Tumor image analysis processing method and system

Abstract

The invention provides a tumor image analysis processing method and system. The method comprises the following steps: acquiring a tumor image of a patient corresponding to an irradiation item; based on the patient tumor image, extracting comprehensive features of the tumor, and based on the comprehensive features, judging a display result corresponding to the tumor; if the tumor is benign, acquiring basic data corresponding to the current benign tumor, and generating a diagnosis and treatment suggestion of the benign tumor; if the tumor is malignant, acquiring a pathological type corresponding to the malignant tumor, extracting intensity distribution data corresponding to the malignant tumor, and analyzing invasiveness corresponding to the malignant tumor; according to the method, the invasiveness of the malignant tumor is comprehensively judged according to the tumor image of the patient and the blood vessel distribution and the blood sampling inspection result corresponding to the tumor position, the misdiagnosis and missed diagnosis situations caused by the poor tumor image are made up, and the diagnosis and treatment advice corresponding to the malignant tumor is generated according to the diagnosis and treatment advice. The effectiveness of tumor result analysis is guaranteed, the workload of doctors is relieved, and effective tumor intervention is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of image processing, and specifically relates to a method and system for analyzing and processing tumor images. Background Art

[0002] With the rapid development of imaging technology in the medical field, the identification of tumors has become more efficient. This technology can clearly show the size, location, and shape of tumors, and also provide rich information about the internal structure of tumors and surrounding tissues in all aspects, so as to help doctors identify tumors efficiently, make accurate tumor treatment decisions, reduce the difficulties of manual tumor identification, reduce the diagnosis probability of false positives and false negatives of tumors, reduce the tumor diagnosis risk, enable tumors to be treated efficiently, and further protect the physical health of patients.

[0003] The prior art is a method and system for analyzing and processing tumor images disclosed in the invention patent application with the publication number CN118822953A. This method and system obtain tumor image data from X-rays through an image acquisition module. The image processing module performs operations such as denoising, enhancement, smoothing, and geometric correction on the image based on the tumor image data transmitted by the image acquisition module. The tumor image positioning module performs image positioning operations based on the corrected tumor image to obtain an image of the area where the tumor is located. The feature extraction module extracts features from this image based on the image of the area where the tumor is located. The machine learning module trains an artificial neural network model according to the tumor image feature value information transmitted by the feature extraction module. The analysis result output module analyzes and evaluates the tumor image according to the artificial neural network model, generates an analysis report on the degree of tumor lesions, and outputs this analysis report to be displayed on the doctor's work computer.

[0004] In view of the above solution, the applicant of the present invention found that at least the following technical problems exist in the above technology: The above invention mainly analyzes and evaluates tumor images and generates an analysis report on the degree of tumor lesions, but does not judge the corresponding manifestation results based on the extracted tumor features, fails to provide patients with corresponding pertinence for each result, reduces the treatment efficiency, and at the same time cannot quickly know the invasiveness corresponding to malignant tumors, which will increase the treatment difficulty of tumors for doctors to a certain extent, consume doctors' treatment energy, cannot help doctors reduce the treatment burden, and cannot efficiently take more effective intervention measures for patients, increasing the tumor diagnosis difficulty. Summary of the Invention

[0005] In order to overcome the above problems existing in the prior art, the present application provides a method and system for analyzing and processing tumor images, and adopts the following technical solutions:

[0006] In a first aspect, the present application provides a method for analyzing and processing tumor images, including:

[0007] Obtain the tumor image of the patient corresponding to the irradiation item;

[0008] Based on the patient's tumor image, extract the comprehensive features of the tumor, and judge the manifestation result corresponding to the tumor based on the comprehensive features; if the tumor is benign, obtain the basic data corresponding to the current benign tumor and generate a diagnosis and treatment recommendation for the benign tumor; if the tumor is malignant, obtain the pathological type corresponding to the malignant tumor, extract the intensity distribution data corresponding to the malignant tumor, and analyze the invasiveness corresponding to the malignant tumor;

[0009] Generate a diagnosis and treatment recommendation for the malignant tumor based on the invasiveness corresponding to the malignant tumor.

[0010] Furthermore, extract the corresponding tumor features, including:

[0011] Based on the known current situation features corresponding to the tumor, determine the location of the tumor corresponding to the tumor image;

[0012] Based on the location of the corresponding tumor, extract the shape and boundary corresponding to the tumor from the tumor image through contour detection technology;

[0013] Extract the texture corresponding to the tumor from the tumor image using the gray-level co-occurrence matrix technology;

[0014] Based on the scan of the irradiation position corresponding to the irradiation device, obtain the feedback echo signal value during irradiation corresponding to the irradiation position;

[0015] Take the shape and boundary, texture, and feedback echo signal value corresponding to the tumor as the comprehensive features of the corresponding tumor.

[0016] Furthermore, judge the manifestation result corresponding to the tumor based on the comprehensive features, including:

[0017] Match the features extracted corresponding to the tumor with the feature sets corresponding to various types of tumors stored in the database;

[0018] When the feature match is included in the feature set corresponding to the benign tumor stored in the database, it is determined that the manifestation result of the current tumor is a benign tumor; otherwise, it is determined to be a malignant tumor;

[0019] Take the judgment result of the feature match as the manifestation result corresponding to the tumor.

[0020] Furthermore, obtain the basic data corresponding to the current benign tumor, including:

[0021] Based on the tumor image, confirm the location corresponding to the benign tumor; according to the location corresponding to the benign tumor, extract the current situation data corresponding to the benign tumor, including the current situation area of the tumor, the occupied area of the compressed tissue by the tumor, and at the same time, based on the frequency of tumor pain obtained during the patient interview, and substitute it into the preset formula;

[0022] The preset formula is as follows: Where LX is the current status coefficient corresponding to the benign tumor, F′ is the set reference tumor current status area, G′ is the set reference tumor compression tissue occupancy, K′ is the set reference tumor pain frequency, F is the current tumor current status area corresponding to the benign tumor, G is the current tumor compression tissue occupancy corresponding to the benign tumor, and K is the current tumor pain frequency corresponding to the benign tumor.

[0023] Furthermore, generate the diagnosis and treatment suggestions for the benign tumor, including:

[0024] Compare the current status coefficient corresponding to the benign tumor with the reference status coefficient corresponding to the benign tumor stored in the database. If the current status coefficient corresponding to the benign tumor is greater than the reference status coefficient corresponding to the benign tumor stored in the database, it is determined that the status of the benign tumor is dangerous;

[0025] If the current status coefficient corresponding to the benign tumor is less than or equal to the reference status coefficient corresponding to the benign tumor stored in the database, it is determined that the status of the benign tumor is safe;

[0026] Based on the different status determination results of the benign tumor, generate corresponding diagnosis and treatment suggestions.

[0027] Furthermore, obtain the pathological type corresponding to the malignant tumor, including:

[0028] Compare the position corresponding to the malignant tumor with the positions of various pathological tumors stored in the database; when the position of the malignant tumor is the same as the position corresponding to the pathological tumor in the database, record this case tumor, and screen out the pathological tumors with matching positions to obtain the screened pathological tumors;

[0029] Compare the extracted malignant tumor features with the feature sets corresponding to the screened pathological tumors one by one; when the malignant tumor features are included in the feature of a certain pathological tumor among the screened pathological tumors, use the pathological type corresponding to this pathological tumor as the pathological type of the current malignant tumor.

[0030] Furthermore, extract the intensity distribution data corresponding to the malignant tumor, including:

[0031] Based on the tumor image, obtain the blood vessel distribution corresponding to the tumor position, and extract the number of blood vessels distributed around the malignant tumor;

[0032] Based on the blood oxygen content and blood flow nutrition value obtained from the blood test results corresponding to the patient, comprehensively obtain the intensity distribution data corresponding to the malignant tumor in the tumor image;

[0033] Input the intensity distribution data corresponding to the malignant tumor in the tumor image into the deep learning model, and obtain the activity value corresponding to the malignant tumor based on the preset formula. If the trend result of the activity value corresponding to the malignant tumor is 0, it is determined that the malignant tumor is active and has strong invasiveness;

[0034] If the trend result of the activity value corresponding to the malignant tumor is -1, it is determined that the malignant tumor is inactive and has weak invasiveness.

[0035] Furthermore, obtain the activity value corresponding to the malignant tumor based on the preset formula. The preset formula is as follows:

[0036]

[0037] Wherein, PL is the activity value corresponding to the malignant tumor, N′ is the set reference blood vessel number, N is the number of blood vessels distributed around the malignant tumor, S′ is the set reference blood oxygen content, S is the blood oxygen content of the blood flow distributed around the malignant tumor, B′ is the set reference blood flow nutrition value, B is the blood flow nutrition value of the blood vessels distributed around the malignant tumor, and Z is the set reference activity value.

[0038] Furthermore, generate the diagnosis and treatment suggestions corresponding to the malignant tumor, including:

[0039] Obtain the classification cluster to which the pathological type corresponding to the malignant tumor belongs among the various clinical malignant tumors stored in the database based on the clustering algorithm;

[0040] Compare the pathological type corresponding to the malignant tumor with the pathological type of the classification cluster to which the patient belongs. If the pathological type corresponding to the malignant tumor is the same as a certain type of malignant tumor in the classification cluster to which the patient belongs, obtain the reference activity values at each stage corresponding to the pathological type of this classification cluster, and use the pathological type of this classification cluster as the first pathological type;

[0041] Compare the activity value corresponding to the malignant tumor with the reference activity values at each stage corresponding to the first pathological type. If the activity value corresponding to the malignant tumor is the same as the reference activity value at a certain stage corresponding to the first pathological type, obtain the diagnosis and treatment suggestions for the reference activity value corresponding to this stage of the patient's first pathological type.

[0042] In a second aspect, the present application also provides a tumor image analysis and processing system, including:

[0043] A tumor image acquisition module for acquiring the tumor image corresponding to the irradiation item of the patient;

[0044] A feature judgment module, configured to extract comprehensive features of a tumor based on a patient's tumor image, and judge the corresponding manifestation result of the tumor based on the comprehensive features; if the tumor is benign, obtain the basic data corresponding to the current benign tumor, and generate a diagnosis and treatment recommendation for the benign tumor; if the tumor is malignant, obtain the pathological type corresponding to the malignant tumor, and extract the intensity distribution data corresponding to the malignant tumor, and analyze the invasiveness corresponding to the malignant tumor.

[0045] A diagnosis and treatment recommendation generation module, configured to generate a diagnosis and treatment recommendation corresponding to a malignant tumor based on the invasiveness corresponding to the malignant tumor.

[0046] In a third aspect, the present application provides an electronic device, including:

[0047] One or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions that, when executed by the device, cause the device to execute the method described in the first aspect.

[0048] In a fourth aspect, the present application provides a computer-readable storage medium, in which a computer program is stored, and when it runs on a computer, it causes the computer to execute the method described in the first aspect.

[0049] In a fifth aspect, the present application provides a computer program that, when executed by a computer, is used to execute the method described in the first aspect.

[0050] In a possible design, the program in the fifth aspect can be stored in whole or in part on a storage medium packaged together with the processor, or can be stored in whole or in part on a memory not packaged together with the processor.

[0051] The present application has the following beneficial effects:

[0052] 1. The present application comprehensively judges the invasiveness of a malignant tumor based on the patient's tumor image and the corresponding blood vessel distribution and blood test results at the tumor location, making up for misdiagnosis and missed diagnosis caused by poor tumor image quality during the process of judging tumor invasiveness, ensuring the effectiveness of tumor result analysis, improving the accuracy of the patient's tumor analysis result, and providing guarantee for the patient.

[0053] 2. The present application obtains the patient's tumor image, extracts tumor features based on the tumor image, judges the corresponding manifestation result of the tumor, and generates different diagnosis and treatment recommendations based on different manifestation results, realizing a comprehensive analysis of tumor patient data, thereby helping doctors obtain effective treatment references, reducing the doctor's work burden, realizing effective tumor intervention, enabling patients to receive efficient treatment, and ensuring the patient's physical health.

[0054] 3. In the process of generating the diagnosis and treatment opinions for cancer patients, this application clusters similar patients together through a clustering method, so that in the process of generating diagnosis and treatment opinions for cancer patients, corresponding diagnosis and treatment suggestions can be generated more accurately for cancer patients, making the generated diagnosis and treatment suggestions more scientific and reasonable. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is an exemplary system architecture diagram to which the embodiments of this application can be applied;

[0056] Figure 2 It is a flowchart of the tumor image analysis and processing method according to the embodiments of this application;

[0057] Figure 3 It is a flowchart of tumor feature extraction according to the embodiments of this application;

[0058] Figure 4 It is a flowchart of the manifestation result corresponding to the tumor according to the embodiments of this application;

[0059] Figure 5 It is a flowchart of generating diagnosis and treatment suggestions for benign tumors according to the embodiments of this application;

[0060] Figure 6 It is a system flowchart according to the embodiments of this application;

[0061] Figure 7 It is a schematic diagram of a computer device according to the embodiments of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0062] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above drawings are intended to cover non-exclusive inclusion. The terms "first", "second", etc. in the specification and claims of this application or the above drawings are used to distinguish different objects and not to describe a specific order.

[0063] Referring to "embodiments" herein means that a particular feature, structure, or characteristic described in connection with the embodiments can be included in at least one embodiment of this application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0064] To enable those skilled in the art to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0065] As Figure 1 shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0066] Users can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0067] The terminal devices 101, 102, 103 may be various electronic devices with a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop portable computers, and desktop computers, etc.

[0068] The server 105 may be a server providing various services, such as a background server that supports the pages displayed on the terminal devices 101, 102, 103.

[0069] It should be noted that the tumor image analysis and processing method provided by the embodiments of this application is generally executed by the server / terminal device. Correspondingly, the tumor image analysis and processing system is generally set in the server / terminal device.

[0070] It should be understood that Figure 1 the numbers of terminal devices, networks, and servers in

[0071] are merely illustrative. According to the implementation requirements, there may be any number of terminal devices, networks, and servers. Figure 2 Continuing to refer to

[0072] Step 201, Obtain tumor images: irradiate the patient based on the irradiation project, and then obtain the tumor images of the patient corresponding to the irradiation project.

[0073] In the embodiment of the present application, the irradiation project corresponding to the patient is obtained from the patient's corresponding case book, where the irradiation project includes: gland irradiation, esophageal irradiation, brain irradiation, and other parts that may produce tumors. The actual irradiation project is determined based on the patient's symptomatic part.

[0074] In the embodiment of the present application, after confirming the irradiation project corresponding to the patient, the irradiation device is used to automatically perform a scan of the irradiation project on the patient, and then automatically irradiate to obtain the tumor images of the patient corresponding to the irradiation project.

[0075] In the embodiment of the present application, the irradiation device includes a linear accelerator, a gamma knife, a proton therapy device, a heavy ion therapy device, a radiotherapy machine, an X-ray therapy machine, etc.

[0076] In the present application, the tumor images of the patient corresponding to the irradiation project are obtained through irradiation, and then analyzed based on the patient's tumor images, so as to quickly determine the current situation of the patient and assist the doctor in helping the patient formulate corresponding ones.

[0077] Step 202, Extract tumor features based on tumor images: based on the patient's tumor images, extract the comprehensive features of the tumor, and judge the corresponding manifestation results of the tumor based on the comprehensive features; if the tumor is benign, obtain the basic data corresponding to the current benign tumor and generate a diagnosis and treatment recommendation for the benign tumor; if the tumor is malignant, obtain the pathological type corresponding to the malignant tumor, and extract the intensity distribution data corresponding to the malignant tumor to analyze the invasiveness corresponding to the malignant tumor.

[0078] In a possible implementation manner, extract the corresponding tumor features, please refer to Figure 3 , and the specific content includes:

[0079] Step 31, Determine the location of the tumor corresponding to the tumor image based on the known current situation features corresponding to the tumor;

[0080] Step 32, Based on the location of the corresponding tumor, extract the shape and boundary of the tumor from the tumor image through contour detection technology;

[0081] Step 33, Use the gray-level co-occurrence matrix technology to extract the texture corresponding to the tumor from the tumor image;

[0082] Step 34, Based on the scan of the irradiation position corresponding to the irradiation device, obtain the feedback echo signal value during irradiation corresponding to the irradiation position;

[0083] Step 35, Take the shape and boundary, texture, and feedback echo signal value corresponding to the tumor as the comprehensive features of the corresponding tumor.

[0084] In the embodiments of the present application, the common manifestations of the known current characteristics corresponding to tumors are: presenting a round and bulging mass.

[0085] In the embodiments of the present application, if the extracted tumor features are pleomorphic, with blurred boundaries and uneven internal structures presented by the texture, and the cell nuclei are enlarged and irregular in shape, then it is a malignant tumor. The contour detection technology and the gray-level co-occurrence matrix technology are currently well-known technologies and will not be elaborated here.

[0086] In a possible implementation manner, to judge the manifestation result corresponding to the tumor, please refer to Figure 4 , and the specific content includes:

[0087] Step 41, match the features corresponding to the extracted tumor with the feature sets corresponding to various types of tumors stored in the database; during the matching process, feature matching based on deep learning or feature matching using distance metrics can be adopted; the items for matching include the shape, boundary, texture, and feedback echo signal value of the tumor.

[0088] Step 42, when the feature matching is included in the feature set corresponding to the benign tumor stored in the database, then determine that the manifestation result of the current tumor is a benign tumor; that is: the shape is oval, the boundary is clear, the internal structure presented by the texture is uniform, the cell nucleus shape is regular, and the feedback echo signal value corresponding to the tumor is included in the reference feedback echo signal value corresponding to the benign tumor stored in the database; otherwise, it is determined to be a malignant tumor.

[0089] Step 43, take the judgment result of the feature matching as the manifestation result corresponding to the tumor.

[0090] In a possible implementation manner, to obtain the basic data corresponding to the current benign tumor, the specific obtaining process is as follows:

[0091] Based on the tumor image of the patient corresponding to the irradiation item, confirm the position corresponding to the benign tumor, and according to the position corresponding to the benign tumor, extract the current situation data corresponding to the benign tumor, including the current situation area of the tumor and the occupied area of the compressed tissue by the tumor. At the same time, based on the frequency of tumor pain obtained during the patient interview, and substitute it into the preset formula;

[0092] The preset formula is: Where LX is the current situation coefficient corresponding to the benign tumor, F′ is the set reference tumor current situation area, G′ is the set reference occupied area of the compressed tissue by the tumor, K′ is the set reference frequency of tumor pain, F is the current situation area of the benign tumor currently corresponding, G is the occupied area of the compressed tissue by the benign tumor currently corresponding, and K is the frequency of tumor pain currently corresponding to the benign tumor.

[0093] In the embodiments of the present application, according to the position corresponding to the benign tumor, the current situation data corresponding to the benign tumor is extracted: based on the position corresponding to the benign tumor, the contour corresponding to the benign tumor in the tumor image is further observed, so as to determine the corresponding tumor current situation area of the benign tumor; secondly, observe the cell distribution area at the position of the benign tumor in the tumor image, and obtain the data of the cell distribution area of the occupied cells of the compressed tissue at the position corresponding to the benign tumor.

[0094] In the embodiments of the present application, the tumor-compressed tissue occupancy is the tissue occupancy area where the tumor compresses the remaining cells.

[0095] In the embodiments of the present application, various standard values are jointly discussed and formulated by multiple professional medical staff, and each standard value is used as the corresponding reference value at present.

[0096] In a possible implementation manner, generate a diagnosis and treatment suggestion for the benign tumor, please refer to Figure 5 , and the specific content includes:

[0097] Step 51, compare the current situation coefficient corresponding to the benign tumor with the reference status coefficient corresponding to the benign tumor stored in the database. If the current situation coefficient corresponding to the benign tumor is greater than the reference status coefficient corresponding to the benign tumor stored in the database, it is determined that the status of the benign tumor is dangerous;

[0098] Step 52, if the current situation coefficient corresponding to the benign tumor is less than or equal to the reference status coefficient corresponding to the benign tumor stored in the database, it is determined that the status of the benign tumor is safe.

[0099] Step 53, generate corresponding diagnosis and treatment suggestions based on different status determination results of the benign tumor.

[0100] For example, when it is determined that the status of the benign tumor is dangerous, a diagnosis and treatment suggestion for surgical resection can be generated; when it is determined that the status of the benign tumor is safe, a diagnosis and treatment suggestion for observing the tumor stage, instructing precautions and review time can be generated, and the patient will carry out stage convalescence according to the precautions and conduct tumor review according to the review time.

[0101] For example, the precautions include balanced diet, appropriate exercise, ensuring sufficient sleep and avoiding smoking and alcohol, etc.

[0102] In a possible implementation manner, obtain the pathological type corresponding to the malignant tumor, and the specific obtaining process is as follows:

[0103] By comparing the position corresponding to the malignant tumor with the positions of various pathological tumors stored in the database; when the position of the malignant tumor is the same as the position corresponding to the pathological tumor in the database, record the case tumor, and screen out the pathological tumors with matching positions to obtain the screened pathological tumors;

[0104] Compare the extracted malignant tumor features with the set of features corresponding to the screened pathological tumors one by one; when a malignant tumor feature is included in a certain pathological tumor feature of the screened pathological tumor, the pathological type corresponding to the pathological tumor is used as the pathological type of the current malignant tumor.

[0105] In the embodiments of the present application, pathological types include adenocarcinoma, squamous cell carcinoma, meningioma, and benign fibroadenoma, etc.

[0106] In a possible implementation manner, intensity distribution data corresponding to a malignant tumor is extracted from a tumor image, and the invasiveness corresponding to the malignant tumor is analyzed. The specific analysis process is as follows:

[0107] Based on the tumor image, obtain the blood vessel distribution corresponding to the tumor location, and extract the number of blood vessels distributed around the malignant tumor.

[0108] Obtain the blood oxygen content and blood flow nutrition value from the blood test results corresponding to the patient, and comprehensively obtain the intensity distribution data corresponding to the malignant tumor in the tumor image based on this. The intensity distribution data includes the number of blood vessels distributed around the tumor, the blood oxygen content, and the blood flow nutrition value.

[0109] Input the intensity distribution data corresponding to the malignant tumor in the tumor image into a deep learning model, and obtain the activity value corresponding to the malignant tumor based on a preset formula. If the trend result of the activity value corresponding to the malignant tumor is 0, it is determined that the malignant tumor is active and its invasiveness is strong, and strong inhibitory measures need to be taken immediately. If the trend result of the activity value corresponding to the malignant tumor is -1, it is determined that the malignant tumor is inactive and its invasiveness is weak, and conservative treatment measures can be taken, so as to analyze the invasiveness corresponding to the malignant tumor.

[0110] In a possible implementation manner, obtain the activity value corresponding to the malignant tumor based on a preset formula. The preset formula is as follows:

[0111]

[0112] Among them, PL is the activity value corresponding to the malignant tumor, N′ is the set reference blood vessel number, N is the number of blood vessels distributed around the malignant tumor, S′ is the set reference blood oxygen content, S is the blood oxygen content of the blood flow distributed around the malignant tumor, B′ is the set reference blood flow nutrition value, B is the blood flow nutrition value of the blood vessels distributed around the malignant tumor, and Z is the set reference activity value.

[0113] In the embodiments of the present application, deep learning technologies include neural networks, generative adversarial networks, and multi-modal learning, etc.

[0114] In the embodiments of the present application, various standard values are jointly discussed and formulated by multiple professional medical staff, and each standard value is used as the corresponding reference value.

[0115] In the embodiments of the present application, the vascular blood flow nutrition value is the nutrients corresponding to blood transportation, including carbohydrates, proteins and amino acids, fats, vitamins, minerals, water, etc.

[0116] In the embodiments of the present application, the blood test results corresponding to the patient are included in the inspection process corresponding to the patient. The inspection process includes blood sampling and irradiation, etc.

[0117] The present application extracts the tumor characteristics of the patient, judges the manifestation results corresponding to the tumor characteristics, and generates different diagnosis and treatment suggestions based on the manifestation results. In the process of judging tumor invasiveness, by combining the number of blood vessels distributed around the patient's tumor, blood oxygen content, and blood flow nutrition value, the activity value corresponding to the malignant tumor is obtained, and then the invasiveness of the malignant tumor is judged. This makes it possible to make up for misdiagnosis and missed diagnosis caused by poor tumor imaging during the process of judging tumor invasiveness, ensures the effectiveness of tumor result analysis, improves the accuracy of the patient's tumor analysis results, and provides guarantee for the patient.

[0118] Step 203: Generate a diagnosis and treatment suggestion corresponding to the malignant tumor based on the invasiveness corresponding to the malignant tumor.

[0119] In the field of the present application, the invasiveness corresponding to the malignant tumor is the activity degree of the tumor, and each clinical malignant tumor is the treatment record of the malignant tumor that has been in treatment or has completed treatment; obtain each activity value corresponding to the clinical malignant tumor from the database, calculate the average value of each activity value corresponding to the clinical malignant tumor, and obtain the average activity value, and use the average activity value as the reference activity value.

[0120] In a possible implementation manner, the process of generating a diagnosis and treatment suggestion corresponding to the tumor is specifically as follows:

[0121] Based on the clustering algorithm, obtain the classification cluster to which the pathological type corresponding to the malignant tumor belongs among the clinical malignant tumors stored in the database. During the classification based on the clustering algorithm, by clustering and classifying historical data, different clustering clusters are obtained. When new data is added, based on the characteristics of the new data, it is added to the corresponding classification cluster, and relevant characteristics are extracted from the corresponding classification cluster.

[0122] Compare the pathological type corresponding to the malignant tumor with the pathological type of the classification cluster to which the patient belongs. If the pathological type corresponding to the malignant tumor is the same as a certain type of malignant tumor in the classification cluster to which the patient belongs, obtain each reference activity value at each stage corresponding to the pathological type of the classification cluster, and use the pathological type of the classification cluster as the first pathological type.

[0123] Compare the activity value corresponding to the malignant tumor with the reference activity values of each stage corresponding to the first pathological type. If the activity value corresponding to the malignant tumor is the same as the reference activity value of a certain stage corresponding to the first pathological type, obtain the diagnosis and treatment suggestions corresponding to the reference activity value of this stage of the patient's first pathological type.

[0124] In the embodiment of the present application, based on the clustering algorithm, obtain the classification clusters to which the pathological type corresponding to the malignant tumor belongs among the various clinical malignant tumors stored in the database, including:

[0125] Divide the data of each clinical malignant tumor stored in the database into K clusters; use the data points of the K clusters as the initial cluster centers;

[0126] Assign data points to clusters: For each data point of each clinical malignant tumor stored in the database, calculate the distance between each data point and the K cluster centers, and the Euclidean distance can be used to assign each data point to the cluster corresponding to the nearest cluster center;

[0127] Update the cluster centers: After each data point is assigned to the corresponding cluster, calculate the mean value of all the data in each cluster, use the mean value of each cluster as the new cluster center, and update the cluster centers;

[0128] By repeatedly executing the steps of assigning data points to clusters and updating the cluster centers, continuously reassign the data points to the clusters corresponding to the updated cluster centers, and update the cluster centers until the maximum number of iterations is reached or the positions of the cluster centers no longer change, then complete the classification of the data of each clinical malignant tumor stored in the database.

[0129] Calculate the distance between the pathological type corresponding to the malignant tumor and the K cluster centers, divide the pathological type corresponding to the malignant tumor into the classification cluster corresponding to the nearest cluster center, and obtain the classification cluster to which the pathological type corresponding to the malignant tumor belongs.

[0130] Based on the invasiveness corresponding to the malignant tumor, obtain the diagnosis and treatment suggestions for the patient, thereby helping the doctor obtain effective diagnosis and treatment references, reducing the doctor's workload, achieving effective tumor intervention, enabling the patient to receive efficient treatment, and ensuring the patient's physical health.

[0131] In the present application, by using the clustering algorithm to obtain the classification clusters to which the pathological type corresponding to the malignant tumor belongs among the various clinical malignant tumors stored in the database, the patient can obtain personalized diagnosis and treatment suggestions that are more in line with their own characteristics.

[0132] In the embodiment of the present application, the data of each clinical malignant tumor stored in the database includes the patient's age, gender, tumor location, tumor size, case type, laboratory test indicators; among them, the laboratory test indicators include: blood routine, biochemical indicators, tumor markers, etc.

[0133] In the embodiments of the present application, tumor information display is further included, that is, step 204, tumor information display: displaying the manifestation result corresponding to the tumor, the diagnosis and treatment suggestions corresponding to the benign tumor, the pathological type corresponding to the malignant tumor, and the diagnosis and treatment suggestions corresponding to the malignant tumor.

[0134] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), etc., or a random access memory (RAM), etc.

[0135] It should be understood that although the steps in the flowchart of the accompanying drawings are displayed in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. Their execution order is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

[0136] Continue to refer to Figure 6 , the tumor image analysis and processing system described in this embodiment includes:

[0137] A tumor image acquisition module 601, configured to acquire a tumor image of a patient corresponding to an irradiation item;

[0138] A feature judgment module 602, configured to extract comprehensive features of a tumor based on a patient's tumor image, and judge the manifestation result corresponding to the tumor based on the comprehensive features; if the tumor is benign, obtain basic data corresponding to the current benign tumor and generate diagnosis and treatment suggestions for the benign tumor; if the tumor is malignant, obtain the pathological type corresponding to the malignant tumor, and extract intensity distribution data corresponding to the malignant tumor, and analyze the invasiveness corresponding to the malignant tumor;

[0139] A diagnosis and treatment suggestion generation module 603, configured to generate diagnosis and treatment suggestions corresponding to a malignant tumor based on the invasiveness corresponding to the malignant tumor.

[0140] To solve the above technical problems, the embodiments of the present application also provide a computer device. Specifically, please refer to Figure 7 , Figure 7 This is the basic structural block diagram of the computer device in this embodiment.

[0141] The computer device 7 includes a memory 7a, a processor 7b, and a network interface 7c that are communicatively connected to each other via a system bus. It should be noted that only the computer device 7 with components 7a - 7c is shown in the figure, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Among them, those skilled in the art of the present technology can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0142] The computer device can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device can perform human-computer interaction with the user through means such as a keyboard, a mouse, a remote control, a touchpad, or a voice control device.

[0143] The memory 7a includes at least one type of readable storage medium, and the readable storage medium includes flash memory, a hard disk, a multimedia card, a card-type memory (such as an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 7a can be an internal storage unit of the computer device 7, such as the hard disk or memory of the computer device 7. In other embodiments, the memory 7a can also be an external storage device of the computer device 7, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device 7. Of course, the memory 7a can also include both the internal storage unit and the external storage device of the computer device 7. In this embodiment, the memory 7a is generally used to store the operating system and various application software installed on the computer device 7, such as the program code of the tumor image analysis and processing method. In addition, the memory 7a can also be used to temporarily store various types of data that have been output or will be output.

[0144] In some embodiments, the processor 7b may be a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips. The processor 7b is generally used to control the overall operation of the computer device 7. In this embodiment, the processor 7b is used to run the program code stored in the memory 7a or process data, such as running the program code of the tumor image analysis processing method.

[0145] The network interface 7c may include a wireless network interface or a wired network interface, which is generally used to establish a communication connection between the computer device 7 and other electronic devices.

[0146] The present application also provides another implementation manner, that is, to provide a non-volatile computer-readable storage medium storing a program of the tumor image analysis processing method, and the tumor image analysis processing can be executed by at least one processor, so that the at least one processor executes the steps of the tumor image analysis processing method as described above.

[0147] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the various embodiments of the present application.

[0148] Obviously, the above-described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The preferred embodiments of the present application are shown in the drawings, but do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure content of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions described in the foregoing specific embodiments, or perform equivalent replacements for some of the technical features. Any equivalent structure directly or indirectly using the content of the specification and drawings of the present application in other related technical fields shall be within the scope of the patent protection of the present application by the same token.

Claims

1. A tumor image analysis and processing method, characterized in that: include: Obtain tumor images of patients corresponding to irradiation items; Based on the patient's tumor image, the comprehensive characteristics of the tumor are extracted, and the corresponding appearance results of the tumor are judged based on the comprehensive characteristics; if the tumor is benign, the basic data corresponding to the current benign tumor is obtained, and the diagnosis and treatment recommendations for the benign tumor are generated; if the tumor is malignant, the pathological type corresponding to the malignant tumor is obtained, and the intensity distribution data corresponding to the malignant tumor is extracted to analyze the invasiveness of the malignant tumor; Based on the corresponding invasiveness of the malignant tumor, corresponding diagnosis and treatment recommendations for the malignant tumor are generated.

2. The tumor image analysis and processing method according to claim 1, characterized in that: Extract corresponding tumor features, including: Determine the location of the tumor corresponding to the tumor image based on the known current characteristics of the tumor; Based on the location of the corresponding tumor, the shape and boundary of the tumor are extracted from the tumor image through contour detection technology; The gray-level co-occurrence matrix technology is used to extract the texture corresponding to the tumor from the tumor image; Based on the scanning of the irradiation position corresponding to the irradiation device, a feedback echo signal value corresponding to the irradiation position during irradiation is obtained; The shape and boundary, texture and feedback echo signal value corresponding to the tumor are taken as the comprehensive features of the corresponding tumor.

3. The tumor image analysis and processing method according to claim 1, characterized in that: The tumor's corresponding appearance results are determined based on comprehensive features, including: Matching the features corresponding to the extracted tumor with the feature sets corresponding to each type of tumor stored in the database; When the feature match is included in the feature set corresponding to the benign tumor stored in the database, the appearance result of the current tumor is determined to be a benign tumor; otherwise, it is determined to be a malignant tumor; The judgment result of feature matching is used as the visualization result corresponding to the tumor.

4. The tumor image analysis and processing method according to claim 1, characterized in that: Obtain the basic data corresponding to the current benign tumor, including: Based on the tumor image, the corresponding position of the benign tumor is confirmed; according to the corresponding position of the benign tumor, the corresponding current data of the benign tumor is extracted, including the current area of ​​the tumor, the space occupied by the tumor compressed tissue, and the frequency of tumor pain obtained during the patient's consultation is substituted into the preset formula; The preset formula is: Among them, LX is the current coefficient corresponding to the benign tumor, F′ is the set reference tumor current area, G′ is the set reference tumor compression tissue space, K′ is the set reference tumor pain frequency, F is the current tumor area corresponding to the benign tumor, G is the current tumor compression tissue space corresponding to the benign tumor, and K is the current tumor pain frequency corresponding to the benign tumor.

5. The tumor image analysis and processing method according to claim 1, characterized in that: Generates recommendations for the diagnosis and treatment of benign tumors, including: The current state coefficient corresponding to the benign tumor is compared with the reference state coefficient corresponding to the benign tumor stored in the database. If the current state coefficient corresponding to the benign tumor is greater than the reference state coefficient corresponding to the benign tumor stored in the database, the benign tumor state is determined to be dangerous. If the current state coefficient corresponding to the benign tumor is less than or equal to the reference state coefficient corresponding to the benign tumor stored in the database, the benign tumor state is determined to be safe; Based on the different status determination results of benign tumors, corresponding diagnosis and treatment recommendations are generated.

6. The tumor image analysis and processing method according to claim 1, characterized in that: Obtain the pathological type corresponding to the malignant tumor, including: Compare the corresponding position of the malignant tumor with the positions of various pathological tumors stored in the database; when the position of the malignant tumor is the same as the corresponding position of the pathological tumor in the database, record the tumor in the case, and screen out the pathological tumors with the matching position to obtain the screened pathological tumor; The extracted malignant tumor features are compared one by one with the feature set corresponding to the screened pathological tumor; when the malignant tumor feature is included in a certain pathological tumor feature of the screened pathological tumor, the pathological type corresponding to the pathological tumor is used as the pathological type of the current malignant tumor.

7. The tumor image analysis and processing method according to claim 1, characterized in that: Extract the intensity distribution data corresponding to the malignant tumor, including: Obtain the vascular distribution corresponding to the tumor location based on the tumor image, and extract the number of blood vessels distributed around the malignant tumor; Based on the blood oxygen content and blood flow nutrient value obtained from the patient's corresponding blood sampling results, the intensity distribution data corresponding to the malignant tumor in the tumor image is comprehensively obtained; The intensity distribution data corresponding to the malignant tumor in the tumor image is input into the deep learning model, and the activity value corresponding to the malignant tumor is obtained based on the preset formula. If the trend result of the activity value corresponding to the malignant tumor is 0, it is determined that the malignant tumor is active and has strong invasiveness; If the activity value trend result corresponding to the malignant tumor is -1, it is judged that the malignant tumor is inactive and its invasiveness is weak.

8. The tumor image analysis and processing method according to claim 7, characterized in that: The activity value corresponding to the malignant tumor is obtained based on the preset formula, which is as follows: Among them, PL is the activity value corresponding to the malignant tumor, N′ is the set reference number of blood vessels, N is the number of blood vessels distributed around the malignant tumor, S′ is the set reference blood oxygen content, S is the blood oxygen content of the blood flow distributed around the malignant tumor, B′ is the set reference blood flow nutrient value, B is the blood flow nutrient value of the blood vessels distributed around the malignant tumor, and Z is the set reference activity value.

9. The tumor image analysis and processing method according to claim 1, characterized in that: Generates diagnosis and treatment recommendations for malignant tumors, including: Based on the clustering algorithm, the classification clusters to which the pathological types corresponding to the malignant tumors belong in each clinical malignant tumor stored in the database are obtained; Compare the pathological type corresponding to the malignant tumor with the pathological type of the classification cluster to which the patient belongs. If the pathological type corresponding to the malignant tumor is the same as a certain type of malignant tumor in the classification cluster to which the patient belongs, obtain the reference activity values ​​of each stage corresponding to the pathological type of the classification cluster, and use the pathological type of the classification cluster as the first pathological type; The activity value corresponding to the malignant tumor is compared with the reference activity value of each stage corresponding to the first pathological type. If the activity value corresponding to the malignant tumor is the same as the reference activity value of a certain stage corresponding to the first pathological type, the diagnosis and treatment recommendations for the reference activity value corresponding to the first pathological type of the patient at that stage are obtained.

10. A tumor image analysis and processing system, used to implement the tumor image analysis and processing method of claims 1-9, characterized in that: include: A tumor image acquisition module, used to acquire tumor images corresponding to the irradiation project of the patient; The feature judgment module is used to extract the comprehensive features of the tumor based on the patient's tumor image, and judge the corresponding appearance results of the tumor based on the comprehensive features; if the tumor is benign, the basic data corresponding to the current benign tumor is obtained, and the diagnosis and treatment recommendations for the benign tumor are generated; if the tumor is malignant, the pathological type corresponding to the malignant tumor is obtained, and the intensity distribution data corresponding to the malignant tumor is extracted to analyze the invasiveness of the malignant tumor; The diagnosis and treatment recommendation generation module is used to generate diagnosis and treatment recommendations corresponding to malignant tumors based on the invasiveness of the malignant tumors.

Images