Tumor embolic agent dose evaluation method, evaluation device, equipment and storage medium

Abstract

The invention relates to a tumor embolic agent dose evaluation method and device, equipment and a storage medium. The method comprises the following steps: acquiring a multi-modal medical image of an interventional object; at least partial region of the interventional object contains a tumor, and the multi-modal medical image comprises tissue images for the tumor collected by at least two imaging modes; performing feature extraction processing on the multi-modal medical image to obtain image omics features and contrast perfusion features in the multi-modal medical image; a reference embolic agent dose required for performing tumor embolic agent interventional treatment on the tumor of the interventional subject is evaluated based on the image omics characteristics and the contrast perfusion characteristics. By adopting the method, the accuracy and feasibility of evaluating the dosage of the tumor embolism agent can be improved, and more reference information can be provided for subsequent medical research.

Description

Technical Field

[0001] The present application relates to the field of medical image technology, and in particular to a method for evaluating a tumor embolic agent dose, an apparatus for evaluating a tumor embolic agent dose, a computer device, a storage medium, and a computer program product. Background Art

[0002] With the continuous development of modern medical technology, tumor interventional embolization equipped with digital subtraction angiography (DSA) has been increasingly used.

[0003] In the prior art, tumor interventional embolization relies on the delivery of a specific dose of embolic agent into the interventional object. The specific dose of embolic agent mainly depends on the rich knowledge and experience of clinicians, and lacks accurate and effective auxiliary design schemes. Therefore, it is impossible to achieve accurate prediction of interventional data (i.e., the dose of embolic agent delivered to the interventional object). Summary of the invention

[0004] Based on this, it is necessary to provide a method for evaluating the dose of a tumor embolic agent, an apparatus for evaluating the dose of a tumor embolic agent, a computer device, a storage medium and a computer program product that can improve the accuracy of evaluating the dose of a tumor embolic agent in order to address the above technical problems.

[0005] In a first aspect, the present application provides a method for evaluating the dosage of a tumor embolic agent. The method comprises:

[0006] Acquire a multimodal medical image of an intervention object; wherein at least a partial area of ​​the intervention object includes a tumor, and the multimodal medical image includes a tissue image of the tumor acquired by at least two imaging methods;

[0007] Performing feature extraction processing on the multimodal medical image to obtain image omics features and contrast perfusion features in the multimodal medical image;

[0008] Based on the imageomics features and the contrast perfusion features, a reference embolic agent dose required for performing tumor embolic agent interventional treatment on the tumor of the intervention subject is evaluated.

[0009] In one embodiment, the acquiring of a multimodal medical image of the intervention object comprises the following two items:

[0010] Acquiring a magnetic resonance image of the intervention object based on magnetic resonance imaging, and using the magnetic resonance image as a first modality medical image of the intervention object;

[0011] A digital angiography image of the intervention object is acquired based on a digital angiography imaging method, and the digital angiography image is used as a second modality medical image of the intervention object.

[0012] In one embodiment, the performing feature extraction processing on the multimodal medical image to obtain the image omics features and contrast perfusion features in the multimodal medical image includes the following two items:

[0013] Performing feature extraction processing on the first modality medical image to obtain image omics features in the first modality medical image; the image omics features are used to express structural features of the tumor;

[0014] Performing feature extraction processing on the second modality medical image to obtain contrast perfusion features in the second modality medical image; the contrast perfusion features are used to express perfusion features of the tumor.

[0015] In one embodiment, performing feature extraction processing on the second modality medical image to obtain the contrast perfusion feature in the second modality medical image includes:

[0016] performing image recognition processing on the second modality medical image to determine a tumor region of the intervention object in the second modality medical image;

[0017] performing image segmentation processing on the second modality medical image to obtain a tumor region image;

[0018] performing data extraction processing on the tumor region image to determine a contrast agent perfusion curve in the tumor region image;

[0019] A key point recognition process is performed on the contrast agent perfusion curve to determine key perfusion parameters in the contrast agent perfusion curve, and the key perfusion parameters are used as contrast perfusion features in the second modality medical image.

[0020] In one embodiment, before evaluating the reference embolic agent dose required for performing tumor embolic agent interventional treatment on the tumor of the intervention subject, the method further includes the following two items:

[0021] Determining, among a plurality of groups of image omics features for the first modality medical image, a first correlation degree between each group of the image omics features and a preset standard embolic agent dose;

[0022] Based on the first correlation degree, determining a target imageomics feature for evaluating the reference embolic agent dose from among the multiple groups of imageomics features;

[0023] as well as

[0024] Determining, among a plurality of groups of contrast perfusion features of the second modality medical image, a second correlation degree between each group of the contrast perfusion features and the standard embolic agent dose;

[0025] Based on the second correlation degree, a target contrast perfusion feature for evaluating the reference embolic agent dose is determined from among the plurality of sets of contrast perfusion features.

[0026] In one embodiment, the reference embolic agent dose is a reference agent amount evaluated for performing the tumor embolic agent intervention treatment on the intervention object;

[0027] The step of evaluating the reference embolic agent dose required for performing tumor embolic agent intervention treatment on the tumor of the intervention subject comprises:

[0028] Based on a preset linear regression function, a multivariate regression process is performed on the target image omics feature and the target angiography perfusion feature to obtain a reference embolic agent dose.

[0029] In one embodiment, the method further comprises:

[0030] Acquiring a multimodal medical image of the intervention object;

[0031] Inputting the multimodal medical image into a pre-trained embolic agent evaluation model to obtain a reference embolic agent dose output by the embolic agent evaluation model;

[0032] The embolic agent evaluation model is used to sequentially perform feature extraction processing, feature screening processing and embolic agent evaluation processing on the multimodal medical image.

[0033] In a second aspect, the present application also provides a device for evaluating the dosage of a tumor embolic agent. The device comprises:

[0034] An image acquisition module, configured to acquire a multimodal medical image of an intervention object; at least a portion of the intervention object includes a tumor, and the multimodal medical image includes a tissue image of the tumor acquired by at least two imaging methods;

[0035] A feature extraction module, used for performing feature extraction processing on the multimodal medical image to obtain image omics features and contrast perfusion features in the multimodal medical image;

[0036] The embolic agent evaluation module is used to evaluate a reference embolic agent dose required for performing tumor embolic agent intervention treatment on the tumor of the intervention object based on the image omics feature and the contrast perfusion feature.

[0037] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0038] Acquire a multimodal medical image of an intervention object; wherein at least a partial area of ​​the intervention object includes a tumor, and the multimodal medical image includes a tissue image of the tumor acquired by at least two imaging methods;

[0039] Performing feature extraction processing on the multimodal medical image to obtain image omics features and contrast perfusion features in the multimodal medical image;

[0040] Based on the imageomics features and the contrast perfusion features, a reference embolic agent dose required for performing tumor embolic agent interventional treatment on the tumor of the intervention subject is evaluated.

[0041] In a fifth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0042] Acquire a multimodal medical image of an intervention object; wherein at least a partial area of ​​the intervention object includes a tumor, and the multimodal medical image includes a tissue image of the tumor acquired by at least two imaging methods;

[0043] Performing feature extraction processing on the multimodal medical image to obtain image omics features and contrast perfusion features in the multimodal medical image;

[0044] Based on the imageomics features and the contrast perfusion features, a reference embolic agent dose required for performing tumor embolic agent interventional treatment on the tumor of the intervention subject is evaluated.

[0045] In a sixth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0046] Acquire a multimodal medical image of an intervention object; wherein at least a partial area of ​​the intervention object includes a tumor, and the multimodal medical image includes a tissue image of the tumor acquired by at least two imaging methods;

[0047] Performing feature extraction processing on the multimodal medical image to obtain image omics features and contrast perfusion features in the multimodal medical image;

[0048] Based on the imageomics features and the contrast perfusion features, a reference embolic agent dose required for performing tumor embolic agent interventional treatment on the tumor of the intervention subject is evaluated.

[0049] The above-mentioned tumor embolic agent dose assessment method, device, computer equipment, storage medium and computer program product, on the one hand, firstly perform feature extraction processing on the multimodal medical image of the intervention object to obtain the image omics features and contrast perfusion features in the image, and then use the image omics features and contrast perfusion features to evaluate the tumor embolic agent intervention treatment on the tumor to obtain the corresponding required reference embolic agent dose, thereby optimizing the evaluation process for the tumor embolic agent dose, and compared with the method in the prior art, the efficiency of tumor embolic agent evaluation is effectively improved by a standardized execution procedure, and the consumption of manpower and material resources is reduced; on the other hand, by performing feature extraction processing on the multimodal medical images acquired by at least two imaging methods, the corresponding image omics features and contrast perfusion features are obtained, and the reference embolic agent dose is obtained by using the image omics features and contrast perfusion features, thereby improving the accuracy and feasibility of the evaluated reference embolic agent dose, and providing more reference information for subsequent medical research. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0051] Figure 1 This is a diagram showing an application environment of a method for evaluating a tumor embolization agent dose according to an exemplary embodiment.

[0052] Figure 2 The figure is a flow chart of a method for evaluating a dosage of a tumor embolic agent according to an exemplary embodiment.

[0053] Figure 3 The present invention is a flowchart showing the steps of obtaining contrast perfusion features in a medical image according to an exemplary embodiment.

[0054] Figure 4 The diagram is a simulated page diagram of a tumor region of an interventional object according to an exemplary embodiment.

[0055] Figure 5 is a schematic diagram of an image page of a tumor region of an interventional object according to an exemplary embodiment;

[0056] Figure 6 The figure is a page diagram showing a contrast agent perfusion curve according to an exemplary embodiment.

[0057] Figure 7 The figure is a flow chart of a method for evaluating a tumor embolic agent dose according to another exemplary embodiment.

[0058] Figure 8 The figure is a block diagram of a device for evaluating the dose of a tumor embolic agent according to an exemplary embodiment.

[0059] Fig. 9 The invention is a block diagram of a computer for evaluating the dose of a tumor embolic agent according to an exemplary embodiment.

[0060] Fig.10 is a block diagram of a computer-readable storage medium for tumor embolic agent dose assessment according to an exemplary embodiment.

[0061] Fig.11 is a block diagram of a computer program product for tumor embolic agent dose assessment according to an exemplary embodiment. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0063] The terms "first", "second", etc. are used many times in this application to describe various operations (or various elements or various applications or various instructions or various data), etc., but these operations (or elements or applications or instructions or data) should not be limited by these terms. These terms are only used to distinguish one operation (or element or application or instruction or data) from another operation (or element or application or instruction or data). For example, a first modality medical image can be called a first modality medical image, and a first modality medical image can also be called a first modality medical image. It's just that the scopes they cover are different, and they do not deviate from the scope of this application. Both the first modality medical image and the first modality medical image are image sets obtained by capturing the interventional object through a predetermined imaging method, but the two are not image sets captured by the same imaging method.

[0064] The method for evaluating the dosage of a tumor embolic agent provided in the present application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the server 104 via a communication network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on a cloud or a network server.

[0065] In some embodiments, reference Figure 1The server 104 first obtains a multimodal medical image of the intervention object; wherein at least a partial area of ​​the intervention object contains a tumor, and the multimodal medical image includes a tissue image of the tumor acquired by at least two imaging methods; then, the server 104 performs feature extraction processing on the multimodal medical image to obtain image omics features and contrast perfusion features in the multimodal medical image; finally, the server 104 evaluates a reference embolic agent dose required for tumor embolic agent interventional treatment of the tumor of the intervention object based on the image omics features and contrast perfusion features.

[0066] In some embodiments, the terminal 102 (such as a mobile terminal, a fixed terminal) can be implemented in various forms. The terminal 102 can be a mobile terminal including a mobile phone, a smart phone, a laptop, a portable handheld device, a personal digital assistant (PDA), a tablet computer (PAD), etc., which can evaluate the tumor embolic agent based on the image omics features and the contrast perfusion features. The terminal 102 can also be an automated teller machine (Automated Teller Machine, ATM), an automatic all-in-one machine, a digital TV, a desktop computer, a fixed computer, etc., which can evaluate the tumor embolic agent based on the image omics features and the contrast perfusion features.

[0067] In the following, it is assumed that the terminal 102 is a fixed terminal. However, it will be understood by those skilled in the art that the configuration according to the embodiments disclosed in the present application can also be applied to a mobile type terminal 102 if there are operations or elements specifically for mobile purposes.

[0068] In some embodiments, the data processing component running on the server 104 may load any of a variety of additional server applications and / or middle-tier applications being executed, such as HTTP (Hypertext Transfer Protocol), FTP (File Transfer Protocol), CGI (Common Gateway Interface), RDBMS (Relational Database Management System), etc.

[0069] In some embodiments, the server 104 may implement corresponding network functions through a deployed server (such as an independent server or a server cluster composed of multiple servers). The server 104 may also be suitable for running one or more application services or software components that provide the terminal 102 described in the above disclosure.

[0070] In some embodiments, the application service may include providing a service interface (such as an image data acquisition interface, an image data display interface, etc.) for multimodal medical images to users, as well as corresponding program services, etc. Among them, the software component may include, for example, an application program (SDK) or a client (APP) with a tumor embolic agent evaluation function.

[0071] In some embodiments, the application or client with the tumor embolic agent evaluation function provided by the server 104 includes a portal port that provides one-to-one application services to users in the foreground and multiple business systems that perform data processing in the background, so as to extend the application of the tumor embolic agent evaluation function to the APP or client, so that users can use and access the embolic agent evaluation function for image features at any time and any place.

[0072] In some embodiments, the tumor embolic agent evaluation function in the APP or client may be a computer program running in user mode to complete one or more specific tasks, which can interact with the user and has a visual user interface. The APP or client may include two parts: a graphical user interface (GUI) and an engine, which can provide a digital client system with multiple application services to the user in the form of a user interface.

[0073] In some embodiments, the user can input corresponding code data or control parameters to the APP or client through a preset input device or automatic control program to execute the application service of the computer program in the server 104 and display the application service in the user interface.

[0074] In some embodiments, the operating system running on the APP or client may include various versions of Microsoft Windows®, Apple Macintosh® and / or Linux operating systems, various commercial or UNIX®-like operating systems (including but not limited to various GNU / Linux operating systems, Google Chrome® OS, etc.) and / or mobile operating systems, such as iOS®, Windows® Phone, Android® OS, BlackBerry® OS, Palm® OS operating systems, and other online operating systems or offline operating systems, without specific limitations here.

[0075] In some embodiments, Figure 2 As shown, a method for evaluating the dose of a tumor embolic agent is provided, and the method is applied to Figure 1 Taking the server 104 in the example as an example, the method includes the following steps:

[0076] Step S11: Acquire a multimodal medical image of the intervention object.

[0077] The intervention object is a medical diagnosis and treatment object to be subjected to tumor embolization agent intervention treatment, and at least a part of the area of ​​the intervention object contains a tumor.

[0078] In some embodiments, the medical diagnosis and treatment object can be, for example, a human subject, an animal subject, etc.

[0079] In one embodiment, the multimodal medical image includes a tissue image of a tumor of the intervention object acquired by at least two imaging methods.

[0080] The at least two imaging methods may include, for example, Magnetic Resonance (MR), Digital Subtraction Angiography (DSA), Computed Tomography (CT), etc., for providing high-resolution, three-dimensionally reconstructed tissue images. Therefore, the acquired multimodal medical images may include, for example, MR images, DSA images, CT images, etc.

[0081] In some embodiments, the server acquires multimodal medical images of the interventional object including two types of images, as follows: first, magnetic resonance data of the interventional object is acquired based on a magnetic resonance imaging method, and then a magnetic resonance image is generated based on the magnetic resonance data, and finally the magnetic resonance image is used as a first modality medical image of the interventional object; and, digital angiography data of the interventional object is acquired based on a digital angiography imaging method, and then a digital angiography image is generated based on the digital angiography data, and finally the digital angiography image is used as a second modality medical image of the interventional object.

[0082] In some embodiments, the server may perform data preprocessing, resampling processing, algorithm reconstruction processing, and image post-processing on the collected object data in sequence to generate corresponding multimodal medical images.

[0083] Among them, data preprocessing is used to preprocess the acquired object data, including removing noise, correcting scanner non-uniformity, correcting gradient drift, etc. These preprocessing steps help improve image quality and accuracy.

[0084] Among them, resampling processing: Since the object data is collected from the object space, data resampling is required to convert it into the image space. This can perform an inverse Fourier transform on the spatial data to obtain the image space data.

[0085] Among them, algorithmic reconstruction processing: image spatial data is converted into the final multimodal medical image using an image reconstruction algorithm. Among them, image reconstruction algorithms may include fast Fourier transform (FFT), filtered back projection algorithm, iterative reconstruction algorithm, etc. These algorithms restore images through mathematical models and image processing techniques according to the characteristics of the object data and the sampling method.

[0086] Among them, image post-processing is used to post-process the reconstructed magnetic resonance images, including removing artifacts, enhancing contrast, smoothing images, etc. These post-processing steps help improve the visualization and diagnostic capabilities of the images.

[0087] Step S12: performing feature extraction processing on the multimodal medical image to obtain image omics features and contrast perfusion features in the multimodal medical image.

[0088] In one embodiment, the server obtains image omics features in a multimodal medical image, including: performing feature extraction processing on a first modality medical image to obtain image omics features in the first modality medical image.

[0089] Among them, image omics features are used to express the structural characteristics of the tumor of the intervention object.

[0090] In some embodiments, the server may perform feature extraction processing on the first modality medical image by means of statistical methods, geometric methods, texture analysis, etc., so as to extract certain quantitative features in the first modality medical image.

[0091] Among them, these quantitative features may include: shape features: including the size, shape, volume, surface area, longest diameter, shortest diameter, circumference, etc. of the tumor; intensity features: including the density, grayscale distribution, average density, standard deviation, maximum value, minimum value, histogram features, etc. of the tumor or tissue; texture features: including grayscale co-occurrence matrix (GLCM), grayscale difference matrix (GLDM), grayscale gradient co-occurrence matrix (GLGCM), grayscale co-occurrence matrix (GLRLM), etc., used to describe the grayscale changes and spatial relationships between pixels in the image; vascular features: including vascular diameter, vascular length, branching angle, blood flow velocity, etc., used to describe the morphology, branching, and hemodynamics of the blood vessels; spatial features: including the location, distance, relative position, etc. of the region, used to describe the spatial distribution and relationship of different regions in the image.

[0092] In another embodiment, the server obtains the contrast perfusion features in the multi-modality medical image, including: performing feature extraction processing on the second modality medical image to obtain the contrast perfusion features in the second modality medical image.

[0093] Among them, the contrast perfusion characteristics are used to express the perfusion characteristics of the tumor of the intervention object, that is, after a certain dose of contrast agent (such as gadolinium-europium, etc.) is perfused into the intervention object, the tumor area of ​​the intervention object has the characteristics of the contrast agent within a certain time range.

[0094] In some embodiments, the server may perform feature extraction processing on the second modality medical image by means of statistical methods, geometric methods, texture analysis, etc., so as to extract certain quantitative features in the second modality medical image.

[0095] Among them, these quantitative features may include: perfusion parameters in the lesion area (i.e., tumor area): including peak perfusion, time to peak, half-peak time, etc. calculated from the lesion area; they may also include analytical features obtained after quantitative analysis of perfusion parameters: such as calculating the area under the time-density curve (AUC), or calculating the perfusion value at a specific time point.

[0096] Step S13: Based on the image omics features and the contrast perfusion features, a reference embolic agent dose required for performing tumor embolic agent intervention treatment on the tumor of the intervention subject is evaluated.

[0097] The reference embolic agent dose is the reference agent quantity evaluated for performing tumor embolic agent interventional treatment on the interventional object, that is, medical workers can refer to the reference embolic agent dose to perform tumor embolic agent interventional treatment on the interventional object.

[0098] In one embodiment, the server evaluates the required reference embolic agent dose, including: performing multivariate regression processing on the target image omics features and the target angiographic perfusion features based on a preset linear regression function to obtain the reference embolic agent dose.

[0099] The linear regression function is obtained by training through a machine learning method or a regression algorithm, and is used to perform regression calculation on the input image features. The machine learning method includes methods such as support vector machine (SVM), random forest (Random Forest), artificial neural network (ANN), etc. The regression algorithm includes linear regression, ridge regression, support vector regression (SVR), etc., which are not specifically limited here.

[0100] In the above-mentioned evaluation process of the tumor embolization agent dose, the server first obtains a multimodal medical image of the intervention object; at least a partial area of ​​the intervention object contains a tumor, and the multimodal medical image includes a tissue image of the tumor acquired by at least two imaging methods; then the multimodal medical image is subjected to feature extraction processing to obtain image omics features and contrast perfusion features in the multimodal medical image; finally, based on the image omics features and contrast perfusion features, the reference embolic agent dose required for tumor embolization agent interventional treatment of the tumor of the intervention object is evaluated. In this way, on the one hand, feature extraction is first performed on the multimodal medical images of the interventional object to obtain image omics features and contrast perfusion features in the image, and then the image omics features and contrast perfusion features are used to evaluate the tumor embolic agent interventional treatment of the tumor to obtain the corresponding required reference embolic agent dose, thereby optimizing the evaluation process for the tumor embolic agent dose, and compared with the method in the prior art, the efficiency of tumor embolic agent evaluation is effectively improved with a standardized execution procedure, and the consumption of manpower and material resources is reduced; on the other hand, feature extraction is performed on the multimodal medical images acquired by at least two imaging methods to obtain the corresponding image omics features and contrast perfusion features, and the reference embolic agent dose is obtained by using the image omics features and contrast perfusion features, thereby improving the accuracy and feasibility of the evaluated reference embolic agent dose, and providing more reference information for subsequent medical research.

[0101] Those skilled in the art will appreciate that in the above methods of the specific embodiments, the disclosed methods can be implemented in more specific ways. For example, the above described implementation of the server evaluating the reference embolic agent dose required for the tumor embolic agent interventional treatment of the tumor of the intervention object based on the image omics features and the contrast perfusion features is only illustrative.

[0102] Exemplarily, the server performs feature extraction processing on the magnetic resonance image to obtain the image omics features in the magnetic resonance image, or performs feature extraction processing on the digital angiography image to obtain the contrast perfusion features in the digital angiography image, etc. This is merely a collection method, and there may be other division methods in actual implementation. For example, the contrast perfusion features in the digital angiography image and the image omics features in the magnetic resonance image can be combined or aggregated into another system, or some features can be ignored or not executed.

[0103] In an exemplary embodiment, see Figure 3 , Figure 3 The flowchart of an embodiment of obtaining the contrast perfusion feature in the medical image in the present application is shown in FIG. In step S12, the server performs feature extraction processing on the second modality medical image to obtain the contrast perfusion feature in the second modality medical image. Specifically, the following technical contents can be performed:

[0104] Step S121: performing image recognition processing on the second modality medical image to determine a tumor region of the interventional object in the second modality medical image.

[0105] Specifically, the server identifies grayscale information, color information, texture information, shape information, etc. of each pixel in the second modality medical image to determine a tumor region of the interventional object in the second modality medical image.

[0106] In an exemplary embodiment, see Figure 4 and Figure 5 , Figure 4 This is a schematic diagram of a simulated page of an embodiment of the present application regarding the tumor region of the intervention object. Figure 5 This is a schematic diagram of an image page of an embodiment of a tumor region of an interventional object in this application. Figure 4 The simulation page in the figure is a schematic page for simulating the tumor area. Figure 4 The server compares the grayscale information, color information, texture information, and shape information of the regions S1, S2, and S3 with the preset standard tumors to determine the image region that matches the standard tumor as the tumor region; and Figure 5 The image page in the figure is a digital angiography image page actually taken for the tumor area. Figure 5 The server determines that the "tumor region" matches a preset standard tumor based on the grayscale information, color information, texture information and shape information of the "tumor region".

[0107] Step S122: performing image segmentation processing on the second modality medical image to obtain a tumor region image.

[0108] In some embodiments, the server divides the second modality medical image into a number of non-overlapping areas according to different lesion areas, so that the image features in the same area show consistency or similarity, but show obvious differences between different areas.

[0109] In some embodiments, before performing image segmentation on the second modality medical image, the server may first perform edge enhancement on the second modality medical image to make the outlines of each region in the second modality medical image more prominent, or increase the contrast of the second modality medical image, thereby being able to more accurately segment the regional image.

[0110] In some embodiments, the server performs image segmentation processing on the second modality medical image, which may include: first performing edge detection on the tumor region image, and then weakening or completely removing the edge of the prominent image and the image area outside the edge based on the result of the edge detection; finally, the server performs binarization processing on the tumor region image to segment the tumor region image with edge enhancement.

[0111] Step S123: performing data extraction processing on the tumor region image to determine the contrast agent perfusion curve in the tumor region image.

[0112] In one embodiment, the server calculates the contrast agent perfusion curve by detecting the change of the concentration or intensity of the contrast agent in the tumor region over time. That is, after the contrast agent is administered to the interventional subject, the contrast agent concentration or intensity in the tumor region at a series of time points is measured and the concentration values ​​or intensity values ​​are associated with time to obtain the contrast agent perfusion curve.

[0113] Step S124: performing key point recognition processing on the contrast agent perfusion curve, determining key perfusion parameters in the contrast agent perfusion curve, and using the key perfusion parameters as contrast perfusion features in the second modality medical image.

[0114] Specifically, the server first identifies key feature points in the contrast agent perfusion curve, determines at least one key point, and then calculates key perfusion parameters corresponding to each key feature point.

[0115] In one embodiment, the key feature points are defined as follows: the contrast agent perfusion curve has two types of mutation points, one is the first type of mutation point where the curve changes from a relatively stable state to an ascending state, and the other is the second type of mutation point where the curve changes from an ascending state to a relatively stable state.

[0116] In one embodiment, the key perfusion parameters may include: the time from the first type mutation point to time 0, the time from the second type mutation point to time 0, and the time difference, intensity difference or slope between the first type mutation point and the second type mutation point.

[0117] In an exemplary embodiment, see Figure 6 , Figure 6 This is a page schematic diagram of an embodiment of a contrast agent perfusion curve in the present application. Curve P0 is the contrast agent perfusion curve, point P1 is the first type of mutation point in the contrast agent perfusion curve, and point P2 is the second type of mutation point in the contrast agent perfusion curve. Then, the server uses the first time from point P1 to time 0, the second time from point P2 to time 0, and the time difference, intensity difference and slope between point P1 and point P2 as key perfusion parameters in the contrast agent perfusion curve.

[0118] In one embodiment, before step S13, that is, after the server obtains the image omics features in the first modality medical image, it is also possible to determine a high-quality image omics feature from multiple groups of image omics features, so as to facilitate the high-quality image omics feature to evaluate the tumor embolization agent dose for the interventional object. Specifically, this can be achieved in the following ways:

[0119] Step 1: Determine, among a plurality of groups of image omics features for a first modality medical image, a first correlation degree between each group of image omics features and a preset standard embolic agent dose.

[0120] Specifically, the server uses each group of image omics features as candidate image omics features, and performs correlation analysis with a preset standard embolic agent dose, so as to obtain a first correlation degree between each group of candidate image omics features and the standard embolic agent dose.

[0121] The standard embolic agent dose is a standard dose predetermined by experienced medical professionals according to standard specifications.

[0122] In one embodiment, the purpose of performing association analysis on candidate image omics features is to select the most discriminative and predictive features from the candidate image omics features.

[0123] Specifically, the server can calculate the linear or nonlinear relationship between the image omics features and the standard embolic agent dose based on correlation coefficients (such as Pearson correlation coefficient, Spearman rank correlation coefficient), variance analysis, mutual information, linear regression, etc., to obtain the corresponding first correlation degree.

[0124] Among them, the degree of association is used to measure the correlation between the candidate image omics features and the standard embolic agent dose. Taking the Pearson correlation coefficient as an example, it is used to measure the strength and direction of the linear correlation between the two variables. Its value range is -1 to 1, and close to 1 indicates positive correlation, close to -1 indicates negative correlation, and close to 0 indicates no correlation.

[0125] Step 2: Based on the first correlation degree, a target image omics feature for evaluating a reference embolic agent dose is determined from among multiple groups of image omics features.

[0126] Specifically, the server first sorts the multiple groups of candidate radiomics features according to the first correlation degree of each group of candidate radiomics features; and then selects the candidate radiomics features with a preset number of correlations ranked first as the target radiomics features.

[0127] In another embodiment, before step S13, that is, after the server obtains the contrast perfusion feature in the second modality medical image, a high-quality contrast perfusion feature can be determined from multiple groups of contrast perfusion features, so as to facilitate the high-quality contrast perfusion feature to evaluate the tumor embolization agent dose for the intervention object. Specifically, this can be achieved in the following ways:

[0128] Step 1: determining a second correlation degree between each group of contrast perfusion features and a standard embolic agent dose among multiple groups of contrast perfusion features of a second modality medical image.

[0129] Specifically, the server uses each group of contrast perfusion features as candidate contrast perfusion features, and performs a correlation analysis with a preset standard embolic agent dose to obtain a second correlation degree between each group of candidate contrast perfusion features and the standard embolic agent dose.

[0130] In one embodiment, the purpose of performing correlation analysis on candidate contrast perfusion features is to select the most discriminative and predictive features from among the candidate contrast perfusion features.

[0131] Specifically, the server can calculate the linear or nonlinear relationship between the contrast perfusion characteristics and the standard embolic agent dose based on correlation coefficients (such as Pearson correlation coefficient, Spearman rank correlation coefficient), variance analysis, mutual information, linear regression, etc. to obtain the corresponding second correlation degree.

[0132] Among them, the degree of association is used to measure the correlation between the candidate contrast perfusion feature and the standard embolic agent dose. Taking the Spearman rank correlation coefficient as an example, it is used to measure the strength, direction and statistical significance of the linear correlation between the two variables. Its value range is -1 to 1, and a higher correlation coefficient indicates that the correlation between the feature and the standard dose is stronger, while a lower correlation coefficient indicates that the correlation between the two is weak or non-existent.

[0133] Step 2: Based on the second correlation degree, a target contrast perfusion feature for evaluating a reference embolic agent dose is determined from among the multiple groups of contrast perfusion features.

[0134] Specifically, the server first sorts the multiple groups of candidate contrast perfusion features according to the second correlation degree of each group of candidate contrast perfusion features; and then selects the candidate contrast perfusion features with a preset number of correlations as the target contrast perfusion features.

[0135] In one embodiment, the server extracts features from multimodal medical images to obtain image omics features and contrast perfusion features in the multimodal medical images; and based on the image omics features and contrast perfusion features, the process of evaluating the dose of tumor embolic agents for interventional objects can be integrated into a pre-trained embolic agent evaluation model for processing to improve the efficiency of data evaluation and reduce labor costs. Specifically, this can be achieved in the following ways:

[0136] Step 1: Acquire multimodal medical images of the interventional object.

[0137] The multimodal medical image includes a first modality medical image carrying image omics features and a second modality medical image carrying contrast perfusion features.

[0138] The first modality medical image may be the MR image or the computed tomography angiography (CTA) image in the above embodiment, and the second modality medical image may be the DSA image, the computed tomography perfusion (CTP) image, etc. in the above embodiment.

[0139] Step 2: Input the multimodal medical image into the pre-trained embolic agent evaluation model to obtain the reference embolic agent dose output by the embolic agent evaluation model.

[0140] The embolic agent evaluation model may be a pre-trained neural network model such as VGG, which is used to sequentially perform feature extraction processing, feature screening processing and embolic agent evaluation processing on the input multimodal medical image to output a reference embolic agent dose.

[0141] In order to more clearly illustrate the method for evaluating the dosage of a tumor embolic agent provided by the embodiment of the present disclosure, the method for evaluating the dosage of a tumor embolic agent is specifically described below with reference to a specific embodiment. Figure 7 , Figure 7 FIG. 1 is a flow chart of a method for evaluating a tumor embolic agent dosage according to another exemplary embodiment. The method for evaluating a tumor embolic agent dosage is used in the server 104 and specifically includes the following contents:

[0142] Step S21: Acquire an MR image of the patient.

[0143] Specifically, before performing surgery on a patient, a nuclear magnetic resonance examination is first performed on the patient to obtain an MR image of the patient.

[0144] In addition to the MR images, CTA images of the patient may also be acquired.

[0145] Among them, MR images or CTA images are three-dimensional images, which are used to express the three-dimensional anatomical structure and some soft tissue information in the patient's body.

[0146] Step S22: extracting multiple groups of candidate radiomics features from the MR image.

[0147] Among them, imaging omics features are used to reflect tumor tissue structure.

[0148] Step S23: traverse the correlation between each group of candidate radiomics features and the standard dose.

[0149] Among them, the standard dose is the amount of embolic agent used that is predetermined by experienced doctors according to standard specifications.

[0150] Step S24: determining a target radiomics feature from the candidate radiomics features.

[0151] The server first sorts the multiple groups of candidate radiomics features according to the relevance, and then selects the candidate radiomics features with a preset number of relevance rankings as the target radiomics features.

[0152] Step S25: Acquire the patient's DSA image.

[0153] Specifically, when a patient is undergoing surgery, a digital angiography test is performed on the patient to obtain a DSA image of the patient.

[0154] In addition to the DSA image, a CTP image of the patient may also be obtained.

[0155] Step S26: performing image recognition on the DSA image to determine the target area in the DSA image.

[0156] The target area is the tumor tissue area in the patient's body.

[0157] The process of image recognition includes feature recognition and image segmentation.

[0158] Step S27: Calculate the contrast agent perfusion curve based on the image in the target area.

[0159] Step S28: Identify a plurality of key feature points in the perfusion curve.

[0160] Among them, the definition of key characteristic points is: the curve has two types of mutation points, one is the first type of mutation point where the curve changes from a relatively stable state to an upward state, and the other is the second type of mutation point where the curve changes from an upward state to a relatively stable state.

[0161] Step S29: Calculate the key perfusion parameters corresponding to each key feature point.

[0162] Among them, the key perfusion parameters include: the time from the first type mutation point to time 0, the time from the second type mutation point to time 0, and the time difference, intensity difference or slope between the first type mutation point and the second type mutation point.

[0163] Step S30: traverse the correlation between each key perfusion parameter and the standard dose.

[0164] Step S31: determining a target key perfusion parameter from a plurality of key perfusion parameters.

[0165] The server first sorts the multiple key perfusion parameters according to the relevance, and then selects the key perfusion parameters with a preset number of relevances as the target key perfusion parameters.

[0166] Step S32: Perform multivariate regression processing on the target radiomics features and the target key perfusion parameters to obtain the predicted embolic agent dose.

[0167] Specifically, the server calculates the radiomics features and key perfusion parameters based on a preset linear regression function to derive the predicted embolic agent dose.

[0168] Step S33: displaying the predicted embolic agent dosage.

[0169] Specifically, the server sends the predicted embolic agent dosage to the doctor for display and medical reference.

[0170] In this way, on the one hand, feature extraction is first performed on the multimodal medical images of the interventional object to obtain image omics features and contrast perfusion features in the image, and then the image omics features and contrast perfusion features are used to evaluate the tumor embolic agent interventional treatment of the tumor to obtain the corresponding required reference embolic agent dose, thereby optimizing the evaluation process for the tumor embolic agent dose, and compared with the method in the prior art, the efficiency of tumor embolic agent evaluation is effectively improved with a standardized execution procedure, and the consumption of manpower and material resources is reduced; on the other hand, feature extraction is performed on the multimodal medical images acquired by at least two imaging methods to obtain the corresponding image omics features and contrast perfusion features, and the reference embolic agent dose is obtained by using the image omics features and contrast perfusion features, thereby improving the accuracy and feasibility of the evaluated reference embolic agent dose, and providing more reference information for subsequent medical research.

[0171] It should be understood that although Figure 2-Figure 7 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2-Figure 7At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0172] It can be understood that the same / similar parts between the various embodiments of the above method in this specification can refer to each other, and each embodiment focuses on the differences from other embodiments. For related points, please refer to the description of other method embodiments.

[0173] Figure 8 is a block diagram of a device for evaluating the dose of a tumor embolization agent provided in an embodiment of the present application. Figure 8 The tumor embolic agent dosage evaluation device 10 includes: an image acquisition module 11 , a feature extraction module 12 , and an embolic agent evaluation module 13 .

[0174] The image acquisition module 11 is used to acquire a multimodal medical image of an intervention object; at least a part of the area of ​​the intervention object includes a tumor, and the multimodal medical image includes a tissue image of the tumor acquired by at least two imaging methods;

[0175] The feature extraction module 12 is used to perform feature extraction processing on the multimodal medical image to obtain image omics features and contrast perfusion features in the multimodal medical image;

[0176] The embolic agent evaluation module 13 is used to evaluate the reference embolic agent dose required for performing tumor embolic agent intervention treatment on the tumor of the intervention subject based on the image omics features and the contrast perfusion features.

[0177] In some embodiments, in the aspect of acquiring a multimodal medical image of an interventional object, the apparatus 10 further includes the following two items:

[0178] Acquiring a magnetic resonance image of the intervention object based on magnetic resonance imaging, and using the magnetic resonance image as a first modality medical image of the intervention object;

[0179] A digital angiography image of the intervention object is acquired based on a digital angiography imaging method, and the digital angiography image is used as a second modality medical image of the intervention object.

[0180] In some embodiments, in performing feature extraction processing on the multimodal medical image to obtain image omics features and contrast perfusion features in the multimodal medical image, the apparatus 10 further includes:

[0181] Performing feature extraction processing on the first modality medical image to obtain image omics features in the first modality medical image; the image omics features are used to express structural features of the tumor;

[0182] The second modality medical image is subjected to feature extraction processing to obtain a contrast perfusion feature in the second modality medical image; the image omics feature is used to express the perfusion feature of the tumor.

[0183] In some embodiments, in the aspect of performing feature extraction processing on the second modality medical image to obtain the contrast perfusion feature in the second modality medical image, the apparatus 10 further includes:

[0184] performing image recognition processing on the second modality medical image to determine a tumor region of the intervention object in the second modality medical image;

[0185] performing image segmentation processing on the second modality medical image to obtain a tumor region image;

[0186] performing data extraction processing on the tumor region image to determine a contrast agent perfusion curve in the tumor region image;

[0187] A key point recognition process is performed on the contrast agent perfusion curve to determine key perfusion parameters in the contrast agent perfusion curve, and the key perfusion parameters are used as contrast perfusion features in the second modality medical image.

[0188] In some embodiments, before evaluating the reference embolic agent dose required for performing tumor embolic agent interventional treatment on the tumor of the intervention subject, the device 10 further includes:

[0189] Determining, among a plurality of groups of image omics features for the first modality medical image, a first correlation degree between each group of the image omics features and a preset standard embolic agent dose;

[0190] Based on the first correlation degree, determining a target imageomics feature for evaluating the reference embolic agent dose from among the multiple groups of imageomics features;

[0191] as well as

[0192] Determining, among a plurality of groups of contrast perfusion features of the second modality medical image, a second correlation degree between each group of the contrast perfusion features and the standard embolic agent dose;

[0193] Based on the second correlation degree, a target contrast perfusion feature for evaluating the reference embolic agent dose is determined from among the plurality of sets of contrast perfusion features.

[0194] In some embodiments, the reference embolic agent dose is a reference agent amount evaluated for performing the tumor embolic agent intervention treatment on the intervention object;

[0195] In the aspect of evaluating the reference embolic agent dose required for performing tumor embolic agent intervention treatment on the tumor of the intervention subject, the device 10 further includes:

[0196] Based on a preset linear regression function, a multivariate regression process is performed on the target image omics feature and the target angiography perfusion feature to obtain a reference embolic agent dose.

[0197] In some embodiments, the apparatus 10 further comprises:

[0198] Acquiring a multimodal medical image of the intervention object;

[0199] Inputting the multimodal medical image into a pre-trained embolic agent evaluation model to obtain a reference embolic agent dose output by the embolic agent evaluation model;

[0200] The embolic agent evaluation model is used to sequentially perform feature extraction processing, feature screening processing and embolic agent evaluation processing on the multimodal medical image.

[0201] Fig. 9 2 is a block diagram of a computer device 20 provided in an embodiment of the present application. For example, the computer device 20 may be an electronic device, an electronic component, or a server array, etc. Fig. 9 The computer device 20 includes a processor 21, which may be a processor set, which may include one or more processors, and the computer device 20 includes a memory resource represented by a memory 22, wherein the memory 22 stores a computer program, such as an application. The computer program stored in the memory 22 may include one or more modules, each corresponding to a set of executable instructions. In addition, the processing component 21 is configured to implement the above-mentioned method for evaluating the dose of a tumor embolic agent when executing the computer program.

[0202] In some embodiments, the computer device 20 is an electronic device in which a computing system can run one or more operating systems, including any operating system discussed above and any commercial server operating system. The computer device 20 can also run any of a variety of additional server applications and / or middle-tier applications, including HTTP (Hypertext Transfer Protocol) servers, FTP (File Transfer Protocol) servers, CGI (Common Gateway Interface) servers, super servers, database servers, etc. Exemplary database servers include, but are not limited to, database servers commercially available from (International Business Machines) and the like.

[0203] In some embodiments, the processing component 21 generally controls the overall operation of the computer device 20, such as operations associated with display, data processing, data communication, and recording operations. The processor 21 may include one or more processor components to execute a computer program to complete all or part of the steps of the above-mentioned method. In addition, the processor component may include one or more modules to facilitate the interaction between the processor component and other components. For example, the processor component may include a multimedia module to facilitate the use of the multimedia component to control the interaction between the user computer device 20 and the processor 21.

[0204] In some embodiments, the processor component in the processor 21 may also be referred to as a CPU (Central Processing Unit). The processor component may be an electronic chip having the ability to process signals. The processor may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor component, etc. In addition, the processor component may be implemented by an integrated circuit chip.

[0205] In some embodiments, the memory 22 is configured to store various types of data to support operations on the computer device 20. Examples of such data include instructions for any application or method operating on the computer device 20, collected data, messages, pictures, videos, etc. The memory 22 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, optical disk, or graphene memory.

[0206] In some embodiments, the memory 22 can be a memory stick, a TF card, etc., which can store all the information in the computer device 20, including the input raw data, computer programs, intermediate operation results and final operation results are all stored in the memory 22. In some embodiments, it stores and retrieves information according to the location specified by the processor. In some embodiments, only with the memory 22 can the computer device 20 have a memory function to ensure normal operation. In some embodiments, the memory 22 of the computer device 20 can be divided into main memory (internal memory) and auxiliary memory (external memory) according to its purpose, and there is also a classification method of dividing it into external memory and internal memory. External memory is usually a magnetic medium or an optical disk, etc., which can store information for a long time. Memory refers to the storage component on the motherboard, which is used to store the data and programs currently being executed, but is only used to temporarily store programs and data. If the power is turned off or the power is cut off, the data will be lost.

[0207] In some embodiments, the computer device 20 may further include: a power supply component 23 configured to perform power management of the computer device 20, a wired or wireless network interface 24 configured to connect the computer device 20 to a network, and an input / output (I / O) interface 25. The computer device 20 may operate based on an operating system stored in the memory 22, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, or the like.

[0208] In some embodiments, power supply assembly 23 provides power to various components of computer device 20. Power supply assembly 23 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to computer device 20.

[0209] In some embodiments, the wired or wireless network interface 24 is configured to facilitate wired or wireless communication between the computer device 20 and other devices. The computer device 20 can access a wireless network based on a communication standard, such as WiFi, a carrier network (such as 2G, 3G, 4G or 5G), or a combination thereof.

[0210] In some embodiments, the wired or wireless network interface 24 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the wired or wireless network interface 24 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0211] In some embodiments, the input / output (I / O) interface 25 provides an interface between the processor 21 and a peripheral interface module, which may be a keyboard, a click wheel, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0212] Fig.10 3 is a block diagram of a computer-readable storage medium 30 provided in an embodiment of the present application. The computer-readable storage medium 30 stores a computer program 31, wherein the computer program 31 implements the above-mentioned method for evaluating the dose of a tumor embolization agent when executed by a processor.

[0213] If the integrated units of the functional units in the various embodiments of the present application are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium 30. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the whole or part of the technical solution can be embodied in the form of a software product. The computer-readable storage medium 30 includes several instructions in a computer program 31 to enable a computer device (which can be a personal computer, a system server, or a network device, etc.), an electronic device (such as MP3, MP4, etc., or a smart terminal such as a mobile phone, a tablet computer, a wearable device, or a desktop computer, etc.) or a processor to execute all or part of the steps of the methods of various implementation methods of the present application.

[0214] Fig.11 4 is a block diagram of a computer program product 40 provided in an embodiment of the present application. The computer program product 40 includes program instructions 41, and the program instructions 41 can be executed by a processor of the server 20 to implement the above-mentioned method for evaluating the dose of a tumor embolic agent.

[0215] Those skilled in the art should understand that the embodiments of the present application may provide a method for evaluating a tumor embolic agent dose, an apparatus 10 for evaluating a tumor embolic agent dose, a computer device 20, a computer-readable storage medium 30, or a computer program product 40. Therefore, the present application may be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may be in the form of a computer program product 40 implemented on one or more computer program instructions 41 (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0216] The present application is described with reference to the flow chart and / or block diagram of the method for evaluating the dose of a tumor embolic agent, the device for evaluating the dose of a tumor embolic agent 10, the computer device 20, the computer-readable storage medium 30, or the computer program product 40 according to the embodiments of the present application. It should be understood that each process and / or block in the flow chart and / or block diagram, as well as the combination of the processes and / or blocks in the flow chart and / or block diagram, can be implemented by the computer program product 40. These computer program products 40 can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the program instructions 41 executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flow chart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0217] These computer program products 40 may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the program instructions 41 stored in the computer program product 40 produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0218] These program instructions 41 may also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the program instructions 41 executed on the computer or other programmable device for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0219] It should be noted that the above-mentioned various methods, devices, electronic devices, computer-readable storage media, computer program products, etc. may also include other implementation methods according to the description of the method embodiments. The specific implementation methods can refer to the description of the relevant method embodiments, and will not be described one by one here.

[0220] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

[0221] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for evaluating the dosage of a tumor embolic agent, characterized in that: The method comprises: Acquire a multimodal medical image of an intervention object; wherein at least a partial area of ​​the intervention object includes a tumor, and the multimodal medical image includes a tissue image of the tumor acquired by at least two imaging methods; Performing feature extraction processing on the multimodal medical image to obtain image omics features and contrast perfusion features in the multimodal medical image; Based on the imageomics features and the contrast perfusion features, a reference embolic agent dose required for performing tumor embolic agent interventional treatment on the tumor of the intervention subject is evaluated.

2. The method according to claim 1, characterized in that: The acquiring of the multimodal medical image of the intervention object includes the following two items: Acquiring a magnetic resonance image of the intervention object based on magnetic resonance imaging, and using the magnetic resonance image as a first modality medical image of the intervention object; A digital angiography image of the intervention object is acquired based on a digital angiography imaging method, and the digital angiography image is used as a second modality medical image of the intervention object.

3. The method according to claim 2, characterized in that The multimodal medical image is subjected to feature extraction processing to obtain image omics features and contrast perfusion features in the multimodal medical image. Includes the following two items: Performing feature extraction processing on the first modality medical image to obtain image omics features in the first modality medical image; the image omics features are used to express structural features of the tumor; Performing feature extraction processing on the second modality medical image to obtain contrast perfusion features in the second modality medical image; the contrast perfusion features are used to express perfusion features of the tumor.

4. The method according to claim 3, characterized in that The performing feature extraction processing on the second modality medical image to obtain the contrast perfusion feature in the second modality medical image includes: performing image recognition processing on the second modality medical image to determine a tumor region of the intervention object in the second modality medical image; performing image segmentation processing on the second modality medical image to obtain a tumor region image; performing data extraction processing on the tumor region image to determine a contrast agent perfusion curve in the tumor region image; A key point recognition process is performed on the contrast agent perfusion curve to determine key perfusion parameters in the contrast agent perfusion curve, and the key perfusion parameters are used as contrast perfusion features in the second modality medical image.

5. The method according to claim 4, characterized in that Before evaluating the reference embolic agent dose required for performing tumor embolic agent interventional treatment on the tumor of the intervention subject, the following two items are also included: Determining, among a plurality of groups of image omics features for the first modality medical image, a first correlation degree between each group of the image omics features and a preset standard embolic agent dose; Based on the first correlation degree, determining a target imageomics feature for evaluating the reference embolic agent dose from among the multiple groups of imageomics features; as well as Determining, among a plurality of groups of contrast perfusion features of the second modality medical image, a second correlation degree between each group of the contrast perfusion features and the standard embolic agent dose; Based on the second correlation degree, a target contrast perfusion feature for evaluating the reference embolic agent dose is determined from among the plurality of sets of contrast perfusion features.

6. The method according to claim 5, characterized in that The reference embolic agent dose is a reference agent quantity evaluated for performing the tumor embolic agent intervention treatment on the intervention object; The step of evaluating the reference embolic agent dose required for performing tumor embolic agent intervention treatment on the tumor of the intervention subject comprises: Based on a preset linear regression function, a multivariate regression process is performed on the target image omics feature and the target angiography perfusion feature to obtain a reference embolic agent dose.

7. The method according to claim 1, characterized in that The method further comprises: Acquiring a multimodal medical image of the intervention object; Inputting the multimodal medical image into a pre-trained embolic agent evaluation model to obtain a reference embolic agent dose output by the embolic agent evaluation model; The embolic agent evaluation model is used to sequentially perform feature extraction processing, feature screening processing and embolic agent evaluation processing on the multimodal medical image.

8. A device for evaluating the dosage of a tumor embolic agent, characterized in that: The device comprises: An image acquisition module, configured to acquire a multimodal medical image of an intervention object; at least a portion of the intervention object includes a tumor, and the multimodal medical image includes a tissue image of the tumor acquired by at least two imaging methods; A feature extraction module, used for performing feature extraction processing on the multimodal medical image to obtain image omics features and contrast perfusion features in the multimodal medical image; The embolic agent evaluation module is used to evaluate a reference embolic agent dose required for performing tumor embolic agent intervention treatment on the tumor of the intervention object based on the image omics feature and the contrast perfusion feature.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images