc.) can be performed based on, for example, DICOM (Digital Imaging and Communication in Medicine) specifications.

  Next, in step 110, an ROI (region of interest) is set in the image displayed on the display unit 22 based on a user instruction input via the report editing unit 28, and the process proceeds to step 120. The number, position, and size of the ROI can be freely set by the user.

  In step 120, the ROI set in step 110 is extracted from the input medical image.

  In the next step 130, measurement processing is performed. This process is a process for detecting the number, position, size, pixel value, shape, and the like of a lesioned portion of the ROI extracted in step 120.

  In the next step 140, the detection result is converted into a report output format to generate a word used in the report, and the process proceeds to step 150.

  In step 150, an example sentence is selected from the example sentences stored in the storage unit 32 based on the supplementary information input in step 100 described above, and the report generated by placing the word generated in step 140 above on the example sentence. create. FIG. 3B shows an example of layout processing. Here, the words generated in step 140 are applied to items such as “part” and “position”.

  At this time, a past report of the patient can be used as an example sentence to create a new report. The type, size, number, etc. of lesions vary greatly depending on the patient's disease name and symptoms, so the accuracy and reliability of the treatment can be ensured by using past reports of the same patient, and the lesion site over time. Changes can be easily observed.

  In step 160, editing processing is performed. This process is a process for the user to confirm and edit the created report. An example of report editing is shown in FIG. Here, for the image shown in FIG. 4 (a), as shown in FIG. 4 (b), a report “There is an abnormal shadow of 30 mm on the right side of the lung” is created, but the user edits the report. This result can be edited via section 28. Here, an example is shown in which the size of the shadow is changed from 30 mm to 35 mm, and as shown in FIG. 4C, it is determined with the content “There is an abnormal shadow of 35 mm on the right side of the lung”.

  In step 170, the report created up to step 160 is stored in the storage unit 32, and the process ends. Note that the user can print the created report or use it in other devices such as an electronic medical record system.

  As described above, the diagnostic imaging support system 10 according to the present embodiment detects a lesion and a feature amount, and further automatically creates a report based on the detection result. As a result, the user can efficiently perform image diagnosis, and the work to be performed by himself / herself is reduced and the burden is reduced.

  In addition, since the user can confirm and edit the automatically created report in this way, the accuracy and reliability of the image diagnosis can be ensured.

1 is a configuration diagram of an image diagnosis support system according to an embodiment of the present invention. It is a figure which shows the structure of the report example sentence production | generation part concerning one Embodiment of this invention. FIG. 5 is a diagram illustrating a processing flow of the image diagnosis support apparatus according to an embodiment of the present invention. It is a figure which shows the example sentence of a report and its editing concerning one embodiment of this invention.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 10 ... Image diagnosis assistance system, 20 ... Image diagnosis assistance apparatus, 22 ... Display part, 24 ... Display position detection part, 26 ... Report example sentence production | generation part, 28 ... Report edit part , 30 ... control unit, 32 ... storage unit, 34 ... ROI extraction processing unit, 36 ... measurement processing unit, 38 ... word generation unit, 40 ... layout processing unit

Claims (4)

Means for inputting a medical image together with accompanying information;
Detecting means for detecting a lesion in the input medical image;
A plurality of example sentence storage means for storing a plurality of example sentences explaining the medical image in association with the supplementary information of the medical image;
Means for automatically selecting an example sentence corresponding to the input incidental information from the stored example sentence;
Applying the detected lesion feature to the selected example sentence and creating a report of the input medical image;
Means for the user to edit the created report;
An image diagnosis support apparatus comprising:   2. The method according to claim 1, further comprising means for setting a region of interest in the input medical image based on an instruction input by a user, wherein the detection unit detects a lesion portion in the set region of interest. Image diagnosis support device.   The image diagnosis support apparatus according to claim 1, further comprising means for editing the stored example sentence.   4. The apparatus according to claim 1, further comprising a unit that accumulates the created report for each patient, wherein the creating unit applies the feature of the detected lesion portion to the accumulated report. The diagnostic imaging support apparatus according to 1.

Images