CN107292816B - An image correction method, system and computer readable medium - Google Patents
An image correction method, system and computer readable medium Download PDFInfo
- Publication number
- CN107292816B CN107292816B CN201710469730.XA CN201710469730A CN107292816B CN 107292816 B CN107292816 B CN 107292816B CN 201710469730 A CN201710469730 A CN 201710469730A CN 107292816 B CN107292816 B CN 107292816B
- Authority
- CN
- China
- Prior art keywords
- image
- image data
- correction matrix
- correction
- uncorrected
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
本发明公开了一种图像校正方法、一种图像校正系统和一种存储图像校正方法的计算机可读媒介。该方法包括：获取图像数据；判断是否有与所述图像数据相关的校正矩阵；在判断出没有与所述图像数据相关的校正矩阵时，根据图像数据，生成未校正的图像；对所述图像进行校正，生成校正后的图像；根据未校正图像和校正后的图像，生成所述校正矩阵。在判断出有与所述图像数据相关的校正矩阵时，获取所述校正矩阵；根据所述校正矩阵和所述图像数据，生成校正后的图像。本方法使相同或相似的图像仅通过一次校正即可实现重复的显示，避免了重复校正，提高了使用效率。
The invention discloses an image correction method, an image correction system and a computer-readable medium storing the image correction method. The method includes: acquiring image data; judging whether there is a correction matrix related to the image data; when judging that there is no correction matrix related to the image data, generating an uncorrected image according to the image data; Correction is performed to generate a corrected image; and the correction matrix is generated according to the uncorrected image and the corrected image. When it is determined that there is a correction matrix related to the image data, the correction matrix is acquired; a corrected image is generated according to the correction matrix and the image data. The method enables the same or similar images to be displayed repeatedly only through one correction, avoids repeated corrections, and improves the use efficiency.
Description
Technical Field
The present invention relates to an image correction method, and more particularly, to an image correction method, system, and computer readable medium for realizing repeated display by only one correction.
Background
During medical scanning, the patient may not be able to remain in a normal position for a long time for scanning due to too long scanning time or illness. The images of the abnormal posture scanning and the normal posture scanning may be greatly different, which affects the judgment of the doctor on the state of an illness. The existing solutions usually make manual correction (e.g. rotation, etc.) on the image by the doctor, but for the same image, each re-display requires the doctor to make a manual correction again, which is very inconvenient.
Disclosure of Invention
In view of the above problems, it is an object of the present invention to enable repeated display of identical or similar images by only one correction.
In order to achieve the purpose of the invention, the technical scheme provided by the invention is as follows:
an image correction method, comprising: acquiring image data; judging whether a correction matrix related to the image data exists or not; generating an uncorrected image from the image data when it is determined that there is no correction matrix associated with the image data; and correcting the image to generate a corrected image.
In the invention, when a correction matrix related to the image data is judged, the correction matrix is obtained; and generating a corrected image according to the correction matrix and the image data.
In the present invention, the image is corrected to generate a corrected image, and then a correction matrix is generated from the uncorrected image and the corrected image.
In the present invention, the generating the correction matrix from the uncorrected image and the corrected image comprises: acquiring one or more annotation points on the uncorrected image and the corrected image; and generating the correction matrix according to the corresponding relation of the one or more marking points.
In the present invention, the generating the correction matrix from the uncorrected image and the corrected image comprises: registering the uncorrected image and the corrected image; and generating the correction matrix according to the registration result.
In the present invention, the correcting includes: segmentation, scaling, displacement, rotation, clipping, filtering, toning, averaging, or smoothing.
In the present invention, the image data is medical image data.
In the present invention, the medical image data includes: PET-CT image data, DR image data, CT image data, MRI image data, US image data, PET image data, or PET-MRI image data.
In the present invention, the method for generating an uncorrected image according to image data includes multiplanar reconstruction (MPR), Volume Rendering (VR), multiplanar volume rendering (MPVR), curved surface reconstruction (CPR), Maximum Intensity Projection (MIP), or surface covering (SSD).
In the present invention, the method further comprises assigning a serial number to the generated image matrix.
In the present invention, the determining whether there is a correction matrix associated with the image data includes determining whether there is a serial number associated with the image data.
In the invention, the serial number is a serial number based on DICOM standard.
In the present invention, the method further comprises: acquiring a standard image template; and generating a standard image correction matrix according to the corrected image and the standard image template.
The invention also discloses an image correction system. The system may include a scanning device and a processing device. The scanning device may acquire image data. The processing device may determine whether there is a correction matrix associated with the image data; upon determining that there is no correction matrix associated with the image data: the processing device may generate an uncorrected image from the image data; correcting the image to generate a corrected image; when it is determined that there is a correction matrix associated with the image data: the processing device obtains the correction matrix; and generating a corrected image according to the correction matrix and the image data.
The present invention also discloses a non-transitory computer-readable medium having stored thereon a computer program comprising instructions executable by at least one processor to perform a method comprising: acquiring image data; judging whether a correction matrix related to the image data exists or not; upon determining that there is no correction matrix associated with the image data: generating an uncorrected image from the image data; correcting the image to generate a corrected image; when it is determined that there is a correction matrix associated with the image data: acquiring the correction matrix; and generating a corrected image according to the correction matrix and the image data.
Drawings
FIG. 1 is a schematic diagram of an image correction system provided in accordance with the present invention;
FIG. 2 is a flow chart of an image correction provided in accordance with the present invention;
fig. 3 is a flow chart of generating a correction matrix according to the present invention.
FIG. 1 labels: 110 is a scanning device, 120 is a processing device, 130 is a network, 140 is a storage device, and 150 is a display device.
Detailed Description
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the present invention is further described below by using specific embodiments and with reference to the accompanying drawings.
As shown in fig. 1, image correction system 100 may include a scanning device 110, a processing device 120, a storage device 140, and a display device 150. The devices in the image correction system 100 may be connected or in communication with each other via a network 130.
The scanning device 110 may scan an object. The object may be an object, a human body, an organ, a tissue, or the like. The scanning device may be a medical image device. In some embodiments, the scanning device 110 may be a Magnetic Resonance Imager (MRI), a Computed Tomography (CT), a Positron Emission Tomography (PET), a B-ultrasound (B-scan), a Thermal Tomography (TTM), a Medical Electronic Endoscope (MEE), or the like. In some embodiments, the scanning device 110 may also be a combination of the above-described devices, such as a PET-CT scanner, a PET-MRI scanner, or the like. The scanning device 110 may generate image data corresponding to the object after scanning. Further, the scanning device 110 may transmit the acquired image data to the processing device 120, the storage device 140, or the display device 150 via the network 130.
The processing device 120 may process the image data. The image data may be obtained by scanning with the scanning device 110 or may be obtained from the storage device 140. In some embodiments, the image data may be two-dimensional or three-dimensional image data representing anatomical and/or functional information of the scanned object. The processing may include reconstructing the image data to generate an image. The reconstruction method may include, but is not limited to, one or more of multiplanar reconstruction (MPR), Volume Reconstruction (VR), multiplanar volume reconstruction (MPVR), curved surface reconstruction (CPR), Maximum Intensity Projection (MIP), Surface Shading (SSD), and the like. The processing may also include performing correction processing on the image data or the generated image. The correction process may include segmentation, scaling, displacement, rotation, clipping, filtering, toning, averaging, smoothing, and the like. In some embodiments, the processing device 120 may pre-process the obtained image data. The pre-processing may include down-sampling, data compression, and the like. In some embodiments, the processing device 120 may generate a correction matrix based on the uncorrected image and the corrected image. The correction matrix may represent a variation process or correspondence. The processing device 120 may send the correction matrix to the storage device 140 for storage.
The network 130 may be any connection that connects two or more devices. For example, the network 130 may be a wired network or a wireless network. In some embodiments, the network 130 may be a single network or a combination of networks. For example, the network 130 may include one or a combination of local area networks, wide area networks, public networks, private networks, wireless local area networks, virtual networks, public telephone networks, and the like. The modules in the image correction system 100 may interact with each other via the connection network 130.
The display device 150 may be used to display images. The display device 150 may include a display screen, a touch screen, and the like. In some embodiments, the display device 150 may include an interactive interface that may receive input from a user or a physician. In some embodiments, the display device 150 may include an input device, such as a touch pad, touch screen, mouse, keyboard, microphone, and the like. The display device 150 may send the user's input to the processing device 120 for processing or to the storage device 140 for storage.
In some embodiments, the display device 150 may display an image that the user may correct (e.g., rotate or displace) through the interactive interface. The display device 150 may transmit the correction operation by the user and the corrected image to the processing device 120. The processing device 120 may generate a correction matrix based on the uncorrected image and the image corrected by the user via the display device 150 (or the image corrected by the processing device 120). The correction matrix may represent the course of a change or correspondence of an image. The correction matrix may be stored in the storage device 140. When the same or similar image needs to be displayed, it can be changed according to the correction matrix to directly form a corrected image. Specific methods for correction matrix formation and invocation may be referred to in the description of other portions of the present invention. For example, reference may be made to fig. 2 and its description.
Fig. 2 is a flow chart of an image correction provided according to the present invention. In some embodiments, flow 200 may be implemented by processing device 120. In step 210, image data may be acquired. The image data may be obtained by the scanning device 110 or may be retrieved from the storage device 140.
In step 220, it may be determined whether a correction matrix associated with the image data is present in a device (e.g., storage device 140) of image correction system 100. If the correction matrix exists, executing step 250; otherwise, step 230 is performed. In some embodiments, the requirement for determining whether there is a correction matrix associated with the image data may be to determine whether there is a correction matrix that is identical, similar, or of the same type or same location as the image data. More specifically, the image correction system 100 may mark a serial number to the correction matrix when acquiring or generating the correction matrix, and the determination of whether there is a correction matrix related to the image data may be to determine whether there is a correction matrix with the same or similar serial number in the storage device 140 or the network 130. The serial number may be a serial number commonly used or common in the industry, such as a serial number based on the Digital imaging and Communications in Medicine (DICOM), or a serial number used internally by image correction system 100. In some embodiments, a correction matrix may correspond to multiple images obtained from a single scan (i.e., multiple images may correspond to the same image sequence) and may be applied to the correction of multiple images. For example, after a correction matrix of one image is obtained, a plurality of images corresponding to the same correction matrix may be corrected using the correction matrix, for example, correction processes such as bed removal, rotation, window width and level adjustment may be performed simultaneously. In some embodiments, a calibration matrix may correspond to a particular region, such as the head, chest, upper limb, lower limb, stomach, etc., of a patient. If a correction matrix for a particular region of a patient is generated, the correction matrix can be used for the correction of the same region of other patients. Similar variations are within the scope of the present application and are not described in detail herein.
In step 230, an image may be generated from the image data. For example, an image may be directly reconstructed from the image data. The image reconstruction method may include, but is not limited to, one or more of multiplanar reconstruction (MPR), Volume Reconstruction (VR), multiplanar volume reconstruction (MPVR), curved surface reconstruction (CPR), Maximum Intensity Projection (MIP), Surface Shading (SSD), and the like. In some embodiments, the reconstructed image may be uncorrected or have problems such as incorrect location, incorrect orientation, incorrect size, incorrect color, inclusion of unwanted objects, inclusion of artifacts, and the like.
In step 240, the uncorrected or problematic image may be corrected. The correction process may include segmentation, scaling, displacement, rotation, clipping, filtering, toning, averaging, smoothing, and the like. The correction process may be input by the user via the display device 150, generated by the processing device 120 itself, or a combination of both.
In step 250, a correction matrix may be acquired. In some embodiments, the correction matrix may be generated from an uncorrected image and a corrected image after a first correction of an image. The correction matrix may be directly acquired without regeneration when the image is subsequently required to be displayed. The method for generating the correction matrix can be referred to step 330 in fig. 3 and the description thereof.
In step 260, a corrected image may be automatically generated from the correction matrix and the image data. In some embodiments, an uncorrected image may be generated prior to generating a corrected image based on the uncorrected image and the correction matrix. In some embodiments, the corrected image may be obtained directly from the image data and the correction matrix. In some embodiments, the corrected image may be displayed by the display device 150, so that the doctor does not need to manually correct the uncorrected image, saving the doctor's diagnosis time while improving the diagnosis quality.
Fig. 3 is a flow chart of generating a correction matrix according to the present invention. In some embodiments, flow 300 may be implemented by processing device 120. Step 310 and step 320 correspond to step 230 and step 240, respectively, and are not described herein again. In some embodiments, flow 300 may be combined with flow 200, e.g., step 330 may be performed after step 240 in fig. 2.
In step 330, a correction matrix may be generated from the uncorrected image and the corrected image. In some embodiments, several corresponding annotation points can be set on the uncorrected image and the corrected image, respectively. The annotation points can be located at the edges, vertices, centers of gravity, etc. of the uncorrected image and the corrected image. The correction matrix may be generated according to a correspondence between positions or angles of the annotation points on the uncorrected image and the corrected image. In some embodiments, the corrected image and the uncorrected image may be registered to generate the correction matrix. Alternatively, a standard image template may be acquired. The standard image template may be a template in which the orientation and size of the relevant image area is an average or close to a large portion of the image. The standard image template may be registered with the corrected image to generate a standard image correction matrix. Based on the correction matrix, the uncorrected image and the corrected image can be converted to each other. For example, the pixel values of the uncorrected image multiplied by the correction matrix equals the pixel values of the corrected image. The uncorrected image or the corrected image may also be converted to an image of standard orientation and size according to the standard image correction matrix.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method of medical scan image correction, comprising:
acquiring image data;
judging whether a correction matrix related to the image data exists or not;
upon determining that there is no correction matrix associated with the image data:
carrying out image reconstruction according to the image data to generate an uncorrected image; and
correcting the image to generate a corrected image;
when it is determined that there is a correction matrix associated with the image data:
acquiring the correction matrix;
carrying out image reconstruction according to the image data to generate an uncorrected image; and
and generating a corrected image according to the correction matrix and the uncorrected image.
2. The image correction method according to claim 1, wherein when it is determined that there is no correction matrix relating to the image data, the correction matrix is generated further based on the uncorrected image and the corrected image.
3. The image correction method according to claim 2, wherein the generating the correction matrix from the uncorrected image and the corrected image comprises:
acquiring one or more annotation points on the uncorrected image and the corrected image; and
and generating the correction matrix according to the corresponding relation of the one or more marking points.
4. The image correction method according to claim 2, wherein the generating the correction matrix from the uncorrected image and the corrected image comprises:
registering the uncorrected image and the corrected image; and
and generating the correction matrix according to the registration result.
5. The image correction method according to claim 1, characterized in that the image data includes: PET-CT image data, DR image data, CT image data, MRI image data, US image data, PET image data, or PET-MRI image data.
6. The image correction method according to claim 1, wherein the image reconstruction method includes multiplanar reconstruction, volume reconstruction, multiplanar volume reconstruction, curved surface reconstruction, maximum density projection, or surface masking.
7. The image correction method according to claim 1, characterized by further comprising: marking the generated image matrix with a serial number; and
the determining whether there is a correction matrix associated with the image data comprises: it is determined whether there is a serial number associated with the image data.
8. The image correction method according to claim 1, characterized by further comprising:
acquiring a standard image template; and
and generating a standard image correction matrix according to the corrected image and the standard image template.
9. A medical scan image correction system, comprising:
a scanning device that acquires image data; and
a processing device that determines whether there is a correction matrix associated with the image data;
upon determining that there is no correction matrix associated with the image data:
the processing equipment carries out image reconstruction according to the image data to generate an uncorrected image; and
correcting the image to generate a corrected image;
when it is determined that there is a correction matrix associated with the image data:
the processing device obtains the correction matrix;
carrying out image reconstruction according to the image data to generate an uncorrected image; and
and generating a corrected image according to the correction matrix and the uncorrected image.
10. A non-transitory computer-readable medium having stored thereon a computer program comprising instructions executable by at least one processor to perform a method comprising:
acquiring image data;
judging whether a correction matrix related to the image data exists or not;
upon determining that there is no correction matrix associated with the image data:
carrying out image reconstruction according to the image data to generate an uncorrected image; and
correcting the image to generate a corrected image;
when it is determined that there is a correction matrix associated with the image data:
acquiring the correction matrix;
carrying out image reconstruction according to the image data to generate an uncorrected image; and
and generating a corrected image according to the correction matrix and the uncorrected image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710469730.XA CN107292816B (en) | 2017-06-20 | 2017-06-20 | An image correction method, system and computer readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710469730.XA CN107292816B (en) | 2017-06-20 | 2017-06-20 | An image correction method, system and computer readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107292816A CN107292816A (en) | 2017-10-24 |
| CN107292816B true CN107292816B (en) | 2021-04-20 |
Family
ID=60097738
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710469730.XA Active CN107292816B (en) | 2017-06-20 | 2017-06-20 | An image correction method, system and computer readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107292816B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6016168A (en) * | 1996-07-25 | 2000-01-18 | Samsung Electronics Co., Ltd. | Color correction device |
| CN101026675A (en) * | 2006-02-24 | 2007-08-29 | 佛山市顺德区顺达电脑厂有限公司 | Image correcting system and method for image access device |
| CN103792011A (en) * | 2014-01-27 | 2014-05-14 | 无锡艾立德智能科技有限公司 | Method and device for compensating for temperature drift through thermal infrared imager in a self-adaptation mode |
| CN104811688A (en) * | 2014-01-28 | 2015-07-29 | 聚晶半导体股份有限公司 | Image acquisition device and image deformation detection method thereof |
| CN105260733A (en) * | 2015-09-11 | 2016-01-20 | 北京百度网讯科技有限公司 | Method and device for processing image information |
-
2017
- 2017-06-20 CN CN201710469730.XA patent/CN107292816B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6016168A (en) * | 1996-07-25 | 2000-01-18 | Samsung Electronics Co., Ltd. | Color correction device |
| CN101026675A (en) * | 2006-02-24 | 2007-08-29 | 佛山市顺德区顺达电脑厂有限公司 | Image correcting system and method for image access device |
| CN103792011A (en) * | 2014-01-27 | 2014-05-14 | 无锡艾立德智能科技有限公司 | Method and device for compensating for temperature drift through thermal infrared imager in a self-adaptation mode |
| CN104811688A (en) * | 2014-01-28 | 2015-07-29 | 聚晶半导体股份有限公司 | Image acquisition device and image deformation detection method thereof |
| CN105260733A (en) * | 2015-09-11 | 2016-01-20 | 北京百度网讯科技有限公司 | Method and device for processing image information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107292816A (en) | 2017-10-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106056537B (en) | Method and device for stitching medical images | |
| JP5462865B2 (en) | Use of non-attenuated corrected PET emission images to compensate for imperfect anatomical images | |
| CN107833231B (en) | Medical image display method, device and computer storage medium | |
| US11176671B2 (en) | Medical image processing apparatus, and method | |
| JP2019103831A (en) | Selection and locking of intraoral images | |
| CN111815735B (en) | A CT Reconstruction Method and Reconstruction System of Human Tissue Adaptive | |
| JP6042879B2 (en) | Apparatus for generating an assignment between an image region and an element class of an image | |
| CN104574292A (en) | CT image correcting method and device | |
| JP6967983B2 (en) | Image processing equipment, image processing methods, and programs | |
| CN112200780B (en) | Bone tissue positioning method, device, computer equipment and storage medium | |
| CN109640824B (en) | Medical Image Reconstruction with Model Regularized Motion Compensation | |
| CN114037803B (en) | Medical image three-dimensional reconstruction method and system | |
| CN115564858A (en) | A metal artifact correction method, system and X-ray image reconstruction method | |
| WO2023138273A1 (en) | Image enhancement method and system | |
| CN110301928A (en) | Rebuild the method, apparatus and system of PET image | |
| CN114943780A (en) | Image reconstruction processing method and system and medical imaging equipment | |
| CN107292816B (en) | An image correction method, system and computer readable medium | |
| JP5602142B2 (en) | Objects and methods for patient-specific anatomical sketches for medical reports | |
| CN113393500B (en) | Spine scanning parameter acquisition method, device, equipment and storage medium | |
| US10074198B2 (en) | Methods and apparatuses for image processing and display | |
| JP7387280B2 (en) | Image processing device, image processing method and program | |
| CN111062998B (en) | Image reconstruction method, device, CT system and storage medium | |
| CN115910288A (en) | Medical image processing method, device and system | |
| JP6732593B2 (en) | Image processing apparatus and image processing method | |
| CN113344942A (en) | Human body massage region segmentation method, device and system and computer storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 201807 Shanghai City, north of the city of Jiading District Road No. 2258 Applicant after: Shanghai Lianying Medical Technology Co., Ltd Address before: 201807 Shanghai City, north of the city of Jiading District Road No. 2258 Applicant before: SHANGHAI UNITED IMAGING HEALTHCARE Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |