Image display method and system with segmentation guiding function

Abstract

The invention relates to the technical field of image analysis, in particular to an image display method and system with a segmentation guiding function, and the method comprises the steps: 1, transmitting a to-be-analyzed image to an image display region, and forming a region image; step 2, performing feature segmentation on the regional image to obtain a first-level feature map; 3, performing region segmentation on the first-level feature map to obtain a second-level feature map; 4, performing static comparison on the second-level feature map; step 5, executing local export of the secondary feature map according to a static comparison result to obtain an independent comparison analysis map; step 6, performing dynamic comparison on the second-level feature map to obtain a comparison result; and step 7, ending the execution, and storing the comparison image. Compared with the prior art, medical staff can conveniently and quickly carry out comparative analysis on the corresponding medical images, meanwhile, dynamic analysis is introduced, a simple image feature analysis mode in a dynamic mode is provided in an auxiliary mode, and diversification of analysis means of the medical staff is achieved.

Description

Technical Field

[0001] The present application relates to the field of image analysis technology, and in particular to an image display method with guided segmentation function, and also to a system. Background Art

[0002] Medical imaging equipment is an extremely important part of image processing equipment in medical equipment. The use of this equipment has greatly helped medical staff to improve the efficiency and accuracy of diagnosis of diseases with specific forms. Some diseases and the forms of diseases on the body can be directly observed through images, and it also facilitates researchers to conduct in-depth research on diseases. However, in the prior art, images are taken in the form of a whole sheet for medical staff to watch. It can be seen that such a large-scale image requires a lot of time for doctors to interpret, and doctors cannot compare and interpret specific areas when interpreting images.

[0003] There is a technology now with an authorization announcement number of CN110942447B and an authorization announcement date of July 21, 2023. It is named a Chinese invention patent for OCT image segmentation method, device, equipment and storage medium. It discloses parsing, segmenting and displaying OCT images based on a denoising model, segmentation model and graphic recognition model, extraction and display of thumbnails, switching display and saving of image denoising results, and CVI calculation and display of custom drawing areas.

[0004] The OCT image segmentation method of the aforementioned solution realizes the detailed segmentation of the OCT image and improves the accuracy of image segmentation. However, there is still a problem that contrast processing cannot be performed for specific regionalized images. Summary of the invention

[0005] The purpose of the present application is to provide an image display method and system with a guided segmentation function, which solves the technical problem that the prior art cannot provide a method and system that can realize the comparison and specific area segmentation of medical data images through comparative analysis of the primary feature map and the secondary feature map.

[0006] According to one aspect of the present application, there is provided an image display method with a guided segmentation function, comprising: step 1. transferring an image to be analyzed to an image display area to form a regional image; step 2. performing at least one feature segmentation on the regional image to obtain at least one primary feature map; step 3. performing regional segmentation on at least one primary feature map to obtain at least one secondary feature map; step 4. performing static comparison on at least one secondary feature map, and if a comparison result is obtained, executing step 5; if no comparison result is obtained, executing step 6; step 5. performing local export of at least one secondary feature map according to the static comparison result to obtain a separate comparison analysis map; step 6. performing dynamic comparison on at least one secondary feature map to obtain a comparison result; step 7. execution ends and the comparison image is saved.

[0007] In some embodiments, the step 1 is specifically as follows: uploading the local storage repository to the system material storage repository, and presenting the image in the system image display area after uploading.

[0008] In some embodiments, the step 2 is specifically as follows: step 2.1. performing image feature extraction on the regional image and mirroring the extracted image features; step 2.2. performing coordinate zeroing processing on the mirrored image; step 2.3. performing color inspection on the mirrored image; step 2.4. obtaining a primary feature map.

[0009] In some embodiments, the step 3 is specifically as follows: step 3.1. locating a specific feature of the primary feature map; step 3.2. limiting the coordinates of the located specific feature to determine the target image for comparison; step 3.3. storing the target image to form an image copy; and step 3.4. obtaining a secondary feature map.

[0010] In some embodiments, step 4 is specifically as follows: step 4.1. Compare the secondary feature map with the standard image to obtain the difference points; step 4.2. Use a histogram to perform image difference point comparison to determine whether the images are similar. If they are similar, execute step 5; if they are not similar, execute step 6.

[0011] In some embodiments, step 5 specifically includes: performing local export of similar images to obtain a separate comparative analysis graph.

[0012] In some embodiments, step 6 specifically includes: performing dynamic comparison, using a convolutional neural network to perform image feature comparison, and obtaining a comparison result.

[0013] According to another aspect of the present application, there is provided an image display system with a guided segmentation function, comprising:

[0014] A receiving unit, the receiving unit is used to transmit the image to be analyzed to the image display area to form a regional image;

[0015] A segmentation unit, the segmentation unit is used to perform at least one feature segmentation on the regional image to obtain at least one primary feature map;

[0016] A sub-segmentation unit, the sub-segmentation unit is used to perform region segmentation on at least one primary feature map to obtain at least one secondary feature map;

[0017] A static comparison unit, the static comparison unit is used to perform static comparison on at least one secondary feature map;

[0018] An export unit, the export unit is used to perform local export of at least one secondary feature map according to the static comparison result to obtain a separate comparison analysis map;

[0019] A dynamic comparison unit is used to perform dynamic comparison on at least one secondary feature map to obtain a comparison result.

[0020] Compared with the prior art, the present application has the following advantages and beneficial effects: the present application processes the primary feature map for specific features to obtain the secondary feature map and then performs comparison, which is different from the prior art which simply performs single-map analysis. The present application makes it more convenient for medical staff to quickly perform comparative analysis of corresponding medical images; at the same time, dynamic analysis is introduced to assist in providing a simple dynamic analysis method for image features, thereby realizing the diversification of medical staff's analysis methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 is a flow chart of the image display method of the present application;

[0023] Figure 2 It is a module diagram of the image display system of the present application.

[0024] Legend:

[0025] none. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0027] This embodiment provides an image display method and system with guided segmentation function. The image display method and system are already in the testing stage. Figure 1-2 Describe them together.

[0028] It should be noted that the present application is optimized based on the existing medical image analysis system. Therefore, the parts that are the same as the existing medical image analysis system will not be repeated, including but not limited to the laser microdissection three-point positioning system.

[0029] Method Embodiment

[0030] refer to Figure 1 , this embodiment provides an image display method with guided segmentation function, specifically:

[0031] First, in step 1, relevant personnel input the image to be analyzed into the image display area, and the system will form a regional image according to a preset program, specifically: the local repository is uploaded to the system material repository, and after uploading, the image is presented in the system image display area.

[0032] Next, in step 2, feature segmentation is performed on the regional image at least once to obtain at least one primary feature map, specifically:

[0033] Step 2.1. Perform image feature extraction on the regional image, and perform mirroring on the extracted image features;

[0034] Step 2.2. Perform coordinate zeroing processing on the mirror image;

[0035] Step 2.3. Perform a color check on the mirror image;

[0036] Step 2.4. Get the first-level feature map.

[0037] It should be noted that the processing algorithms used for feature segmentation in this embodiment include the optimal threshold method and the threshold segmentation method. The coordinate zeroing process for the mirror image is specifically: the mirror image is aligned with the zero point coordinate of the mirror display area. Furthermore, the median cut algorithm is used when performing color inspection. The above methods and algorithms are known algorithms, so they will not be described here.

[0038] Further, in step 3, region segmentation is performed on at least one primary feature map to obtain at least one secondary feature map, specifically:

[0039] Step 3.1. Perform specific feature localization of the first-level feature map;

[0040] Step 3.2. Implement coordinate limiting on the specific features to determine the comparison target image;

[0041] Step 3.3. Store the target image to form an image copy;

[0042] Step 3.4. Get the secondary feature map.

[0043] It should be noted that in step 3.1, the features that need to be selected and analyzed in the primary feature map are selected. The features can be part of the features in the pathological section or other influencing features. The type of feature is determined by the department using it. After completing the above steps, the feature positioning process is realized. In step 3.2., after determining the features, coordinate limiting is performed on the located specific features. In other words, the image of the area where the feature is located is delineated, and then the comparison target image is determined. In order to ensure the integrity of the target image and to place the original file that needs to be found for subsequent operations, the target image is stored and a copy of the image is formed.

[0044] Furthermore, in step 4, static comparison is performed on at least one secondary feature map. If a comparison result is obtained, step 5 is executed; if no comparison result is obtained, step 6 is executed, which is specifically:

[0045] Step 4.1. Compare the secondary feature map with the standard image to obtain the difference points;

[0046] Step 4.2. Use the histogram to perform image difference point comparison to determine whether the images are similar. If they are similar, proceed to step 5; if they are not similar, proceed to step 6.

[0047] Furthermore, in step 5, local export of at least one secondary feature map is performed according to the static comparison result to obtain a separate comparison analysis map, specifically:

[0048] Perform partial export of similar images to obtain separate comparative analysis graphs. The export process is common image export, such as image export of Photoshop software, etc.

[0049] Finally, in step 6, a dynamic comparison is performed on at least one secondary feature map to obtain a comparison result, specifically:

[0050] Perform dynamic comparison, use convolutional neural network to perform image feature comparison, and obtain comparison results. The processing of convolutional neural network is an existing image feature processing method, which will not be described here.

[0051] In summary, after the above steps are executed, the execution is terminated and the comparison image is saved.

[0052] System Example

[0053] refer to Figure 2In order to better understand the present application, a system corresponding to the above method is now provided. The system is based on the method of the present application and has an image display system with guided segmentation function, including:

[0054] A receiving unit, the receiving unit is used to transmit the image to be analyzed to the image display area to form a regional image;

[0055] A segmentation unit, the segmentation unit is used to perform at least one feature segmentation on the regional image to obtain at least one primary feature map;

[0056] A sub-segmentation unit, the sub-segmentation unit is used to perform region segmentation on at least one primary feature map to obtain at least one secondary feature map;

[0057] A static comparison unit, the static comparison unit is used to perform static comparison on at least one secondary feature map;

[0058] An export unit, the export unit is used to perform local export of at least one secondary feature map according to the static comparison result to obtain a separate comparison analysis map;

[0059] The dynamic comparison unit is used to perform dynamic comparison on at least one secondary feature map to obtain a comparison result.

[0060] The above shows and describes the basic principles and main features of the present application and the advantages of the present application. For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or basic features of the present application. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present application is defined by the attached claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved.

[0061] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. An image display method with guided segmentation function, characterized in that: Step 1. Input the image to be analyzed into the image display area to form a regional image; Step 2. Perform at least one feature segmentation on the regional image to obtain at least one primary feature map; Step 3. Perform region segmentation on at least one primary feature map to obtain at least one secondary feature map; Step 4. Perform static comparison on at least one secondary feature map. If a comparison result is obtained, execute step 5; if no comparison result is obtained, execute step 6; Step 5. Perform local export of at least one secondary feature map according to the static comparison result to obtain a separate comparison analysis map; Step 6. Perform dynamic comparison on at least one secondary feature map to obtain a comparison result; Step 7. Execution ends and the comparison image is saved.

2. The image display method according to claim 1, characterized in that: The step 1 is specifically as follows: the local storage repository is uploaded to the system material storage repository, and after the upload, the image is presented in the system image display area.

3. The image display method according to claim 1, characterized in that: The step 2 is specifically as follows: Step 2.

1. Perform image feature extraction on the regional image, and perform mirroring on the extracted image features; Step 2.

2. Perform coordinate zeroing processing on the mirror image; Step 2.

3. Perform a color check on the mirror image; Step 2.

4. Get the first-level feature map.

4. The image display method according to claim 1, characterized in that: The step 3 is specifically as follows: Step 3.

1. Perform specific feature localization of the first-level feature map; Step 3.

2. Implement coordinate limiting on the specific features to determine the comparison target image; Step 3.

3. Store the target image to form an image copy; Step 3.

4. Get the secondary feature map.

5. The image display method according to claim 1, characterized in that: The step 4 is specifically as follows: Step 4.

1. Compare the secondary feature map with the standard image to obtain the difference points; Step 4.

2. Use the histogram to perform image difference point comparison to determine whether the images are similar. If they are similar, proceed to step 5; if they are not similar, proceed to step 6.

6. The image display method according to claim 1, characterized in that: The step 5 is specifically as follows: Perform local export of similar images to obtain separate comparative analysis images.

7. The image display method according to claim 1, characterized in that: The step 6 is specifically as follows: Perform dynamic comparison and use convolutional neural network to perform image feature comparison to obtain comparison results.

8. An image display system with guided segmentation function, characterized in that: include: A receiving unit, the receiving unit is used to transmit the image to be analyzed to the image display area to form a regional image; A segmentation unit, the segmentation unit is used to perform at least one feature segmentation on the regional image to obtain at least one primary feature map; A sub-segmentation unit, the sub-segmentation unit is used to perform region segmentation on at least one primary feature map to obtain at least one secondary feature map; A static comparison unit, the static comparison unit is used to perform static comparison on at least one secondary feature map; An export unit, the export unit is used to perform local export of at least one secondary feature map according to the static comparison result to obtain a separate comparison analysis map; A dynamic comparison unit is used to perform dynamic comparison on at least one secondary feature map to obtain a comparison result.

Images