A tumor CT image segmentation processing method and system

Abstract

The present application relates to the technical field of tumor image analysis, in particular to a tumor CT image segmentation processing method and system, comprising the following steps: based on the CT image of the patient's tumor, adjusting the image processing parameters to enhance the image, extracting various image feature information of the medical image, and generating an image enhancement processing result.In the present application, the image is enhanced by adjusting the contrast and brightness of the image, which improves the visual quality of the image, provides a clearer basis for subsequent edge detection, improves the accuracy of edge detection, segments the tumor area by combining texture and color information, extracts the geometric features of the tumor, enhances the understanding of the tumor morphology, constructs a three-dimensional model and calculates the tumor volume, which is crucial for disease stage assessment and treatment planning, integrates tumor volume estimation data and key patient information, optimizes the classification and storage process of the image, and improves the efficiency of data retrieval.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of tumor image analysis, in particular to a tumor CT image segmentation processing method and system. BACKGROUND

[0002] The technical field of tumor image analysis involves extracting information important for tumor diagnosis and treatment by analyzing and processing medical imaging data. Through the use of various image processing techniques, including image processing, computer vision, and machine learning, CT, MRI, and various medical imaging device obtained image data are analyzed, including image preprocessing, feature recognition, image segmentation, and pattern classification, aiming to assist doctors in identifying lesion areas in complex medical images, assessing the type and stage of the disease, and helping medical professionals diagnose and monitor.

[0003] Among them, the tumor image segmentation processing method refers to using multiple image processing steps to accurately separate tumor tissue and normal tissue from medical images, covering image enhancement, edge detection, and region growing techniques. Image enhancement is used to improve image quality and make tumor regions clearer. Edge detection is used to determine the accurate boundary between tumor and non-tumor tissue. Region growing technology gradually expands the identified tumor area according to preset standards until the entire tumor area is completely divided, achieving accurate identification and segmentation of tumor regions from CT images.

[0004] Traditional tumor CT image segmentation processing methods have deficiencies in edge detection and accurate segmentation of tumor regions. In the case of highly heterogeneous tumor tissue and blurred tumor edges, it is difficult to accurately identify, resulting in low accuracy of tumor boundary identification. In three-dimensional reconstruction and volume calculation, there is often a lack of effective integration, which cannot fully utilize multi-angle image data, limiting the accuracy of diagnosis and treatment planning, leading to misjudgment of tumor stage and inaccurate treatment plan in actual operation, affecting treatment effect and patient prognosis, lacking accurate adjustment of image processing parameters, resulting in loss of image information, affecting adjustment of treatment plan and prediction of disease. SUMMARY

[0005] To solve the technical problems existing in the prior art, the present application provides a tumor CT image segmentation processing method and system. The technical solution is as follows:

[0006] On the one hand, a tumor CT image segmentation processing method is provided, the method comprising:

[0007] S1: Based on the patient's tumor CT image, adjust the image processing parameters to enhance the image, extract various image feature information of the medical image, and generate an image enhancement processing result;

[0008] S2: based on the image enhancement processing result, edge detection is performed on the image by analyzing the pixel intensity and texture features of multiple regions, edge information of the image is extracted, and an edge information extraction record is generated;

[0009] S3: using the edge information extraction record, a tumor region in the image is segmented according to the texture features and color information of the image, the segmentation parameters are adjusted by analyzing the accuracy of segmentation, the geometric features of the tumor are extracted, and a tumor segmentation image is generated;

[0010] S4: according to the tumor segmentation image, the shape information and shooting angle of the tumor in the plurality of medical images of the target patient are used to perform three-dimensional reconstruction on the tumor, and the volume of the tumor is calculated, and tumor volume estimation data is generated;

[0011] S5: according to the tumor volume estimation data, the image is classified according to the patient information, tumor type, location, volume and shooting time of the target image, the retrieval efficiency is optimized by matching the retrieval label, and an image classification and storage record is generated.

[0012] As a further scheme of the present application, the image enhancement processing result is specifically an image enhancement parameter, a color feature extraction record, and a texture feature extraction result, the edge information extraction record includes pixel intensity analysis result, texture feature analysis information, and image edge information, the tumor segmentation image specifically refers to segmentation accuracy analysis result, segmentation parameter adjustment record, and tumor geometric feature information, the tumor volume estimation data specifically refers to tumor three-dimensional model, tumor volume calculation data, and image shooting angle information, and the image classification and storage record includes patient information extraction record, tumor information data set, and retrieval label matching record.

[0013] As a further scheme of the present application, based on the CT image of the tumor of the patient, the image processing parameters are adjusted to enhance the image, and various image feature information of the medical image is extracted, and the step of generating the image enhancement processing result is specifically:

[0014] S101: based on the CT image of the tumor of the patient, the image is enhanced by adjusting the contrast and brightness parameters of the image, including adjusting the contrast and brightness, and generating an image preprocessing record;

[0015] S102: based on the image preprocessing record, the color features of the image are extracted, and color feature data is generated;

[0016] S103: based on the color feature data, the texture feature information of the target medical image is analyzed and extracted, and the image enhancement processing result is generated.

[0017] As a further scheme of the present application, based on the image enhancement processing result, edge detection is performed on the image by analyzing the pixel intensity and texture features of multiple regions, edge information of the image is extracted, and an edge information extraction record is generated. The step is specifically:

[0018] S201: Based on the image enhancement processing result, pixel intensity information of multiple regions in the image is extracted, and a local intensity analysis result is generated.

[0019] S202: Based on the local intensity analysis result, edge detection is performed on the image, edge information in the image is identified, and an edge feature analysis result is generated.

[0020] S203: Based on the edge feature analysis result, the continuity and sharpness of the edge are analyzed, the edge extraction parameters are adjusted, the extracted edge information is recorded, and an edge information extraction record is generated.

[0021] As a further scheme of the present application, the specific formula for identifying the edge information in the image is:

[0022]

[0023] wherein H i represents the calculation result of the gradient direction histogram corresponding to the i-th pixel point, i is an index variable, w i is the weight of the i-th pixel point, is the partial derivative of the function f at the x i point, is the partial derivative symbol, f represents the brightness function of the image, x i represents the position of the i-th considered pixel point.

[0024] As a further scheme of the present application, using the edge information extraction record, the tumor region in the image is segmented according to the texture features and color information of the image, the segmentation parameters are adjusted by analyzing the accuracy of segmentation, the geometric features of the tumor are extracted, and a tumor segmentation image is generated. The step is specifically:

[0025] S301: Using the edge information extraction record, the image is segmented according to the texture and color information in the image, the tumor and non-tumor regions are identified, and a preliminary tumor segmentation image is generated.

[0026] S302: According to the preliminary tumor segmentation image, the segmentation parameters are adjusted to optimize the segmentation accuracy by analyzing the accuracy of image segmentation, and a segmentation parameter optimization record is generated.

[0027] S303: Based on the segmentation parameter optimization record, the image is segmented and the geometric feature information of the tumor is extracted, including shape and boundary, and a tumor segmentation image is generated.

[0028] As a further scheme of the present application, the specific formula for optimizing the segmentation accuracy by adjusting the segmentation parameters is:

[0029]

[0030] wherein P new represents the new segmentation parameter value, P old represents the original segmentation parameter, a represents the learning rate, P best represents the currently known best segmentation parameter, D represents the difference between the current segmentation effect and the target effect, D max represents the acceptable maximum difference.

[0031] As a further scheme of the present application, according to the tumor segmentation image, according to the shape information and the shooting angle of the tumor in the plurality of medical images of the target patient, the tumor is three-dimensionally reconstructed, and the volume of the tumor is calculated, and the step of generating the tumor volume estimation data is specifically:

[0032] S401: Based on the tumor segmentation image, analyze the plurality of medical images of the target patient, extract the shooting angle and the geometric shape information of the tumor, and generate shape and angle analysis data;

[0033] S402: Based on the shape and angle analysis data, construct a three-dimensional model of the patient's tumor, and map color features and texture features onto the model to generate a three-dimensional tumor model;

[0034] S403: Based on the three-dimensional tumor model, according to the geometric shape information, the volume of the tumor is calculated, and the tumor volume estimation data is generated.

[0035] As a further scheme of the present application, according to the tumor volume estimation data, according to the patient information, tumor type, location, volume and shooting time of the target image, the image is classified, the search label is matched to optimize the search efficiency, and the step of generating the image classification and storage record is specifically:

[0036] S501: Based on the tumor volume estimation data, extract the tumor type, location, volume and shooting time information of the target medical image, combine the personal information of the patient, and generate a classification information extraction record;

[0037] S502: Based on the classification information extraction record, according to the feature information of the tumor and the patient information, the image is classified, and the image classification result is generated;

[0038] S503: Using the image classification result, matching the search label for the medical image, optimizing the search efficiency, and generating the image classification and storage record.

[0039] In another aspect, a tumor CT image segmentation processing system is provided, which is applied to a tumor CT image segmentation processing method, and the system comprises:

[0040] An image preprocessing module performs enhancement processing on the image based on the tumor CT image of the patient by adjusting the contrast and brightness of the image, records the color and texture features of the image, and generates an image enhancement processing result in combination with feature extraction.

[0041] An edge detection module analyzes the pixel intensity and texture features of multiple regions in the image by using the image enhancement processing result, identifies and extracts the edge information of the image through edge detection, and generates an edge information extraction record.

[0042] An image segmentation module uses the edge information extraction record to segment the tumor region in the image according to the texture features and color information of the image, optimizes the segmentation processing parameters in combination with the analysis of the segmentation accuracy, extracts the geometric features of the tumor, and generates a tumor segmentation image.

[0043] A three-dimensional modeling module analyzes multiple medical images of the patient based on the tumor segmentation image, performs three-dimensional reconstruction on the images according to the shooting angle of the images and the shape information of the tumor, and calculates the tumor volume to generate tumor volume estimation data.

[0044] A data classification module extracts patient information, tumor type, location, volume, and shooting time according to the tumor volume estimation data, classifies the image data, and generates image classification and storage records in combination with matching and searching labels.

[0045] The technical scheme provided by the embodiments of the present application has at least the following beneficial effects:

[0046] The image is enhanced by adjusting the contrast and brightness of the image, which improves the visual quality of the image, provides a clearer basis for subsequent edge detection, improves the accuracy of edge detection, segments the tumor region in combination with texture and color information, extracts the geometric features of the tumor, enhances the understanding of the tumor morphology, constructs a three-dimensional model, and calculates the tumor volume, which is crucial for disease stage assessment and treatment plan development. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical scheme in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0048] Figure 1 Workflow diagram of the present application;

[0049] Figure 2 S1 refinement flowchart of the present application;

[0050] Figure 3 S2 refinement flowchart of the present application;

[0051] Figure 4 S3 refinement flowchart of the present application;

[0052] Figure 5 S4 refinement flowchart of the present application;

[0053] Figure 6 S5 refinement flowchart of the present application;

[0054] Figure 7 System flowchart of the present application. DETAILED DESCRIPTION

[0055] The technical solutions in the present application will be described below with reference to the drawings.

[0056] In the embodiments of the present application, the words such as "example", "for example" are used to represent as an example, illustration or description. Any embodiment or design scheme described as "example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. In fact, the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present application, the meaning expressed by "and / or" can be both, or can be one of the two.

[0057] In the embodiments of the present application, "image" and "picture" can be used interchangeably at times. It should be pointed out that when the distinction is not emphasized, the meanings expressed are consistent. "Of", "corresponding" and "corresponding" can be used interchangeably at times. It should be pointed out that when the distinction is not emphasized, the meanings expressed are consistent.

[0058] In the embodiments of the present application, sometimes the subscript such as W1 can be written in the form of non-subscript such as W1. When the distinction is not emphasized, the meanings expressed are consistent.

[0059] To make the technical problems, technical solutions and advantages to be solved by the present application clearer, specific embodiments will be described in detail below with reference to the drawings.

[0060] The embodiments of the present application provide a tumor CT image segmentation processing method, which comprises the following steps: Figure 1The tumor CT image segmentation processing method flow chart is shown. The processing flow of the method can include the following steps:

[0061] S1: Based on the patient's tumor CT image, adjust the image processing parameters to enhance the image, extract multiple image feature information of the medical image, and generate an image enhancement processing result;

[0062] S2: Based on the image enhancement processing result, the edge information of the image is extracted by analyzing the pixel intensity and texture features of multiple regions, and the edge information extraction record is generated;

[0063] S3: Using the edge information extraction record, the tumor region in the image is segmented according to the texture features and color information of the image, the segmentation parameters are adjusted by analyzing the accuracy of the segmentation, the geometric features of the tumor are extracted, and the tumor segmentation image is generated;

[0064] S4: According to the tumor segmentation image, according to the shape information and shooting angle of the tumor in multiple medical images of the target patient, the tumor is three-dimensionally reconstructed, and the volume of the tumor is calculated, and the tumor volume estimation data is generated;

[0065] S5: According to the tumor volume estimation data, according to the patient information, tumor type, location, volume and shooting time of the target image, the image is classified, the search label is matched to optimize the search efficiency, and the image classification and storage record is generated.

[0066] The image enhancement processing result is the image enhancement parameter, the color feature extraction record, the texture feature extraction result, the edge information extraction record includes the pixel intensity analysis result, the texture feature analysis information and the image edge information, the tumor segmentation image specifically refers to the segmentation accuracy analysis result, the segmentation parameter adjustment record and the tumor geometric feature information, the tumor volume estimation data specifically refers to the tumor three-dimensional model, the tumor volume calculation data and the image shooting angle information, and the image classification and storage record includes the patient information extraction record, the tumor information data set and the search label matching record.

[0067] Please refer to Figure 2 , based on the patient's tumor CT image, adjust the image processing parameters to enhance the image, extract multiple image feature information of the medical image, and generate an image enhancement processing result, the steps are specifically as follows:

[0068] S101: Based on the patient's tumor CT image, adjust the contrast and brightness parameters of the image to enhance the image, including adjusting the contrast and brightness, and generate an image preprocessing record;

[0069] The image is preliminarily processed, the contrast and brightness parameters of the image are modified, the image quality is improved, the tumor details in the image are more clearly visible, the image is processed by using an image processing software such as Adobe Photoshop, it is ensured that the dark and bright details in the image are properly displayed, the edge features in the image are further enhanced by using a high-pass filter, the contrast between the tumor and the surrounding tissue is strengthened, and the image parameters recorded in the process include the contrast values before and after adjustment, the brightness values and the filter setting parameters. The target data is saved in the image preprocessing record and used for reference and reproduction in subsequent steps.

[0070] S102: Based on the image preprocessing record, color feature extraction is performed on the image to generate color feature data.

[0071] The color analysis tool, such as the color space conversion function in Matlab, is used to convert the image from the RGB color space to the HSV color space, the color distribution and saturation in the image are intuitively analyzed, the tumor area and the normal tissue are identified and distinguished, the hue, saturation and brightness in the HSV space are statistically analyzed, the color histogram of each area is calculated, the color feature data is generated, and the data record includes the distribution of each main color component and its statistical characteristics, which provides basic data for the next step of texture feature extraction.

[0072] S103: Based on the color feature data, the texture feature information of the target medical image is analyzed and extracted to generate an image enhancement processing result.

[0073] The texture information of the image is further extracted by using image processing tools and techniques, the texture pattern in the image is analyzed by using the gray level co-occurrence matrix method, the subtle changes of the texture in the local area of the image are captured, such as the texture difference between the tumor tissue and the surrounding normal tissue, the GLCM matrix is calculated by setting different distance and angle parameters, and the statistical indicators of the texture, such as the contrast, uniformity, entropy and correlation, are obtained from the GLCM matrix. The target texture index provides quantitative texture features for the image enhancement processing result, makes the tumor recognition and analysis more accurate, and further promotes the accurate diagnosis of the nature and boundary of the tumor.

[0074] Please refer to Figure 3 , based on the image enhancement processing result, the edge information of the image is extracted by analyzing the pixel intensity and texture features of multiple regions, and the steps of generating the edge information extraction record are as follows:

[0075] S201: Based on the image enhancement processing result, the pixel intensity information of multiple regions in the image is extracted to generate a local intensity analysis result.

[0076] The enhanced image is segmented into multiple small regions, each region usually including hundreds to thousands of pixels, using image analysis software such as ImageJ. For each region, the average pixel intensity value is calculated by summing the brightness values of all pixels in the region and dividing by the total number of pixels. The standard deviation of pixel intensity is also analyzed to assess the degree of variation in pixel intensity within the region, which helps to distinguish edge intensity in subsequent steps. The average intensity and standard deviation data for each region are recorded and constitute the local intensity analysis results. The target data is crucial for understanding the illumination and detail changes of the image region and provides accurate input data for edge detection.

[0077] S202: Based on the local intensity analysis results, edge detection is performed on the image to identify edge information in the image, and edge feature analysis results are generated.

[0078] The specific formula for identifying edge information in the image is:

[0079]

[0080] where H i represents the calculation result of the gradient direction histogram corresponding to the i-th pixel point, i is the index variable, w i is the weight of the i-th pixel point, is the partial derivative of the function f at the x i point, is the partial derivative symbol, f represents the brightness function of the image, x i represents the position of the i-th considered pixel point.

[0081] Formula:

[0082]

[0083] Formula details and formula calculation derivation process:

[0084] The formula is used to calculate the gradient direction histogram of each pixel point in the image, and the result is used to detect the edges in the image and determine the boundaries between tumor and non-tumor tissues.

[0085] Parameter meaning and setting value:

[0086] w i is the weight coefficient, representing the influence of the i-th pixel point, assuming w i = 0.5;

[0087] x i is the position of the pixel point in the image;

[0088] f(x i ) is the brightness value of the pixel point x i , assuming f(xi ) = 120;

[0089] representative pixel x i of the luminance gradient, assuming that f(x i ) the luminance of its adjacent pixels x i+1 and x i-1 are 125 and 115 respectively,

[0090] Substitute the parameters into the formula for calculation:

[0091] H i = 0.5 · (5) 2 = 0.5 · 25 = 12.5;

[0092] The result H i = 12.5 indicates that the edge feature of the pixel point x i in the image is more significant, and the numerical value reflects a higher luminance change rate from this point. In edge detection, such high values indicate possible boundary areas, ensuring more accurate segmentation of tumor and non-tumor tissues.

[0093] S203: Based on the edge feature analysis result, the continuity and clarity of the edge are analyzed, the edge extraction parameters are adjusted, and the edge information extraction record is recorded after extraction;

[0094] The edge continuity algorithm is used to determine the continuity of the edge. If a broken or blurred edge is detected, the algorithm will automatically adjust the edge extraction parameters, such as adjusting the low threshold and high threshold in the Canny algorithm, to improve the accuracy of edge detection. The adjusted parameters are recorded and used for repeated execution of the edge detection process until the preset edge continuity and clarity standards are met. The result of the step, i.e. the edge information extraction record, details all the adjusted parameters and improved edge information, providing an important basis for ensuring clear separation of tumor and non-tumor regions in subsequent image processing steps.

[0095] Referring to Figure 4 , the edge information extraction record is used to segment the tumor region in the image based on the texture features and color information of the image. By analyzing the accuracy of the segmentation, the segmentation parameters are adjusted, and the geometric features of the tumor are extracted to generate a tumor segmentation image. The steps are as follows:

[0096] S301: Use the edge information extraction record to segment the image based on the texture and color information in the image, identify the tumor and non-tumor regions, and generate a preliminary tumor segmentation image;

[0097] Region growing algorithm is used, which is a method of image segmentation based on similarity criteria. Region growing algorithm starts from a seed point, and adds the pixels adjacent to the seed point to the seed region. If the target pixel has similar texture or color features with the seed point, through iteration, all pixels meeting the conditions are included. In the implementation process, the seed point position is determined according to the edge information. Generally, the pixel located in the obvious tumor region is selected as the seed point. Region growing is carried out based on the gray value, color and texture information of the pixel, until the preset growth boundary is reached, that is, the boundary line provided by edge detection. The preliminary tumor segmentation image generated by this process clearly shows the boundary between tumor and non-tumor regions, and provides an accurate basis for subsequent analysis.

[0098] S302: According to the preliminary tumor segmentation image, the segmentation accuracy of the image is analyzed, the segmentation parameters are adjusted to optimize the segmentation accuracy, and a segmentation parameter optimization record is generated.

[0099] The specific formula for adjusting the segmentation parameters to optimize the segmentation accuracy is:

[0100]

[0101] P new new segmentation parameter value, P old original segmentation parameter, α represents learning rate, P best current known best segmentation parameter, D represents the difference between the current segmentation effect and the target effect, D max represents the acceptable maximum difference.

[0102] Formula:

[0103]

[0104] Formula details and formula calculation derivation process:

[0105] The formula is used to optimize the parameters in the image segmentation algorithm, and adjust the segmentation parameters to improve the segmentation accuracy.

[0106] Parameter meaning and setting value:

[0107] P old is the original segmentation parameter, which is assumed to be 0.2;

[0108] P best is the current best segmentation parameter, which is assumed to be 0.5;

[0109] α is the learning rate, which is assumed to be 0.05;

[0110] D is the difference between the current segmentation effect and the target effect, which is assumed to be 15;

[0111] Dmax For the acceptable maximum difference, assume 100;

[0112] Substitute the parameters into the formula for calculation:

[0113]

[0114] P new = 0.2 + 0.05·0.3·0.15;

[0115] P new = 0.2 + 0.00225;

[0116] P new = 0.20225;

[0117] The result 0.20225 is the new value after parameter adjustment, and the calculation process is used to improve the image edge and texture difference, which provides accurate tumor recognition and boundary definition for subsequent analysis.

[0118] S303: Based on the segmentation parameter optimization record, segment the image and extract the geometric feature information of the tumor, including shape and boundary, to generate a tumor segmentation image;

[0119] The computational geometry technique is used to define and quantify the shape parameters of the tumor, including the use of geometric moments and contour analysis to calculate the area, perimeter and shape complexity of the tumor. Through target geometry calculation, the physical morphology of the tumor is accurately described, providing important information about the tumor growth pattern and diffusion path for clinical use. The boundary extraction adopts a gradient-based method, which determines the tumor edge by identifying the area with the most significant changes in color and texture information. The execution of the target process ensures that the tumor area can be accurately segmented from the CT image, and each geometric feature of the tumor is recorded in detail, providing a reliable data basis for subsequent treatment planning and monitoring.

[0120] Please refer to Figure 5 , according to the shape information and shooting angle of the tumor in the multiple medical images of the target patient, the tumor is reconstructed in three dimensions, and the volume of the tumor is calculated, and the steps of generating tumor volume estimation data are as follows:

[0121] S401: Based on the tumor segmentation image, analyze the multiple medical images of the target patient, extract the shooting angle and geometric shape information of the tumor, and generate shape and angle analysis data;

[0122] From multiple medical images, key shape and angle information is extracted, image registration techniques are used to align CT images taken at different time points, ensuring that the tumor shape information extracted from each image is comparable. The technology relies on positioning markers in the image or the tumor's own distinctive features to ensure accurate alignment between images. The aligned image data is processed by feature extraction algorithms, such as gradient-based shape descriptors, which quantify the tumor's geometric features in the image, such as boundary curvature, area, and volume. Each extracted feature is recorded and analyzed to assess changes and developments in tumor shape. The shape and angle analysis data is generated by combining the shape and angle information from all images, and the target data reflects the morphological changes of the tumor at different time points, providing necessary input information for subsequent three-dimensional modeling.

[0123] S402: Based on the shape and angle analysis data, a three-dimensional model of the patient's tumor is constructed, and color features and texture features are mapped onto the model to generate a three-dimensional tumor model;

[0124] A voxelization method is applied to convert two-dimensional image data into point clouds in three-dimensional space, where each point cloud represents a voxel of the tumor at a specific location, and its attributes include color and texture information, which are inherited from the original CT images. Through three-dimensional rendering techniques such as volume rendering or surface rendering, the point cloud is converted into a continuous three-dimensional surface model, which accurately maps the texture features of the tumor and allows doctors to observe the tumor structure from multiple angles. The generated three-dimensional tumor model is a comprehensive and dynamic representation of the tumor morphology, providing a powerful visual aid for clinical practice.

[0125] S403: Based on the three-dimensional tumor model, the tumor volume is calculated based on geometric shape information to generate tumor volume estimation data;

[0126] A geometric volume calculation method is used to estimate the tumor volume, which utilizes the geometric data of the three-dimensional model, such as edge length, area, and voxel density, to calculate the entire tumor volume through mathematical formulas. The calculation formula may include three-dimensional integration or accumulation of voxels for complex shapes. Each voxel represents a small cube, and its volume is the cube of its edge length. By accumulating the volumes of all voxels, the total volume of the entire tumor is obtained. This calculation method not only provides a quantitative measure of tumor size but also reflects the internal volume distribution of the tumor. The generated tumor volume estimation data has important clinical significance for evaluating tumor growth rate and treatment response, helping doctors develop more accurate treatment plans.

[0127] Please refer to Figure 6 , based on the tumor volume estimation data, the image is classified according to the patient information, tumor type, location, volume, and shooting time of the target image, and the search efficiency is optimized by matching the search tags. The steps of generating image classification and storage records are as follows:

[0128] S501: Based on the tumor volume estimation data, the tumor type, location, volume and shooting time information of the target medical image are extracted, combined with the personal information of the patient, and the classification information extraction record is generated;

[0129] Using data mining techniques such as decision tree algorithm, image data is analyzed and classified, decision tree selects the most effective attribute for branching by evaluating the information gain of each indicator, and gradually refines the classification standard, relevant data such as age, gender and medical history is retrieved from the patient's personal information database, and is associated with image data to enhance the accuracy of classification, each data is verified and cleaned to ensure the quality of input data, through the target step, the system generates a complete classification information extraction record, which includes detailed classification data of each image and its corresponding patient personal information, which provides basic data for subsequent image processing and analysis.

[0130] S502: Based on the classification information extraction record, the image is classified according to the characteristic information of the tumor and the patient information, and the image classification result is generated;

[0131] Support vector machine in machine learning technology is used for further classification processing of tumor images, support vector machine classifies by constructing one or more hyperplanes in high-dimensional space, including training phase and classification phase, labeled image set is used to train the model in the training phase, and the model is used to classify new images in the classification phase, SVM model evaluates the feature vector of each image, such as texture, shape and boundary information, and identifies the tumor type according to the set classification standard, each image is labeled with specific tumor type, and detailed image classification result is generated, the target result not only includes the category of tumor, but also accurately to the specific characteristics of tumor, such as grading and prognosis index.

[0132] S503: Using image classification results, matching retrieval labels for medical images are matched, retrieval efficiency is optimized, and image classification and storage records are generated;

[0133] Label matching technology is used to optimize the retrieval and storage process of medical images, label system creates a set of descriptive labels for each image based on the classification results of the image and medical records, the target label covers tumor type, location, volume and specific medical indicators, natural language processing technology is applied in the label generation process to convert medical terminology and classification information into keywords easy to retrieve, image storage system dynamically adjusts the storage location and backup strategy of images according to the relevance and search frequency of labels, in this way, not only improves the management efficiency of medical image library, but also improves the speed and accuracy of medical workflow, so that doctors and researchers can quickly find the required image materials.

[0134] Please refer to Figure 7The tumor CT image segmentation processing system is used for executing the tumor CT image segmentation processing method, and the system comprises the following modules:

[0135] The image preprocessing module performs enhancement processing on the image based on the tumor CT image of the patient by adjusting the brightness of the contrast of the image, records the color and texture features of the image in combination with feature extraction, and generates an image enhancement processing result.

[0136] The edge detection module analyzes the pixel intensity and texture features of a plurality of regions in the image by using the image enhancement processing result, identifies and extracts the edge information of the image through edge detection, and generates an edge information extraction record.

[0137] The image segmentation module uses the edge information extraction record to segment the tumor region in the image according to the texture features and color information of the image, optimizes the segmentation processing parameters in combination with the analysis of the segmentation accuracy, extracts the geometric features of the tumor, and generates a tumor segmentation image.

[0138] The three-dimensional modeling module analyzes a plurality of medical images of the patient based on the tumor segmentation image, performs three-dimensional reconstruction on the images and calculates the tumor volume according to the shooting angle of the images and the shape information of the tumor, and generates tumor volume estimation data.

[0139] The data classification module extracts patient information, tumor type, location, volume, and shooting time according to the tumor volume estimation data, classifies the image data, and matches the search tags to generate image classification and storage records.

[0140] The above-described embodiments can be implemented in whole or in part by software, hardware (e.g., circuitry), firmware, or any combination thereof. When implemented in software, the above-described embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions according to the embodiments of the present application are entirely or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center through a wired (e.g., infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0141] It should be understood that the term "and / or" herein merely describes an association relationship of associated objects, which means that there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. In addition, the character " / " herein generally represents an "or" relationship between the associated objects before and after it, but it can also represent an "and / or" relationship, which can be understood according to the context before and after it.

[0142] In the present application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0143] It should be understood that in various embodiments of the present application, the size of the sequence number of the above-described processes does not mean the order of execution, and the execution order of the processes should be determined according to their functions and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0144] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0145] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the devices, apparatuses and units described above can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0146] In several embodiments provided by the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0147] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0148] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit.

[0149] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts of the present application that essentially contribute to the prior art or the parts of the technical solutions can be embodied in the form of software products. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0150] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A tumor CT image segmentation processing method characterized by, The method comprises: S1: based on the CT image of the tumor of the patient, adjusting the image processing parameters to enhance the image, extracting various image feature information of the medical image, and generating an image enhancement processing result; S2: based on the image enhancement processing result, by analyzing the pixel intensity and texture features of multiple regions, the edge information of the image is extracted by edge detection, and an edge information extraction record is generated; S3: using the edge information extraction record, according to the texture features and color information of the image, the tumor region in the image is segmented, the segmentation accuracy is analyzed, the segmentation parameters are adjusted, the geometric features of the tumor are extracted, and a tumor segmentation image is generated; S4: according to the tumor segmentation image, according to the shape information and shooting angle of the tumor in the multiple medical images of the target patient, the tumor is three-dimensionally reconstructed, and the volume of the tumor is calculated, and tumor volume estimation data is generated; According to the tumor segmentation image, according to the shape information and shooting angle of the tumor in the multiple medical images of the target patient, the tumor is three-dimensionally reconstructed, and the volume of the tumor is calculated, and tumor volume estimation data is generated, which comprises: S401: based on the tumor segmentation image, analyze the multiple medical images of the target patient, use image registration technology to align the CT images taken at different times, extract the shooting angle and the geometric shape information of the tumor, and generate shape and angle analysis data; S402: based on the shape and angle analysis data, convert the two-dimensional image data into point cloud in three-dimensional space, construct the three-dimensional model of the patient's tumor, and map the color features and texture features to the model, and generate a three-dimensional tumor model; S403: based on the three-dimensional tumor model, according to the geometric shape information, the volume of the tumor is calculated, and tumor volume estimation data is generated; S5: according to the tumor volume estimation data, according to the patient information, tumor type, location, volume and shooting time of the target image, the image is classified, the retrieval label is matched to optimize the retrieval efficiency, and an image classification and storage record is generated.

2. The tumor CT image segmentation processing method according to claim 1, characterized by, The image enhancement processing result is specifically an image enhancement parameter, a color feature extraction record, a texture feature extraction result, the edge information extraction record includes a pixel intensity analysis result, texture feature analysis information and image edge information, the tumor segmentation image specifically refers to a segmentation accuracy analysis result, a segmentation parameter adjustment record and tumor geometric feature information, the tumor volume estimation data specifically refers to a tumor three-dimensional model, tumor volume calculation data and image shooting angle information, and the image classification and storage record includes a patient information extraction record, a tumor information data set and a retrieval label matching record.

3. The tumor CT image segmentation processing method according to claim 1, characterized by, Based on the CT image of the tumor of the patient, adjusting the image processing parameters to enhance the image, extracting various image feature information of the medical image, and generating an image enhancement processing result, which comprises: S101: based on the CT image of the tumor of the patient, adjusting the contrast and brightness parameters of the image to enhance the image, including adjusting the contrast and brightness, and generating an image preprocessing record; S102: based on the image preprocessing record, extracting the color features of the image, and generating color feature data; S103: Based on the color feature data, analyze and extract the texture feature information of the target medical image, and generate an image enhancement processing result.

4. The tumor CT image segmentation processing method according to claim 1, characterized by, Based on the image enhancement processing result, the edge information of the image is extracted by analyzing the pixel intensity and texture features of multiple regions, and the edge information extraction record is generated. The specific steps are: S201: Based on the image enhancement processing result, extract the pixel intensity information of multiple regions in the image, and generate a local intensity analysis result; S202: Based on the local intensity analysis result, perform edge detection on the image to identify the edge information in the image, and generate an edge feature analysis result; S203: Based on the edge feature analysis result, adjust the edge extraction parameters by analyzing the continuity and clarity of the edge, and record the extracted edge information to generate an edge information extraction record.

5. The tumor CT image segmentation processing method according to claim 4, characterized by, The specific formula for identifying the edge information in the image is: ； wherein, represents the result of the computation of the gradient direction histogram corresponding to the is an index variable, is the weight of the is the partial derivative of the function at the point is the sign of the partial derivative, represents the luminance function of the image, represents the position of the pixel point under consideration.​​​ 6. The tumor CT image segmentation processing method according to claim 1, characterized by, Using the edge information extraction record, the tumor region in the image is segmented according to the texture features and color information of the image, the segmentation parameters are adjusted by analyzing the accuracy of the segmentation, the geometric features of the tumor are extracted, and the tumor segmentation image is generated. The specific steps are: S301: Using the edge information extraction record, segment the image according to the texture and color information in the image, identify the tumor and non-tumor regions, and generate a preliminary tumor segmentation image; S302: According to the preliminary tumor segmentation image, adjust the segmentation parameters to optimize the segmentation accuracy by analyzing the accuracy of the image segmentation, and generate a segmentation parameter optimization record; S303: Based on the segmentation parameter optimization record, segment the image and extract the geometric feature information of the tumor, including shape and boundary, and generate a tumor segmentation image.

7. The tumor CT image segmentation processing method according to claim 6, characterized by, The specific formula for adjusting the segmentation parameters to optimize the segmentation accuracy is: ； wherein, represents a new split parameter value, represents an original split parameter, represents a learning rate, represents a currently known best split parameter, represents a degree of difference between a current split effect and a target effect, represents an acceptable maximum degree of difference.

8. The tumor CT image segmentation processing method according to claim 1, characterized by, According to the tumor volume estimation data, according to the patient information, tumor type, location, volume and shooting time of the target image, the image is classified, the retrieval label is matched to optimize the retrieval efficiency, and the image classification and storage record is generated. The specific steps are: S501: Based on the tumor volume estimation data, extract the tumor type, location, volume and shooting time information of the target medical image, and combine the patient's personal information to generate a classification information extraction record; S502: Based on the classification information extraction record, classify the image according to the feature information of the tumor and the patient information, and generate an image classification result; S503: Using the image classification result, match the retrieval label for the medical image to optimize the retrieval efficiency, and generate an image classification and storage record.

9. A tumor CT image segmentation processing system characterized by comprising: The tumor CT image segmentation processing method according to any one of claims 1-8, the system comprises: The image preprocessing module enhances the image based on the contrast of the patient's tumor CT image, adjusts the brightness of the image, combines feature extraction, records the color and texture features of the image, and generates an image enhancement processing result; The edge detection module uses the image enhancement processing result to analyze the pixel intensity and texture features of multiple regions in the image, identifies and extracts the edge information of the image through edge detection, and generates an edge information extraction record; The image segmentation module uses the edge information extraction record to segment the tumor region in the image according to the texture features and color information of the image, optimizes the segmentation processing parameters in combination with the analysis of the segmentation accuracy, extracts the geometric features of the tumor, and generates a tumor segmentation image; The three-dimensional modeling module analyzes multiple medical images of the patient based on the tumor segmentation image, performs three-dimensional reconstruction on the images and calculates the tumor volume according to the shooting angle of the images and the shape information of the tumor, and generates tumor volume estimation data; The data classification module extracts patient information, tumor type, location, volume, and shooting time according to the tumor volume estimation data, classifies the image data, and matches the search tags to generate image classification and storage records.

Images