Intelligent display method, system, medium and device for tumor images
By acquiring and verifying tumor image data, feature fusion and displaying are solved, and the problems of low application efficiency and data security of tumor image films are achieved, and efficient and safe image information display is achieved.
Patent Information
- Application Number
- CN202410908272.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-08
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-07-08
AI Technical Summary
In the prior art, tumor images need to be viewed and analyzed separately one by one, resulting in low application efficiency and difficult to guarantee the security and privacy protection of medical data.
By obtaining multiple tumor image photos and related information of the patient, performing permission verification, obtaining feature maps and fusion of features, generating target image photos, combining patient-related information for visual display, providing an intuitive interactive interface to ensure data security and privacy protection .
It realizes unified processing and comprehensive display of multiple types of tumor images, improves the application efficiency of oncology medical imaging, ensures data security and privacy protection, and provides an intuitive way to understand patient information.
Smart Images

Figure CN118444829B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of medical image display technology, and in particular to an intelligent display method, system, medium and device for tumor images. Background Art
[0002] With the continuous development of medical imaging technology, various high-precision imaging devices are widely used in clinical practice. These devices can produce a large number of detailed medical images, providing important support for medical diagnosis. Especially in the field of tumor imaging, different types of imaging technologies, such as CT, MRI and PET, each have their own unique advantages and can reveal the characteristics of tumors from different angles.
[0003] At present, medical institutions usually take various types of tumor images for patients in order to fully understand the condition of the tumor. These tumor images are usually stored in the hospital's information system in digital form, or presented in the form of physical images. However, since different types of tumor images often need to be viewed and analyzed independently, this brings certain inconveniences to doctors or patients, resulting in low efficiency in the application of tumor images. Summary of the invention
[0004] The present application provides a method, system, medium and device for intelligently displaying tumor images, which can improve the application efficiency of tumor images.
[0005] In a first aspect, the present application provides a method for intelligently displaying tumor images, the method comprising:
[0006] Acquire multiple tumor image photos and patient-related information of the patient, and perform authority verification based on the patient-related information and each of the tumor image photos to obtain an authority verification result;
[0007] When the permission verification result is passed, obtaining a feature map corresponding to each of the tumor image photos;
[0008] Based on the patient-related information, the feature maps are feature-fused to obtain a target image photo, wherein the target image photo includes a plurality of tumor features and feature data corresponding to each of the tumor features;
[0009] In response to the patient's click operation, the target image photo is visualized based on the click operation.
[0010] By adopting the above technical solution, by obtaining multiple tumor images and patient-related information of the patient and performing authority verification, the problem of medical data security and privacy protection is effectively solved. After the authority verification is passed, the feature map corresponding to each tumor image is obtained, and feature fusion is performed based on the patient-related information to obtain a target image containing multiple tumor features and their corresponding feature data. It not only integrates the image data from different imaging devices, but also makes full use of the patient's personal information, realizes the unified processing and comprehensive display of multiple types of tumor images, and visualizes the target image by responding to the patient's click operation, providing an intuitive and interactive interface, so that patients can more clearly and comprehensively understand the medical image information of their own tumors. Compared with the existing technology, it overcomes the inconvenience of needing to view and analyze different types of images one by one in the traditional system, and improves the application efficiency of tumor medical images.
[0011] Optionally, the obtaining of multiple tumor imaging photos of the patient and patient-related information includes:
[0012] After obtaining the first identity information of the patient, generating a prompt message for second identity verification based on the first identity information;
[0013] When the second identity authentication is successful, the patient-related information of the patient is retrieved, and multiple tumor images of the patient are scanned to obtain tumor image photos corresponding to each of the tumor images, and the tumor image films include at least any one of the CT image films, MRI image films and PET image films.
[0014] By adopting the above technical solution, the patient's first identity information is first obtained, and then the second identity authentication prompt information is generated based on the information, which further improves the security of medical data access. This multi-level identity authentication method effectively prevents unauthorized access and provides stronger protection for the patient's privacy information. When the second identity authentication is successful, the system will scan the patient's tumor image, which not only ensures the legitimacy of data access, but also optimizes the efficiency of system resource utilization.
[0015] Optionally, performing authority verification based on the patient-related information and each of the tumor imaging photos to obtain an authority verification result includes:
[0016] Identifying metadata in each of the tumor image photos, the metadata including the identity of the subject and the time of shooting;
[0017] Based on the shooting times, calculating the shooting time difference between the tumor image photos;
[0018] Determine whether the identity of the photographed person is consistent with the identity information in the patient-related information, and whether each of the time differences is less than a time difference threshold;
[0019] When the identity of the photographed person is consistent with the identity information in the patient-related information, and the time difference is less than the time difference threshold, determining that the authority verification result is passed;
[0020] When the identity of the photographed person is inconsistent with the identity information in the patient-related information, or the time difference is not less than a time difference threshold, it is determined that the authority verification result is a failure.
[0021] By adopting the above technical solution, by identifying the metadata in the image photos, especially the identity of the subject and the shooting time, by calculating the shooting time difference between different image photos, and comparing it with the preset time difference threshold, it is possible to effectively determine whether these images belong to the same continuous diagnosis and treatment process. At the same time, by comparing the identity of the subject with the identity information in the patient-related information, it can be ensured that the viewed image does belong to the current patient. This multi-dimensional verification method not only improves the security of data access, but also greatly reduces the risk of medical data mismatch. The system will only allow access when the identity of the subject is consistent and the time difference is within a reasonable range. This strict control mechanism effectively protects the privacy of patients, while also ensuring the integrity and continuity of medical data. In addition, it can prevent the image data of different patients from being mistakenly mixed or compared.
[0022] Optionally, the obtaining of the feature graph corresponding to each of the tumor image photos includes:
[0023] Performing image preprocessing on each of the tumor images to obtain a standard tumor image;
[0024] The electronic identifier on the tumor image photo is scanned to obtain characteristic data corresponding to each tumor image photo, and the characteristic data is recorded on the corresponding standard tumor image photo to obtain a characteristic map corresponding to each tumor image photo.
[0025] By adopting the above technical solution, each tumor image photo is preprocessed to obtain a standard tumor image photo, achieving the standardization of images of different sources and types. By scanning the electronic identification on the tumor image photo, the feature data corresponding to each image photo can be quickly and accurately obtained. Not only the efficiency of data extraction is improved, but also the accuracy of feature data is ensured. The extracted feature data is recorded on the corresponding standard tumor image photo to form a feature map, so that the feature map not only retains the visual information of the original image, but also contains rich quantitative feature data, providing doctors and patients with more comprehensive and intuitive information.
[0026] Optionally, based on the patient-related information, the feature fusion of each feature map to obtain a target image photo includes:
[0027] Determining a weight coefficient of each of the feature graphs based on the patient-related information;
[0028] Perform weighted superposition on each of the feature maps according to the corresponding weight coefficients to obtain a fused feature map;
[0029] Performing image registration on the fusion feature map and each of the standard tumor image photos to obtain a registered fusion feature map;
[0030] The registered fusion feature map is superimposed on a preset human body model map to obtain the target image photo.
[0031] By adopting the above technical solution, the weight coefficient of each feature map is determined based on the patient-related information, which fully considers the individual differences of patients and realizes the personalization of image analysis. By weighted superposition of each feature map according to the corresponding weight coefficient, a fused feature map is obtained, which not only integrates the information from different types of images, but also highlights the features that are more important to specific patients. The fused feature map is image registered with each standard tumor image photograph to ensure the precise correspondence of data from different sources in spatial position and improve the accuracy of the fusion result. Finally, the registered fused feature map is superimposed on the preset human body model map to obtain the target image photograph, which converts the abstract feature data into an intuitive visual representation, so that doctors and patients can more easily understand the location and characteristics of the tumor.
[0032] Optionally, in response to the patient's click operation, visually displaying the target image photo based on the click operation includes:
[0033] In response to a click operation by the patient, determining a request type corresponding to the click operation;
[0034] If the request type is a local display request, determining a target area corresponding to the click operation; judging whether the target area includes a tumor feature; when the target area includes the tumor feature, generating a detailed information interface of the tumor feature based on feature data corresponding to the tumor feature, and superimposing and displaying the detailed information interface on the display interface of the target image photo, wherein the detailed information interface includes at least one of the size, shape, location, growth rate, malignancy and metabolic activity of the tumor;
[0035] If the request type is an overall display request, a multi-dimensional tumor evolution visualization interface is generated for display based on the tumor features and corresponding feature data in the target image photo.
[0036] By adopting the above technical solution, the request type is determined by responding to the patient's click operation, and the intelligent selection of the display method is realized. For local display requests, the target area corresponding to the click operation is accurately located. When the target area contains tumor features, a detailed information interface is generated based on the data of the feature, and the interface is superimposed on the display interface of the target image photo, so that the patient can quickly and intuitively obtain specific information about the area of interest. For overall display requests, a multi-dimensional tumor evolution visualization interface is generated based on all tumor features and corresponding feature data in the target image photo. By providing both local and overall display methods, it not only meets the needs of in-depth analysis of specific areas, but also provides a macro overview of the disease, greatly improving the readability and practicality of the image information.
[0037] Optionally, the patient-related information further includes multimodal physiological data of the patient, and the method further includes:
[0038] When the permission verification result is passed, the multimodal physiological data is time-synchronized with the target image photo to obtain a synchronized data set;
[0039] In a three-dimensional coordinate system, the target image photo is mapped to the XY plane, and the time axis is mapped to the Z axis;
[0040] Along the Z-axis direction, the multimodal physiological data is displayed in the form of curves of different colors;
[0041] Generate an interactive data cube in the three-dimensional coordinate system, wherein the XY plane represents the spatial dimension and the Z axis represents the time dimension, and connect the key feature points of the target image photo with the physiological data nodes at the corresponding time points on the surface of the data cube to form a feature-physiological association network diagram;
[0042] In response to a user's click operation on the feature-physiology association network diagram, the feature-physiology association network diagram is visualized.
[0043] By adopting the above technical solution, the multimodal physiological data and the target image photos are time-synchronized to obtain a synchronized data set, which ensures the consistency of different types of data in the time dimension. By mapping the target image photos to the XY plane of the three-dimensional coordinate system and mapping the time axis to the Z axis, an intuitive three-dimensional data display space is created. The multimodal physiological data are displayed in the form of curves of different colors along the Z axis, making the time series data clearly visible. By generating an interactive data cube in the three-dimensional coordinate system, the key feature points of the target image photos are connected to the physiological data nodes at the corresponding time points to form a feature-physiological association network. This visualization method intuitively displays the potential association between image features and physiological data, providing patients with a more intuitive and easier to understand way to understand their own health status, further improving the efficiency of image use.
[0044] In a second aspect of the present application, a system for intelligently displaying tumor images is provided, the system comprising:
[0045] The permission verification module is used to obtain multiple tumor image photos of the patient and patient-related information, and perform permission verification based on the patient-related information and each of the tumor image photos to obtain a permission verification result;
[0046] A feature map acquisition module, used for acquiring a feature map corresponding to each tumor image photo when the permission verification result is passed;
[0047] A feature data acquisition module, configured to perform feature fusion on each of the feature maps based on the patient related information to obtain a target image photo, wherein the target image photo includes a plurality of tumor features and feature data corresponding to each of the tumor features;
[0048] The visualization display module is used to respond to the patient's click operation and to perform a visualization display on the target image photo based on the click operation.
[0049] In a third aspect of the present application, a computer storage medium is provided, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the above method steps.
[0050] In a fourth aspect of the present application, an electronic device is provided, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.
[0051] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
[0052] This application effectively solves the problem of medical data security and privacy protection by obtaining multiple tumor images and patient-related information of the patient and performing authority verification. After the authority verification is passed, the feature map corresponding to each tumor image photo is obtained, and feature fusion is performed based on the patient-related information to obtain a target image photo containing multiple tumor features and their corresponding feature data. It not only integrates the image data from different imaging devices, but also makes full use of the patient's personal information, realizes the unified processing and comprehensive display of various types of tumor images, and visualizes the target image photos by responding to the patient's click operation, providing an intuitive and interactive interface, so that patients can more clearly and comprehensively understand the medical image information of their own tumors. Compared with the existing technology, it overcomes the inconvenience of needing to view and analyze different types of images one by one in the traditional system, and improves the efficiency of using tumor medical images. BRIEF DESCRIPTION OF THE DRAWINGS
[0053] Figure 1 It is a flowchart of a method for intelligently displaying tumor images provided in an embodiment of the present application;
[0054] Figure 2 It is a module schematic diagram of an intelligent display system for tumor images provided in an embodiment of the present application;
[0055] Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.
[0056] Description of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION
[0057] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.
[0058] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.
[0059] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.
[0060] The following will provide a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.
[0061] The embodiments of the present application can be applied to the intelligent image display machine of the oncology department of the hospital. This intelligent display machine can be set up in a special area of the hospital, such as the public area of the oncology outpatient department or the inpatient department or the doctor's office. The intelligent display machine is equipped with a large-size touch screen and supports multi-touch operation, which is convenient for patients and doctors to interactively view and analyze images. The intelligent display machine can also be connected to the hospital's information system to realize data interaction with the electronic medical record. Patients can put their various tumor images into the display machine for scanning. The intelligent display machine is equipped with a high-resolution scanning device that can quickly and accurately scan various types of tumor images, including different types of images such as CT, MRI and PET. After the scan is completed, the display machine will automatically perform image processing and feature extraction, and perform personalized data fusion and display based on the patient's personal information.
[0062] It should be noted that in another feasible embodiment, if the hospital takes into account the sensitivity of medical data and the need for privacy protection, for example, some complex analysis functions or the viewing of sensitive information must be performed under the doctor's authority. In this case, the doctor can accompany the patient to use the smart display machine, and with the doctor's authority, explain the imaging results to the patient on the smart display machine and conduct more in-depth analysis and discussion.
[0063] Please refer to Figure 1 , a flowchart of a method for intelligent display of tumor images is proposed, the method can be implemented by a computer program, can be implemented by a single-chip microcomputer, and can also be run on an intelligent display system for tumor images. The computer program can be integrated in a computer device, or can be run as an independent tool application. Specifically, the method includes steps 10 to 40, and the above steps are as follows:
[0064] Step 10: Obtain multiple tumor image photos and patient-related information of the patient, and perform permission verification based on the patient-related information and each tumor image photo to obtain a permission verification result.
[0065] Tumor imaging photos refer to digital images obtained through various medical imaging technologies that show tumors and surrounding tissue structures in the human body. In the embodiments of the present application, tumor imaging photos refer to digitized image files rather than traditional films. These digital images can be directly read and processed by the intelligent display system.
[0066] Patient-related information in this embodiment of the application refers to a series of data closely related to the patient and his or her health status, including but not limited to personal basic information, medical history, current health status, treatment-related information, multimodal physiological data, and imaging detection records.
[0067] In the embodiments of the present application, permission verification refers to a key security mechanism used to ensure that only authorized users can access and view tumor imaging data and related information, mainly including identity verification and time validity verification of the image films.
[0068] Specifically, patients can authenticate their identity on the intelligent imaging display machine through biometrics or ID cards. Once the authentication is passed, the system obtains multiple tumor images of the patient through scanning equipment or hospital database interface. These tumor images may come from different imaging devices such as CT, MRI or PET. At the same time, the system will also extract relevant information of the patient from the hospital's electronic medical record system based on the patient's identity information, including basic personal information, medical history and current health status.
[0069] Permission verification is performed based on the obtained patient-related information and each tumor image photo, mainly to protect patient privacy and ensure data security. First, the system will identify the metadata in the tumor image photo, especially the identity of the subject and the shooting time, and compare the identity of the subject with the identity of the user currently requesting access. It will also calculate the shooting time difference between different image photos to ensure that these time differences are within the preset reasonable range. This multi-level verification mechanism can effectively prevent unauthorized access and data confusion. After the verification is completed, the system will display the permission verification results. If the verification passes, the system will allow the user to enter the next stage of data processing and display; if the verification fails, the system will deny access and record the failed attempt.
[0070] It should be noted that the permission verification process may also include checking the user's access level. For example, a patient may only be able to view his or her own imaging data, while a doctor may have the authority to view the data of multiple patients. The system will determine the scope of data and functions that the user can access based on his or her role and permission level.
[0071] Based on the above embodiment, as an optional embodiment, the step of obtaining multiple tumor images of the patient and patient-related information may further include the following steps:
[0072] Step 1011: After obtaining the patient's first identity information, generate prompt information for second identity verification based on the first identity information.
[0073] Specifically, the patient can perform the first identity authentication on the intelligent imaging film display machine by biometrics or ID card, or by entering the patient's name and ID card number. The system will then verify the validity of this information in the background database. When the first identity information is successfully verified, the system will generate a prompt message for the second identity authentication based on this information. The prompt message can be a randomly generated verification code, which is sent to the patient via a text message or email associated with the patient's pre-registered mobile phone number or email address. Alternatively, the system may generate a series of security questions based on the patient's medical record information, such as "When was your last visit?" The process of generating the second identity authentication prompt message will consider multiple factors. First, the system will analyze the reliability of the first identity information. If potential risks are found, the complexity of the second identity authentication may be increased. Second, the system will consider the patient's personal situation. For example, for older patients, easier questions may be selected. In addition, the system will also consider the sensitivity of the data. For highly sensitive information, a more stringent second identity authentication may be required.
[0074] Step 1012: When the second identity verification is successful, retrieve the patient-related information of the patient, and scan multiple tumor images of the patient to obtain tumor image photos corresponding to each tumor image.
[0075] Specifically, when the patient enters the correct random code or correctly answers the security question, the second identity verification is determined to be successful, and the patient-related information of the patient is retrieved from the hospital's electronic medical record system. The patient-related information may include the patient's basic personal information, medical history, and image records. The patient can put the solid tumor image into the intelligent image display machine. When the second identity verification is successful, the system will start the scanning program and scan multiple tumor images in turn. These images may include one of CT images, MRI images, and PET images. The scanning process uses high-resolution digital equipment to ensure that all details on the image can be accurately captured. The system will automatically identify different types of images and use corresponding scanning parameters to obtain the best digitization effect. After the scan is completed, the digital tumor image photos corresponding to each tumor image can be obtained.
[0076] Based on the above embodiment, as an optional embodiment, the step of performing authority verification based on the patient-related information and each tumor image photo to obtain the authority verification result may also include the following steps:
[0077] Step 1021: Identify metadata in each tumor image photo, where the metadata includes the identity of the subject and the shooting time.
[0078] Specifically, metadata recognition can be performed on each digitized tumor image using advanced image processing algorithms and optical character recognition (OCR) technology. The system will automatically scan specific areas of tumor images, such as photo borders or corners. These areas usually contain patient information and shooting details. For different types of imaging equipment (such as CT, MRI, PET, etc.), the system will use corresponding recognition templates to adapt to metadata arrangements in different formats. During the recognition process, two key types of information are extracted: the identity of the subject and the shooting time. The identity of the subject usually includes the patient's name, ID number or medical record number; the shooting time includes the specific date and time of the imaging examination. The system will perform preliminary formatting on the identified information to ensure data consistency and comparability.
[0079] Step 1022: Calculate the shooting time difference between each tumor image photo based on each shooting time.
[0080] Specifically, all tumor images are sorted by shooting time, and the time difference between adjacent images is calculated pair by pair. The calculation uses a high-precision time difference algorithm, which can be accurate to the second level. For time series with a large span, the time difference between non-adjacent images is also calculated to fully understand the entire observation period. The calculated time difference data will be temporarily stored and associated with the corresponding image pairs to prepare for subsequent analysis and display.
[0081] Step 1023: Determine whether the identity of the photographed person is consistent with the identity information in the patient-related information, and whether each time difference is less than a time difference threshold.
[0082] Specifically, the identity information of the subject extracted from the metadata of the tumor image photo is compared with the identity information in the patient-related information previously obtained through identity authentication to determine whether the identity of the subject is consistent with the identity information in the patient-related information. The comparison process uses a string matching algorithm. Considering the possible slight differences (such as different spellings of names), fuzzy matching technology can also be used. At the same time, the system will compare each previously calculated time difference with a preset time difference threshold to determine whether each time difference is less than the time difference threshold. The time difference threshold is dynamic and depends on the acuteness of the patient's tumor and the specific image type combination. For example, if the patient has an acutely progressive tumor, the time difference threshold between CT and MRI images may be set to 7 days; for slowly growing tumors, the time difference threshold may be extended to 30 days, and the time difference between PET-CT images may be allowed to be slightly larger because PET-CT is usually taken less frequently.
[0083] Step 1024: When the identity of the photographed person is consistent with the identity information in the patient-related information, and the time difference is less than the time difference threshold, it is determined that the permission verification result is passed.
[0084] Specifically, the system uses a high-precision string matching algorithm to ensure that the identity of the subject in the tumor image photo is exactly the same as the identity information in the patient-related information obtained through initial verification. This match not only includes the precise matching of names, but can also involve the verification of other unique identifiers, such as patient IDs or medical record numbers. At the same time, the system will review the previously calculated time differences between different types of tumor images to ensure that they are within their respective preset time difference thresholds. Only when both conditions are met will the system mark the permission verification result as "passed".
[0085] Step 1025: When the identity of the photographed person is inconsistent with the identity information in the patient-related information, or the time difference is not less than the time difference threshold, it is determined that the authority verification result is a failure.
[0086] Specifically, when the identity of the subject is inconsistent with the identity information in the patient-related information, or the time difference is not less than the time difference threshold, the permission verification result is determined to be a failure. That is, if either the identity or the time difference does not meet the conditions, subsequent operations cannot be performed. By comparing the identity of the subject with the identity information in the patient-related information, it can be ensured that the viewed image does belong to the current patient. By strictly controlling the time difference between different types of images, it is ensured that the subsequent multimodal image fusion analysis can accurately reflect the patient's current condition and avoid misjudgments that may be caused by the use of outdated or irrelevant data.
[0087] Step 20: When the permission verification result is passed, obtain the feature map corresponding to each tumor image photo.
[0088] A feature map refers to a high-dimensional, highly abstract data representation extracted from original tumor images through image processing and deep learning techniques.
[0089] Specifically, when the result of the permission verification is passed, the original image is preprocessed, including denoising, standardization, and contrast enhancement operations to improve the image quality. Pre-trained deep convolutional neural networks (such as ResNet, DenseNet, etc.) will be used to extract high-level features of the image. These networks have been trained on a large amount of medical image data and can effectively identify key features related to tumors. For different types of tumor images (such as CT, MRI, PET, etc.), feature extraction models optimized specifically for the image modality will be used. For example, for CT images, special attention may be paid to the density and boundary characteristics of the tumor; while for MRI images, the system may pay more attention to tissue contrast and texture information. At the same time, the system will also consider the specific conditions of the patient, such as tumor type and location, to adjust the parameters and focus of feature extraction. The extracted features will be organized into the form of feature maps. A feature map is a multidimensional data structure that contains feature information at various locations in the image. These features may include the size, shape, texture, boundary characteristics, and state of surrounding tissues of the tumor. The system generates a corresponding feature map for each tumor image photo and stores these feature maps in association with the original image and its metadata.
[0090] In another feasible embodiment, the characteristic data can also be obtained directly by scanning the electronic identification on each tumor image photo. The electronic identification can be a QR code, barcode or machine-readable mark embedded in the image, which contains the key characteristic information of the image, that is, various quantitative and qualitative characteristic data, such as the size, shape, position, boundary characteristics, internal structure, etc. of the tumor, and the characteristic data is recorded on the corresponding tumor image photo to obtain the characteristic map corresponding to each tumor image photo.
[0091] Based on the above embodiment, as an optional embodiment, when the permission verification result is passed, the step of obtaining the feature map corresponding to each tumor image photo may further include the following steps:
[0092] Step 201: performing image preprocessing on each tumor image to obtain a standard tumor image.
[0093] Specifically, the system will perform denoising on each tumor image separately, using advanced noise suppression algorithms, such as adaptive median filtering or wavelet transform denoising, to remove random noise in the image and improve the signal-to-noise ratio. Next, the system will perform brightness and contrast standardization, which uses techniques such as histogram equalization or adaptive contrast enhancement to ensure that images from different sources have similar brightness distribution and contrast range.
[0094] The system then performs geometric correction and spatial standardization. This process involves complex image registration algorithms, such as mutual information-based registration methods, which map each image to a predefined standard spatial coordinate system, ensuring that images taken by different patients and at different time points are spatially comparable. For images of different modalities (such as CT, MRI), modality-specific preprocessing is also performed, such as standardization of CT values or normalization of MRI signal intensity. The system then performs image segmentation to accurately locate and extract tumor areas. Deep learning models such as U-Net or Mask R-CNN can be used to automatically identify and segment tumor areas. The segmented tumor areas will be highlighted, while the background tissues will be appropriately suppressed so that subsequent analysis can focus on key areas. Finally, the system will perform a quality assessment on the processed images to ensure that the preprocessing results meet the predetermined quality standards. If the preprocessing results of a certain image do not meet the requirements, the system will automatically adjust the parameters and re-execute the relevant steps until the standards are met, thereby obtaining a standard tumor image.
[0095] Step 202: Scan the electronic mark on the tumor image photo to obtain the characteristic data corresponding to each tumor image photo, and record the characteristic data on the corresponding standard tumor image photo to obtain the characteristic map corresponding to each tumor image photo.
[0096] Specifically, the electronic identifier on the tumor image is scanned, which may be a QR code, barcode, or other machine-readable mark embedded in the corner or edge of the image. The system uses high-precision image recognition algorithms, such as deep learning-based target detection models such as YOLO or Faster R-CNN, to accurately locate and identify these electronic identifiers. These algorithms can maintain a high recognition rate even when the image quality is poor or the identifier is partially obscured. After identifying the electronic identifier, the system decodes the information contained in it, which usually includes metadata such as the image's unique identifier, acquisition device information, and acquisition time. The system uses this information to retrieve detailed feature data associated with the image in the database, which can include quantitative features of the tumor (such as size, volume, shape complexity) and qualitative features (such as edge clarity, internal heterogeneity, and relationship with surrounding tissues).
[0097] The retrieved feature data is accurately mapped to the corresponding standard tumor image. This process involves a complex spatial registration algorithm to ensure that each feature data point can accurately correspond to the correct position on the standard image. The system can use an anatomical landmark-based registration method or an image similarity-based registration algorithm, such as the mutual information maximization method, to achieve this precise mapping. During the mapping process, quantitative indicators can be displayed in the form of numerical labels at specific locations corresponding to specific tumor features, and feature maps corresponding to each tumor image can be obtained.
[0098] Step 30: Based on the patient-related information, the feature maps are feature-fused to obtain a target image photo, which includes multiple tumor features and feature data corresponding to each tumor feature.
[0099] In the embodiment of the present application, the target image photo refers to a highly information-based, personalized comprehensive image representation generated through a feature fusion process.
[0100] Tumor characteristics refer to quantitative and qualitative indicators that describe various aspects of the tumor's attributes, and characteristic data refer to specific numerical values or descriptive information extracted from the target image photographs to characterize the tumor's characteristics.
[0101] Specifically, relevant information of the patient is retrieved, including but not limited to age, gender, medical history, genetic test results, previous treatment records, etc. This information provides important background and constraints for feature fusion. Then, the previously generated feature maps are imported into the feature fusion module. These feature maps may come from different imaging modalities (such as CT, MRI, PET, etc.). For example, based on the cause of the disease in the patient's relevant information, the weight coefficient of each feature map is determined; each feature map is weighted and superimposed according to the corresponding weight coefficient to obtain a fused feature map. A pixel-level weighted summation algorithm can be used, and image processing techniques such as multi-resolution analysis or wavelet transform can be combined to ensure that features of different scales can be reasonably expressed. The fused feature map is image-aligned with each standard tumor image to obtain a fused feature map after alignment. A high-precision non-rigid alignment algorithm can be used, such as a free deformation model based on B-splines or a alignment network based on deep learning. The alignment process takes into account the intensity difference and geometric deformation between images of different modalities to ensure that the fused features can accurately correspond to the standardized anatomical space. Finally, the aligned fused feature map is superimposed on the preset human body model map to obtain the target image photo.
[0102] Based on the above embodiment, as an optional embodiment, based on the patient-related information, the step of fusing the feature maps to obtain the target image photo may further include the following steps:
[0103] Step 301: Determine the weight coefficient of each feature graph based on patient-related information.
[0104] Since the tumor condition of each patient is different, the weight coefficients of different feature maps in the subsequent fusion process are dynamically determined based on the patient-related information, thereby ensuring that the generated target image photos can reflect the patient's individual characteristics and clinical concerns to the greatest extent.
[0105] Specifically, analyze the patient's relevant information. This information may include, but is not limited to, the patient's age, gender, medical history, genetic test results, previous treatment records, current symptoms, and laboratory test results. Using machine learning algorithms, such as support vector machines or random forests, the patient's relevant information (such as age, gender, genetic characteristics, previous treatment history, etc.) is used as input to output the weight coefficients of each feature map. This method ensures the personalization of weight distribution. The weight coefficients are usually between 0 and 1, and the sum is 1, reflecting the relative importance of each modality in a specific patient situation. For example, for a 45-year-old patient who was followed up 6 months after brain glioma surgery: the weight of the feature map corresponding to the CT image is 0.2, the weight of the feature map corresponding to the MRI image is 0.6, and the weight of the feature map corresponding to the PET image is 0.2.
[0106] Step 302: Perform weighted superposition on each feature map according to the corresponding weight coefficient to obtain a fused feature map.
[0107] Specifically, a pixel-level weighted summation algorithm is used, combined with advanced image processing techniques such as multi-resolution analysis or wavelet transform, to ensure that features of different scales can be reasonably expressed. During the fusion process, the system also applies nonlinear mapping functions to handle possible scale differences and complex relationships between different features. This weighted fusion method not only integrates multimodal information, but also retains the key information of each feature map, so that the generated fused feature map can fully reflect the multidimensional characteristics of the tumor.
[0108] Step 303: performing image registration on the fused feature map and each standard tumor image photograph to obtain a registered fused feature map.
[0109] Specifically, a high-precision non-rigid registration algorithm is used, such as a free-deformation model based on B-spline or a registration network based on deep learning. The registration process takes into account the intensity differences and geometric deformations between images of different modalities, ensuring that the fused features can be accurately mapped to the standardized anatomical space. Finally, a registered fusion feature map is obtained. This registered fusion feature map accurately corresponds to the standard tumor image in space, while retaining the key information of the original fusion feature map.
[0110] Step 304: superimpose the registered fusion feature map onto the preset human body model map to obtain a target image photo.
[0111] Specifically, the registered fusion feature map is superimposed on the preset human body model map, which is a high-precision digital human anatomical model that contains detailed organ structures, vascular distribution and important anatomical landmarks. It has been carefully designed to adapt to different body shapes and different anatomical variations, ensuring that the final generated target image has good versatility and specificity. The superposition process uses advanced image fusion and visualization technology. First, the registered fusion feature map is accurately spatially aligned with the human body model map to ensure that each pixel in the fusion feature map can accurately correspond to the corresponding anatomical position of the human body model map. The system uses multi-layer rendering technology, with the human body model map as the bottom layer and the fusion feature map as the upper layer for superposition, converting different information in the fusion feature map into an intuitive visual representation. For example, a heat map may be used to represent metabolic activity, and different color depths may be used to represent the density or degree of spread of the tumor. For key pathological features, such as tumor boundaries or suspected metastatic lesions, the system will apply feature enhancement algorithms. This can include edge sharpening, local contrast enhancement and other technologies to make these important features more prominent in the final target image. By superimposing complex multimodal fusion information onto the familiar human body model graph structure, abstract feature data can be transformed into intuitive visual representations, making it easier for patients to understand the location and characteristics of the tumor.
[0112] Step 40: In response to the patient's click operation, the target image photo is visualized based on the click operation.
[0113] Specifically, the target image photo is displayed on the display screen of the intelligent image display machine. The target image photo is a comprehensive representation of the fusion feature map superimposed on the human body model map, which contains rich anatomical structure and pathological information. The display screen allows patients to interact with the target image photo through a touch screen, mouse or other input devices. When the patient's click operation is detected, the system will respond immediately and perform corresponding visual display according to the click position and content. Since the target image photo not only integrates the image data from different imaging devices, but also makes full use of the patient's personal information, it realizes the unified processing and comprehensive display of various types of tumor images. By responding to the patient's click operation, the target image photo is visualized and displayed, providing an intuitive and interactive interface, so that patients can more clearly and comprehensively understand the medical imaging information of their own tumors. Compared with the existing technology, it overcomes the inconvenience of viewing and analyzing different types of images one by one in the traditional system, and improves the efficiency of the use of tumor medical images.
[0114] Based on the above embodiment, as an optional embodiment, based on the patient-related information and in response to the patient's click operation, the step of visually displaying the target image photo based on the click operation may further include the following steps:
[0115] Step 401: In response to a click operation by a patient, determine a request type corresponding to the click operation.
[0116] Specifically, the patient's click operation on the target image is first captured, including multi-dimensional information such as the precise coordinates of the click, the duration, and the click pattern in a short period of time. Then a multi-level comprehensive analysis is performed to determine the request type. First, the spatial distribution of the click position in the target image is analyzed. If the click position is concentrated in a relatively small area or a specific anatomical structure, the system tends to identify it as a local display request; on the contrary, if the click position is scattered or covers a large range, it may be identified as an overall display request. Secondly, the system considers the temporal characteristics of the click. For example, a quick single click may indicate a local interest in a specific location, while a long press or multiple consecutive clicks may suggest that the patient wants to obtain more comprehensive information and tends to request an overall display.
[0117] Step 402: If the request type is a local display request, determine the target area corresponding to the click operation; determine whether the target area contains tumor features; when the target area contains tumor features, generate a detailed information interface of the tumor features based on the feature data corresponding to the tumor features, and overlay the detailed information interface on the display interface of the target image photo.
[0118] Specifically, if the request type is a local display request, the target area is accurately located based on the patient's click operation. High-precision image segmentation algorithms and spatial mapping technologies can be used to convert the click coordinates into specific anatomical positions and ranges in the target image photo to determine whether the target area contains tumor features. When the target area contains tumor features, all feature data related to the tumor features are obtained. The feature data may include quantitative and qualitative indicators such as the size, shape, boundary features, internal structure, and metabolic activity of the tumor. A detailed information interface for the tumor feature is generated based on these feature data. The detailed information interface includes at least one of the size, shape, location, growth rate, malignancy, and metabolic activity of the tumor. The generated detailed information interface is superimposed on the display interface of the target image photo. This superposition process uses layer management and transparency control technology to ensure that the newly added information does not obscure key image details while clearly presenting all important data.
[0119] Step 403: If the request type is an overall display request, a multi-dimensional tumor evolution visualization interface is generated for display based on the tumor features in the target image photo and the corresponding feature data.
[0120] Specifically, if the request type is an overall display request, based on the tumor features and corresponding feature data in the target image, the patient's pre-stored patient history data and clinical information are combined to perform time series analysis on these multi-dimensional data, track the changing trend of each feature over time, and build a multi-dimensional tumor evolution visualization interface. The core elements of the interface include: Timeline: throughout the entire interface, clearly marking the time node of each data point, so that users can intuitively understand the development process of the tumor; 3D tumor model: using volume rendering technology, create an interactive three-dimensional tumor model to show the morphological changes of the tumor at different time points. Users can rotate and scale this model to observe various aspects of the tumor in depth; Multi-parameter trend chart: using high-dimensional data visualization technology such as parallel coordinates or radar charts, simultaneously display the changing trends of multiple tumor features (such as size, degree of spread, metabolic activity, etc.) over time; Treatment response mapping: marking treatment events (such as surgery, radiotherapy, chemotherapy) on the timeline, and intuitively displaying the effects of various treatments on tumor features through color coding or icons. Comparative analysis view: allowing users to select any two time points, the system will automatically generate a detailed comparative analysis report, highlighting key changes.
[0121] Based on the above embodiment, as an optional embodiment, a method for intelligently displaying tumor images also includes a process of generating and displaying a feature-physiological network, and the specific contents are as follows:
[0122] When the permission verification result is passed, the patient's multimodal physiological data in the patient-related information can also be combined with the target image to generate a feature-physiological network diagram and perform a visual display.
[0123] Specifically, multimodal physiological data (such as heart rate, blood pressure, blood oxygen saturation, etc.) are precisely synchronized with the target image photos in the time dimension to form a unified synchronized data set. This synchronization not only takes into account the differences in acquisition frequencies of different data sources, but also applies interpolation technology to fill possible data gaps to ensure the continuity and consistency of the time series. Construct a three-dimensional visualization framework. In this framework, the target image photos are mapped to the XY plane, representing the spatial dimension; and the time axis is mapped to the Z axis, forming a unified representation method in time and space. This mapping method allows users to intuitively understand the distribution of image features in space and time. Then, along the Z axis, the multimodal physiological data are superimposed and displayed in the form of curves of different colors. Each physiological indicator is given a unique color code, for example, heart rate may be represented by red and blood pressure by blue. This color coding not only enhances the distinguishability of the data, but also helps users quickly identify the changing trends of different physiological parameters.
[0124] Based on this three-dimensional framework, the system further generates an interactive data cube. The XY plane of this cube represents the spatial dimension and displays the target image photos; the Z axis represents the time dimension and displays the changes in physiological data. On the surface of the data cube, the system uses image processing and feature extraction algorithms to identify key feature points in the target image photos. At the same time, significant physiological data nodes are marked at the corresponding time points. Then, connections are established between these feature points and data nodes to form a complex feature-physiological association network diagram. When responding to the user's click operation on the feature-physiological association network diagram, the feature-physiological association network diagram is visualized. The feature-physiological association network diagram intuitively shows the potential association between image features and physiological indicators, providing patients with a more intuitive and easier to understand way to understand their own health status, further improving the efficiency of the use of imaging films.
[0125] See also Figure 2 , is a schematic diagram of a module of an intelligent display system for tumor images provided in an embodiment of the present application. The intelligent display system for tumor images may include: an authority verification module, a feature map acquisition module, a feature data acquisition module, and a visualization display module, wherein:
[0126] The permission verification module is used to obtain multiple tumor image photos of the patient and patient-related information, and perform permission verification based on the patient-related information and each of the tumor image photos to obtain a permission verification result;
[0127] A feature map acquisition module, used for acquiring a feature map corresponding to each tumor image photo when the permission verification result is passed;
[0128] A feature data acquisition module, configured to perform feature fusion on each of the feature maps based on the patient related information to obtain a target image photo, wherein the target image photo includes a plurality of tumor features and feature data corresponding to each of the tumor features;
[0129] The visualization display module is used to respond to the patient's click operation and to perform visualization display on the target image photo based on the click operation.
[0130] Optionally, the authority verification module is also used to generate a prompt message for a second identity authentication based on the patient's first identity information after obtaining the first identity information of the patient; when the second identity authentication is successful, retrieve the patient's related information and scan multiple tumor images of the patient to obtain tumor image photos corresponding to each of the tumor images, wherein the tumor image includes at least one of a CT image, an MRI image and a PET image.
[0131] Optionally, the authority verification module is also used to identify metadata in each of the tumor image photos, the metadata including the identity of the subject and the shooting time; based on each of the shooting times, calculate the shooting time difference between each of the tumor image photos; determine whether the identity of the subject is consistent with the identity information in the patient-related information, and whether each of the time differences is less than a time difference threshold; when the identity of the subject is consistent with the identity information in the patient-related information, and the time difference is less than the time difference threshold, determine that the authority verification result is passed; when the identity of the subject is inconsistent with the identity information in the patient-related information, or the time difference is not less than the time difference threshold, determine that the authority verification result is failed.
[0132] Optionally, the feature map acquisition module is also used to perform image preprocessing on each of the tumor image photos to obtain a standard tumor image photo; scan the electronic mark on the tumor image photo to obtain feature data corresponding to each of the tumor image photos, and record the feature data on the corresponding standard tumor image photo to obtain a feature map corresponding to each of the tumor image photos.
[0133] Optionally, the feature data acquisition module is also used to determine the weight coefficient of each feature map based on the patient-related information; perform weighted superposition on each feature map according to the corresponding weight coefficient to obtain a fused feature map; perform image registration on the fused feature map and each standard tumor image photograph to obtain a registered fused feature map; and superimpose the registered fused feature map on a preset human body model image to obtain the target image photograph.
[0134] Optionally, the visualization display module is also used to determine, in response to the patient's click operation, a request type corresponding to the click operation; if the request type is a local display request, determine the target area corresponding to the click operation; determine whether the target area contains tumor characteristics; when the target area contains the tumor characteristics, generate a detailed information interface of the tumor characteristics based on the characteristic data corresponding to the tumor characteristics, and superimpose the detailed information interface on the display interface of the target image photo, wherein the detailed information interface includes at least one of the size, shape, location, growth rate, malignancy and metabolic activity of the tumor; if the request type is an overall display request, based on the tumor characteristics and corresponding characteristic data in the target image photo, generate a multi-dimensional tumor evolution visualization interface for display.
[0135] Optionally, the visualization display module is also used to, when the permission verification result is passed, time synchronize the multimodal physiological data with the target image photo to obtain a synchronized data set; in a three-dimensional coordinate system, map the target image photo to the XY plane, and map the time axis to the Z axis; along the Z axis direction, display the multimodal physiological data in the form of curves of different colors; generate an interactive data cube in the three-dimensional coordinate system, wherein the XY plane represents the spatial dimension and the Z axis represents the time dimension, and on the surface of the data cube, connect the key feature points of the target image photo with the physiological data nodes at the corresponding time points to form a feature-physiological association network diagram; in response to the user's click operation on the feature-physiological network, visualize the feature-physiological association network diagram.
[0136] It should be noted that: when the system provided in the above embodiment realizes its functions, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.
[0137] An embodiment of the present application also provides a computer storage medium, which can store multiple instructions. The instructions are suitable for being loaded by a processor and executing a method for intelligently displaying tumor images of the above embodiment. The specific execution process can be found in the specific description of the above embodiment, which will not be repeated here.
[0138] Please refer to Figure 3 The application also discloses an electronic device. Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .
[0139] The communication bus 302 is used to realize the connection and communication between these components.
[0140] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.
[0141] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).
[0142] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.
[0143] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 The memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for an intelligent display method of tumor images.
[0144] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program of the intelligent display method of a tumor image film stored in the memory 305, and when executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.
[0145] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0146] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.
[0147] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0148] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0149] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.
[0150] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.
[0151] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.
Claims
1. An intelligent display method for tumor images. It is characterized in that include: Obtain multiple tumor images and patient-related information of the patient; Identifying metadata in each of the tumor image photos, the metadata including the identity of the subject and the time of shooting; Based on the shooting times, calculating the shooting time difference between the tumor image photos; Determine whether the identity of the photographed person is consistent with the identity information in the patient-related information, and whether each of the time differences is less than a time difference threshold; When the identity of the photographed person is consistent with the identity information in the patient-related information, and the time difference is less than the time difference threshold, determining that the authority verification result is passed; When the identity of the photographed person is inconsistent with the identity information in the patient-related information, or the time difference is not less than the time difference threshold, determining that the authority verification result is a failure; When the result of the authorization verification is passed, performing image preprocessing on each of the tumor image photos to obtain a standard tumor image photo; scanning the electronic mark on each of the tumor image photos to obtain feature data corresponding to each of the tumor image photos, and recording the feature data on the corresponding standard tumor image photo to obtain a feature map corresponding to each of the tumor image photos; Based on the patient-related information, the feature maps are feature-fused to obtain a target image photo, wherein the target image photo includes a plurality of tumor features and feature data corresponding to each of the tumor features; In response to a click operation of the patient, visually displaying the target image photo based on the click operation; The patient-related information also includes multimodal physiological data of the patient, and the method further includes: When the permission verification result is passed, the multimodal physiological data is time-synchronized with the target image photo to obtain a synchronized data set; In a three-dimensional coordinate system, the target image photo is mapped to the XY plane, and the time axis is mapped to the Z axis; Along the Z-axis direction, the multimodal physiological data is displayed in the form of curves of different colors; Generate an interactive data cube in the three-dimensional coordinate system, wherein the XY plane represents the spatial dimension, the Z axis represents the time dimension, and on the surface of the data cube, connect the key feature points of the target image photo with the physiological data nodes at the corresponding time points to form a feature-physiological association network diagram; In response to a user's click operation on the feature-physiology association network diagram, the feature-physiology association network diagram is visualized.
2. The method for intelligently displaying tumor images according to claim 1, It is characterized in that The obtaining of multiple tumor imaging photos and patient-related information of the patient includes: After obtaining the first identity information of the patient, generating a prompt message for second identity verification based on the first identity information; When the second identity authentication is successful, the patient-related information of the patient is retrieved, and multiple tumor images of the patient are scanned to obtain tumor image photos corresponding to each of the tumor images, and the tumor image films include at least one of the CT image films, MRI image films and PET image films.
3. The method for intelligently displaying tumor images according to claim 1, It is characterized in that Based on the patient-related information, the feature maps are subjected to feature fusion to obtain a target image photo, including: Determining a weight coefficient of each of the feature graphs based on the patient-related information; Perform weighted superposition on each of the feature maps according to the corresponding weight coefficients to obtain a fused feature map; Performing image registration on the fusion feature map and each of the standard tumor image photos to obtain a registered fusion feature map; The registered fusion feature map is superimposed on a preset human body model map to obtain the target image photo.
4. The method for intelligently displaying tumor images according to claim 1, It is characterized in that In response to the patient's click operation, visually displaying the target image photo based on the click operation includes: In response to a click operation by the patient, determining a request type corresponding to the click operation; If the request type is a local display request, determining a target area corresponding to the click operation; judging whether the target area includes a tumor feature; when the target area includes the tumor feature, generating a detailed information interface of the tumor feature based on feature data corresponding to the tumor feature, and superimposing and displaying the detailed information interface on the display interface of the target image photo, wherein the detailed information interface includes at least one of the size, shape, location, growth rate, malignancy and metabolic activity of the tumor; If the request type is an overall display request, a multi-dimensional tumor evolution visualization interface is generated for display based on the tumor features and corresponding feature data in the target image photo.
5. A system for implementing the intelligent display method of tumor images according to claim 1, It is characterized in that The system comprises: The permission verification module is used to obtain multiple tumor image photos of the patient and patient-related information, and perform permission verification based on the patient-related information and each of the tumor image photos to obtain a permission verification result; A feature map acquisition module, used for acquiring a feature map corresponding to each tumor image photo when the permission verification result is passed; A feature data acquisition module, configured to perform feature fusion on each of the feature maps based on the patient related information to obtain a target image photo, wherein the target image photo includes a plurality of tumor features and feature data corresponding to each of the tumor features; The visualization display module is used to respond to the patient's click operation and to perform visualization display on the target image photo based on the click operation.
6. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method according to any one of claims 1 to 4.
7. An electronic device, It is characterized in that It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-4.
