Combined liver and gallbladder medical image processing and analyzing software system
Through the combination of graph threshold segmentation algorithm and deep learning model, the problems of segmentation error and threshold adjustment in the hepatobiliary medical image processing system are solved, better cutting effect and diagnostic report generation are achieved, and diagnostic accuracy and efficiency are improved.
Patent Information
- Application Number
- CN202411020120.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-29
- Publication Date
- 2024-11-15
AI Technical Summary
The existing hepatobiliary medical image processing and analysis software systems are prone to segmentation errors during the image segmentation process, and cannot automatically adjust the threshold value, resulting in poor cutting effect.
The graph threshold segmentation algorithm and deep learning model are used to segment and correct the liver and gallbladder organs, and the segmentation results are optimized through dynamic threshold calculation and CRF (cyclic random field) model, and a diagnostic report is generated in combination with morphological analysis and three-dimensional visualization technology.
Automatic adjustment and optimization during the segmentation process is realized, cutting effect is improved, detailed three-dimensional models and structured reports are generated, and diagnostic accuracy and efficiency are enhanced.
Smart Images

Figure CN118967927A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of medical image processing, and in particular relates to a combined hepatobiliary medical image processing and analysis software system. Background Art
[0002] The hepatobiliary medical image processing and analysis software system is a software system specifically used to process and analyze liver and bile duct related imaging data. This type of software system is designed to improve the accuracy and efficiency of doctors' diagnosis of liver and bile duct diseases, provide reliable auxiliary tools for clinical decision-making, and promote the digitalization and intelligent management of medical information.
[0003] The existing hepatobiliary medical image processing and analysis software system is prone to segmentation errors during image segmentation and cannot be adjusted automatically. In addition, the cutting process is relatively rigid and the threshold cannot be adjusted, resulting in poor cutting effects. Summary of the invention
[0004] In view of the deficiencies in the prior art, the present invention provides a combined hepatobiliary medical image processing and analysis software system to solve the above technical problems.
[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a combined hepatobiliary medical image processing, the image processing steps are: S1: obtaining medical image data of the hepatobiliary system through CT scanning, MRI and ultrasound equipment, and preprocessing the original image; S2: using an image segmentation algorithm to segment the hepatobiliary organs, analyzing the segmentation results, and if the results do not meet expectations, the system automatically corrects; S3: using morphological analysis to perform lesion detection and quantitative analysis, and automatically detecting abnormal lesions in the image; S4: based on the segmented image data, generating a three-dimensional model of the liver and gallbladder, and providing a three-dimensional visualization effect; S5: combining the analysis results and clinical data, generating an auxiliary diagnosis report, providing detailed analysis results and suggestions, and automatically generating a structured image report; S6: safely storing the processed image data and analysis results, integrating them with the hospital information system, and sharing and managing medical information.
[0006] Preferably, the step of S1 is:
[0007] Through X-ray scanning, a large number of cross-sectional images are generated to construct three-dimensional images, and magnetic resonance technology is used to obtain detailed information on tissue structure and function, and high-frequency sound waves are used to form images inside the liver and gallbladder;
[0008] After acquiring the original image, denoising is performed to reduce the noise in the image and improve the image quality. The image is smoothed by filtering technology, the contrast of the image is adjusted, the details and structure in the image are highlighted, and grayscale standardization is performed to make the grayscale levels of different images comparable under the same standard.
[0009] Spatial and temporal alignment of images acquired at different times and with different devices;
[0010] Convert image data acquired by different devices into a unified format for unified processing and analysis;
[0011] For images that require three-dimensional reconstruction, stereoscopic images are reconstructed;
[0012] Perform quality control and image verification on the preprocessed images.
[0013] Preferably, the step of S2 is:
[0014] Use the graph threshold segmentation algorithm to segment the liver and gallbladder organ areas;
[0015] Establish segmentation image analysis and recognition model;
[0016] Check the accuracy of the segmentation, the clarity of the boundaries, and any incorrectly segmented areas;
[0017] The system identifies bad types of segmentation results, including over-segmentation, under-segmentation and blurred boundaries.
[0018] Based on the results of the analysis, the system selects a correction strategy;
[0019] Threshold adjustment: Set the dynamic threshold. The dynamic threshold calculation formula is:
[0020] [Y min =μ-k·σ]
[0021] [Y max =μ+k·σ]
[0022] Among them, Y min is the minimum value of the impact factor, Y max is the minimum value of the impact factor, μ is the average value of the impact factor, k is the multiple adjusted as needed, which is 1 and 2, and σ is the standard deviation;
[0023] Deep learning correction: Use deep learning models to correct and fine-tune segmentation results;
[0024] Given an input image I, the initial segmentation result S init , the goal of CRF is to optimize the segmentation result S:
[0025] [S=CRF(S init ,I)]
[0026] The specific form of the CRF formula is:
[0027] Where E(S,I) is the energy function and Z is the normalization constant used to ensure that the sum of the probability distribution is 1;
[0028] The system automatically applies the selected correction strategy and reprocesses the image data;
[0029] After correction, the system re-evaluates the segmentation results.
[0030] Preferably, the step of S2 is:
[0031] Use the graph threshold segmentation algorithm to segment the liver and gallbladder organ areas;
[0032] Establish segmentation image analysis and recognition model;
[0033] Check the accuracy of the segmentation, the clarity of the boundaries, and any incorrectly segmented areas;
[0034] The system identifies bad types of segmentation results, including over-segmentation, under-segmentation and blurred boundaries.
[0035] Based on the results of the analysis, the system selects a correction strategy;
[0036] Threshold adjustment: Set the dynamic threshold. The dynamic threshold calculation formula is:
[0037] [Y min =μ-k·σ]
[0038] [Y max =μ+k·σ]
[0039] Among them, Y min is the minimum value of the impact factor, Y max is the minimum value of the impact factor, μ is the average value of the impact factor, k is the multiple adjusted as needed, which is 1 and 2, and σ is the standard deviation;
[0040] Deep learning correction: Use deep learning models to correct and fine-tune segmentation results;
[0041] Given an input image I, the initial segmentation result S init , the goal of CRF is to optimize the segmentation result S:
[0042] [S=CRF(S init ,I)]
[0043] The specific form of the CRF formula is:
[0044] Where E(S,I) is the energy function and Z is the normalization constant used to ensure that the sum of the probability distribution is 1;
[0045] The system automatically applies the selected correction strategy and reprocesses the image data;
[0046] After correction, the system re-evaluates the segmentation results.
[0047] Preferably, the step of S3 is:
[0048] Perform feature extraction, calculate the area, perimeter and shape characteristics of the lesion area, and perform quantitative analysis;
[0049] Quantitatively analyze the location, size and shape of the lesion based on the results of morphological operations and feature extraction;
[0050] The detected lesion areas are analyzed and compared and verified with medical experts.
[0051] Preferably, the step of S4 is:
[0052] Converting the segmented 2D image data into 3D volume data is achieved by stacking the 2D slices to form a 3D volume, where each volume contains information about its spatial position and grayscale value;
[0053] Using volume rendering and volume data surface extraction algorithms, the three-dimensional volume data are converted into surface models of the liver and gallbladder;
[0054] Processing of the surface mesh extracted from the volume data, including smoothing and removal of small geometric errors or noise;
[0055] There is color information available, which is mapped onto the generated three-dimensional model;
[0056] Use 3D visualization software to load and visually present the processed 3D model;
[0057] Generate final 3D model images and videos, and record relevant processing steps and results for further analysis and reporting.
[0058] Preferably, the step of S5 is:
[0059] The data obtained from the imaging analysis are combined with clinical data to map the location of the lesion onto the patient’s anatomy;
[0060] Design report templates including title, patient information, imaging data summary, analysis results, and recommendations;
[0061] Use natural language generation technology to generate report text based on the filled data;
[0062] Perform quality control on generated reports, including grammar checking, logical consistency checking, and clinical plausibility review;
[0063] The generated structured report is exported in the format of a PDF document.
[0064] Preferably, the step of S6 is:
[0065] Store processed image data and analysis results in a secure data storage system;
[0066] Convert data into standardized medical imaging formats;
[0067] Design and implement data connections and interfaces for integration with hospital information systems, including ensuring security and consistency of data transmission, and complying with standards and regulations for healthcare information technology;
[0068] Implement authentication and access control measures;
[0069] Develop data sharing and management strategies, including determining who has the right to access, use and share data;
[0070] Perform integration testing and verification to ensure that the processed imaging data and analysis results can be correctly integrated into the hospital information system.
[0071] A combined hepatobiliary medical image analysis software system comprises: an image acquisition module, an image segmentation module, a lesion detection module, a three-dimensional visualization module, a report production module and a data storage module.
[0072] Preferably, the image acquisition module: the image acquisition module is used to acquire medical image data of the hepatobiliary system and pre-process the original image;
[0073] Image segmentation module: The image segmentation module is electrically connected to the image acquisition module, and is used to segment the liver and gallbladder organs and analyze and correct the segmentation results.
[0074] Lesion detection module: The lesion detection module is electrically connected to the image segmentation module and the image acquisition module. The lesion detection module is used to perform lesion detection and quantitative analysis using morphological analysis to automatically detect abnormal lesions in the image;
[0075] Three-dimensional visualization module: The three-dimensional visualization module is electrically connected to the lesion detection module, the image segmentation module and the image acquisition module, and the three-dimensional visualization module is used to provide a three-dimensional visualization effect based on the segmented image data;
[0076] Report production module and data storage module: The report production module and data storage module are electrically connected to the three-dimensional visualization module and the lesion detection module. The report production module and data storage module are used to safely store the processed image data and analysis results, integrate with the hospital information system, and share and manage medical information.
[0077] Preferably, users of hospital information systems are trained, technical support is provided, and a continuous monitoring mechanism is established to regularly review the security and efficiency of data sharing and integration.
[0078] Compared with the prior art, the present invention has the following beneficial effects:
[0079] By constructing a segmentation model, the present application can automatically adjust the image when segmentation errors occur during the segmentation process, and can adjust the threshold, resulting in better cutting effects. BRIEF DESCRIPTION OF THE DRAWINGS
[0080] Figure 1 This is a cloud system framework diagram of the present invention;
[0081] Figure 2 This is a diagram of the operation steps of the cloud system of the present invention. DETAILED DESCRIPTION
[0082] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0083] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making any creative work shall fall within the scope of protection of the present invention.
[0084] The present invention provides a technical solution: a combined hepatobiliary medical image processing, the image processing steps are:
[0085] S1: Obtain medical imaging data of the hepatobiliary system through CT scanning, MRI and ultrasound equipment, and pre-process the original images;
[0086] S2: Use image segmentation algorithm to segment the liver and gallbladder organs, analyze the segmentation results, and if the results do not meet expectations, the system will automatically correct them;
[0087] S3: Use morphological analysis for lesion detection and quantitative analysis to automatically detect abnormal lesions in images;
[0088] S4: Generate a three-dimensional model of the liver and gallbladder based on the segmented image data to provide a three-dimensional visualization effect;
[0089] S5: Combine analysis results and clinical data to generate auxiliary diagnosis reports, provide detailed analysis results and suggestions, and automatically generate structured imaging reports;
[0090] S6: Safely store processed imaging data and analysis results and integrate them with hospital information systems to share and manage medical information.
[0091] Furthermore, the steps of S1 are:
[0092] Through X-ray scanning, a large number of cross-sectional images are generated to construct three-dimensional images, and magnetic resonance technology is used to obtain detailed information on tissue structure and function, and high-frequency sound waves are used to form images inside the liver and gallbladder;
[0093] After acquiring the original image, denoising is performed to reduce the noise in the image and improve the image quality. The image is smoothed by filtering technology, the contrast of the image is adjusted, the details and structure in the image are highlighted, and grayscale standardization is performed to make the grayscale levels of different images comparable under the same standard.
[0094] Spatial and temporal alignment of images acquired at different times and with different devices;
[0095] Convert image data acquired by different devices into a unified format for unified processing and analysis;
[0096] For images that require three-dimensional reconstruction, stereoscopic images are reconstructed;
[0097] Perform quality control and image verification on the preprocessed images.
[0098] Furthermore, the steps of S2 are:
[0099] Use the graph threshold segmentation algorithm to segment the liver and gallbladder organ areas;
[0100] Establish segmentation image analysis and recognition model;
[0101] Check the accuracy of the segmentation, the clarity of the boundaries, and any incorrectly segmented areas;
[0102] The system identifies bad types of segmentation results, including over-segmentation, under-segmentation and blurred boundaries.
[0103] Based on the results of the analysis, the system selects a correction strategy;
[0104] Threshold adjustment: Set the dynamic threshold. The dynamic threshold calculation formula is:
[0105] [Y min =μ-k·σ]
[0106] [Y max =μ+k·σ]
[0107] Among them, Y min is the minimum value of the impact factor, Y maxis the minimum value of the impact factor, μ is the average value of the impact factor, k is the multiple adjusted as needed, which is 1 and 2, and σ is the standard deviation;
[0108] Deep learning correction: Use deep learning models to correct and fine-tune segmentation results;
[0109] Given an input image I, the initial segmentation result S init , the goal of CRF is to optimize the segmentation result S:
[0110] [S=CRF(S init ,I)]
[0111] The specific form of the CRF formula is:
[0112] Where E(S,I) is the energy function and Z is the normalization constant used to ensure that the sum of the probability distribution is 1;
[0113] The system automatically applies the selected correction strategy and reprocesses the image data;
[0114] After correction, the system re-evaluates the segmentation results.
[0115] Furthermore, the steps of S2 are:
[0116] Use the graph threshold segmentation algorithm to segment the liver and gallbladder organ areas;
[0117] Establish segmentation image analysis and recognition model;
[0118] Check the accuracy of the segmentation, the clarity of the boundaries, and any incorrectly segmented areas;
[0119] The system identifies bad types of segmentation results, including over-segmentation, under-segmentation and blurred boundaries.
[0120] Based on the results of the analysis, the system selects a correction strategy;
[0121] Threshold adjustment: Set the dynamic threshold. The dynamic threshold calculation formula is:
[0122] [Y min =μ-k·σ]
[0123] [Y max =μ+k·σ]
[0124] Among them, Y min is the minimum value of the impact factor, Y max is the minimum value of the impact factor, μ is the average value of the impact factor, k is the multiple adjusted as needed, which is 1 and 2, and σ is the standard deviation;
[0125] Deep learning correction: Use deep learning models to correct and fine-tune segmentation results;
[0126] Given an input image I, the initial segmentation result S init , the goal of CRF is to optimize the segmentation result S:
[0127] [S = CRF (S init ,I)]
[0128] The specific form of the CRF formula is:
[0129] Where E(S,I) is the energy function and Z is the normalization constant used to ensure that the sum of the probability distribution is 1;
[0130] The system automatically applies the selected correction strategy and reprocesses the image data;
[0131] After correction, the system re-evaluates the segmentation results.
[0132] Furthermore, the steps of S3 are:
[0133] Perform feature extraction, calculate the area, perimeter and shape characteristics of the lesion area, and perform quantitative analysis;
[0134] Quantitatively analyze the location, size and shape of the lesion based on the results of morphological operations and feature extraction;
[0135] The detected lesion areas are analyzed and compared and verified with medical experts.
[0136] Furthermore, the steps of S4 are:
[0137] Converting the segmented 2D image data into 3D volume data is achieved by stacking the 2D slices to form a 3D volume, where each volume contains information about its spatial position and grayscale value;
[0138] Using volume rendering and volume data surface extraction algorithms, the three-dimensional volume data are converted into surface models of the liver and gallbladder;
[0139] Processing of the surface mesh extracted from the volume data, including smoothing and removal of small geometric errors or noise;
[0140] There is color information available, which is mapped onto the generated three-dimensional model;
[0141] Use 3D visualization software to load and visually present the processed 3D model;
[0142] Generate final 3D model images and videos, and record relevant processing steps and results for further analysis and reporting.
[0143] Furthermore, the steps of S5 are:
[0144] The data obtained from the imaging analysis are combined with clinical data to map the location of the lesion onto the patient’s anatomy;
[0145] Design report templates including title, patient information, imaging data summary, analysis results, and recommendations;
[0146] Use natural language generation technology to generate report text based on the filled data;
[0147] Perform quality control on generated reports, including grammar checking, logical consistency checking, and clinical plausibility review;
[0148] The generated structured report is exported in the format of a PDF document.
[0149] Furthermore, the steps of S6 are:
[0150] Store processed image data and analysis results in a secure data storage system;
[0151] Convert data into standardized medical imaging formats;
[0152] Design and implement data connections and interfaces for integration with hospital information systems, including ensuring security and consistency of data transmission, and complying with standards and regulations for healthcare information technology;
[0153] Implement authentication and access control measures;
[0154] Develop data sharing and management strategies, including determining who has the right to access, use and share data;
[0155] Perform integration testing and verification to ensure that the processed imaging data and analysis results can be correctly integrated into the hospital information system.
[0156] A combined hepatobiliary medical image analysis software system comprises: an image acquisition module, an image segmentation module, a lesion detection module, a three-dimensional visualization module, a report production module and a data storage module.
[0157] Further, the image acquisition module: the image acquisition module is used to acquire medical image data of the hepatobiliary system and pre-process the original image;
[0158] Image segmentation module: The image segmentation module is electrically connected to the image acquisition module, and is used to segment the liver and gallbladder organs and analyze and correct the segmentation results.
[0159] Lesion detection module: The lesion detection module is electrically connected to the image segmentation module and the image acquisition module. The lesion detection module is used to perform lesion detection and quantitative analysis using morphological analysis to automatically detect abnormal lesions in the image;
[0160] Three-dimensional visualization module: The three-dimensional visualization module is electrically connected to the lesion detection module, the image segmentation module and the image acquisition module, and the three-dimensional visualization module is used to provide a three-dimensional visualization effect based on the segmented image data;
[0161] Report production module and data storage module: The report production module and data storage module are electrically connected to the three-dimensional visualization module and the lesion detection module. The report production module and data storage module are used to safely store the processed image data and analysis results, integrate with the hospital information system, and share and manage medical information.
[0162] Furthermore, users of hospital information systems should be trained, technical support should be provided, and a continuous monitoring mechanism should be established to regularly review the security and efficiency of data sharing and integration.
[0163] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.
[0164] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A combined hepatobiliary medical image processing, characterized in that: The image processing steps are: S1: Obtain medical imaging data of the hepatobiliary system through CT scanning, MRI and ultrasound equipment, and pre-process the original images; S2: Use image segmentation algorithm to segment the liver and gallbladder organs, analyze the segmentation results, and if the results do not meet expectations, the system will automatically correct them; S3: Use morphological analysis for lesion detection and quantitative analysis to automatically detect abnormal lesions in images; S4: Generate a three-dimensional model of the liver and gallbladder based on the segmented image data to provide a three-dimensional visualization effect; S5: Combine analysis results and clinical data to generate auxiliary diagnosis reports, provide detailed analysis results and suggestions, and automatically generate structured imaging reports; S6: Safely store processed imaging data and analysis results and integrate them with hospital information systems to share and manage medical information.
2. The combined hepatobiliary medical image processing according to claim 1, characterized in that: The steps of S1 are: Through X-ray scanning, a large number of cross-sectional images are generated to construct three-dimensional images, and magnetic resonance technology is used to obtain detailed information on tissue structure and function, and high-frequency sound waves are used to form images inside the liver and gallbladder; After acquiring the original image, denoising is performed to reduce the noise in the image and improve the image quality. The image is smoothed by filtering technology, the contrast of the image is adjusted, the details and structure in the image are highlighted, and grayscale standardization is performed to make the grayscale levels of different images comparable under the same standard. Spatial and temporal alignment of images acquired at different times and with different devices; Convert image data acquired by different devices into a unified format for unified processing and analysis; For images that require three-dimensional reconstruction, stereoscopic images are reconstructed; Perform quality control and image verification on the preprocessed images.
3. The combined hepatobiliary medical image processing according to claim 1, characterized in that: The steps of S2 are: Use the graph threshold segmentation algorithm to segment the liver and gallbladder organ areas; Establish segmentation image analysis and recognition model; Check the accuracy of the segmentation, the clarity of the boundaries, and any incorrectly segmented areas; The system identifies bad types of segmentation results, including over-segmentation, under-segmentation and blurred boundaries. Based on the results of the analysis, the system selects a correction strategy; Threshold adjustment: Set the dynamic threshold. The dynamic threshold calculation formula is: [Y min =μ-k·σ] [Y max =μ+k·σ] Among them, Y min is the minimum value of the impact factor, Y max is the minimum value of the impact factor, μ is the average value of the impact factor, k is the multiple adjusted as needed, which is 1 and 2, and σ is the standard deviation; Deep learning correction: Use deep learning models to correct and fine-tune segmentation results; Given an input image I, the initial segmentation result S init , the goal of CRF is to optimize the segmentation result S: [S=CRF(S init ,I)] The specific form of the CRF formula is: Where E(S,I) is the energy function and Z is the normalization constant used to ensure that the sum of the probability distribution is 1; The system automatically applies the selected correction strategy and reprocesses the image data; After correction, the system re-evaluates the segmentation results.
4. The combined hepatobiliary medical image processing according to claim 1, characterized in that: The steps of S3 are: Perform feature extraction, calculate the area, perimeter and shape characteristics of the lesion area, and perform quantitative analysis; Quantitatively analyze the location, size and shape of the lesion based on the results of morphological operations and feature extraction; The detected lesion areas are analyzed and compared and verified with medical experts.
5. The combined hepatobiliary medical image processing according to claim 1, characterized in that: The steps of S4 are: Converting the segmented 2D image data into 3D volume data is achieved by stacking the 2D slices to form a 3D volume, where each volume contains information about its spatial position and grayscale value; There is color information available, which is mapped onto the generated three-dimensional model; Generate final 3D model images and videos, and record relevant processing steps and results for further analysis and reporting.
6. The combined hepatobiliary medical image processing according to claim 1, characterized in that: The steps of S5 are: The data obtained from the imaging analysis are combined with clinical data to map the location of the lesion onto the patient’s anatomy; Design report templates including title, patient information, imaging data summary, analysis results, and recommendations; Use natural language generation technology to generate report text based on the filled data; Perform quality control on generated reports, including grammar checking, logical consistency checking, and clinical plausibility review; The generated structured report is exported in the format of a PDF document.
7. The combined hepatobiliary medical image processing according to claim 1, characterized in that: The steps of S6 are: Store processed image data and analysis results in a secure data storage system; Convert data into standardized medical imaging formats; Design and implement data connections and interfaces for integration with hospital information systems, including ensuring security and consistency of data transmission, and complying with standards and regulations for healthcare information technology; Implement authentication and access control measures; Develop data sharing and management strategies, including determining who has the right to access, use and share data; Perform integration testing and verification to ensure that the processed imaging data and analysis results can be correctly integrated into the hospital information system.
8. A combined hepatobiliary medical image analysis software system, characterized in that: The analysis software system includes: image acquisition module, image segmentation module, lesion detection module, 3D visualization module, report production module and data storage module.
9. The combined hepatobiliary medical image analysis software system according to claim 8, characterized in that: Image acquisition module: The image acquisition module is used to acquire medical image data of the hepatobiliary system and pre-process the original images; Image segmentation module: The image segmentation module is electrically connected to the image acquisition module, and is used to segment the liver and gallbladder organs and analyze and correct the segmentation results. Lesion detection module: The lesion detection module is electrically connected to the image segmentation module and the image acquisition module. The lesion detection module is used to perform lesion detection and quantitative analysis using morphological analysis to automatically detect abnormal lesions in the image; Three-dimensional visualization module: The three-dimensional visualization module is electrically connected to the lesion detection module, the image segmentation module and the image acquisition module, and the three-dimensional visualization module is used to provide a three-dimensional visualization effect based on the segmented image data; Report production module and data storage module: The report production module and data storage module are electrically connected to the three-dimensional visualization module and the lesion detection module. The report production module and data storage module are used to safely store the processed image data and analysis results, integrate with the hospital information system, and share and manage medical information.
10. The combined hepatobiliary medical image analysis software system according to claim 8, characterized in that: Train users of hospital information systems, provide technical support, establish continuous monitoring mechanisms, and regularly review the security and efficiency of data sharing and integration.
Citation Information
Cited By
Liver and gall CT image processing method and system
CN119941692A
A method and system for processing hepatobiliary CT images
CN119941692B
Medical image intelligent teaching platform based on AI
CN121506405A
An AI-based medical image intelligent teaching platform
CN121506405B
