Method and apparatus for generating quantitative physiological parameter map on the basis of magnetic resonance

Generating an adversarial network through deep learning models, the problems of cumbersome operation and low accuracy in the generation of quantitative physiological parameter graphs of magnetic resonance are solved, and efficient and accurate quantitative physiological parameter graphs are achieved, reducing the hemodynamic model and artificial parameters. The dependence of the , improves the computing efficiency.

WO2024243733A1PCT designated stage expired Publication Date: 2024-12-05SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI

Patent Information

Application Number
PCT/CN2023/096606
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-26
Publication Date
2024-12-05

AI Technical Summary

Technical Problem

The prior art is cumbersome and has low accuracy when generating magnetic resonance quantitative physiological parameter diagrams, especially since the accuracy and reliability of the arterial input function depend on the time resolution and sampling rate of the collected data, and traditional methods require a large amount of computing resources and time.

Method used

Deep learning models, especially generative adversarial networks, trained by obtaining DCE-MRI images and quantitative physiological parameter maps, and generate accurate quantitative physiological parameter maps using the generative network and dual discriminator network to reduce the preset hemodynamic model. and the dependence of manual parameters to improve computing efficiency.

Benefits of technology

Reduces manual intervention, improves the accuracy and generation efficiency of quantitative physiological parameter maps, and can generate accurate Ktrans parameter maps based on a small number of DCE-MRI images, reduces the requirements for images to be processed, reduces the workload and computational complexity. .

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2023096606_05122024_PF_FP_ABST
    Figure CN2023096606_05122024_PF_FP_ABST
Patent Text Reader

Abstract

Provided are a method and apparatus for generating a quantitative physiological parameter map on the basis of magnetic resonance. The method comprises: acquiring each group of DCE-MRI images and a quantitative physiological parameter map corresponding to each group of DCE-MRI images; using each group of DCE-MRI images and the quantitative physiological parameter map as training inputs to train a deep learning model until the loss function value of the deep learning model meets a preset requirement, wherein the deep learning model is a generative adversarial network comprising a generation network and a discrimination network, the generation network is used for generating an output image, and the discrimination network comprises a global discriminator and a local discriminator; and using the deep learning model, of which the loss function value meets the preset requirement, as a quantitative physiological parameter map generation model, and processing a DCE-MRI image to be processed to obtain a quantitative physiological parameter map. The generation efficiency and accuracy of quantitative physiological parameter maps can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

A method and device for generating a magnetic resonance quantitative physiological parameter map Technical Field

[0001] The embodiments of this specification relate to the field of imaging technology, and in particular to a method and device for generating a magnetic resonance quantitative physiological parameter map. Background Art

[0002] Quantitative physiological parameters are numerical parameters used to assess the physiological function and metabolic state within tissues. They can help doctors diagnose and monitor diseases such as tumors and stroke. In medical imaging, quantitative physiological parameters are digital data obtained through imaging techniques that reflect physiological conditions within tissues, such as blood flow, blood oxygenation, and metabolism. These parameters are typically calculated from imaging data such as computed tomography (CT), magnetic resonance imaging (MRI), ultrasound (US), and positron emission tomography (PET). Therefore, different model assumptions and algorithms can lead to different results in the generated parameter maps. The arterial input function (AIF) is a key parameter in the calculation of quantitative physiological parameters. The accuracy and reliability of the AIF often depend on the temporal resolution and sampling rate of the acquired data. However, due to the difficulty in estimating the AIF for each patient, the population average AIF is often used for PK analysis, an approach that has certain limitations and errors. Furthermore, traditional quantitative physiological parameter generation requires significant computational resources and time.

[0003] In view of this, the embodiments of this specification aim to provide a method for generating a magnetic resonance quantitative physiological parameter map.

[0004] Summary of the Invention

[0005] In view of the above problems in the prior art, the purpose of the embodiments of this specification is to provide a method for generating a magnetic resonance quantitative physiological parameter map to solve the problems of cumbersome operation and low accuracy in the prior art when generating a quantitative physiological parameter map.

[0006] In order to solve the above technical problems, the specific technical solutions of the embodiments of this specification are as follows:

[0007] In a first aspect, an embodiment of this specification provides a method for generating a magnetic resonance quantitative physiological parameter map, comprising:

[0008] Acquiring each group of DCE-MRI images and a quantitative physiological parameter map corresponding to each group of DCE-MRI images;

[0009] Using the groups of DCE-MRI images and the quantitative physiological parameter maps as training inputs, the deep learning model is trained until the loss function value of the deep learning model meets preset requirements, the deep learning model is a generative adversarial network, the generative adversarial network includes a generative network and a discriminative network, the generative network is used to generate an output image, the discriminative network includes a global discriminator and a local discriminator, the global discriminator is used to discriminate the similarity between the output image and the quantitative physiological parameter map, and the local discriminator is used to discriminate the similarity between a local region of interest of the output image and a corresponding local region of interest in the quantitative physiological parameter map;

[0010] The deep learning model when the loss function value meets the preset requirements is used as a quantitative physiological parameter map generation model, and the DCE-MRI image to be processed is processed to obtain a quantitative physiological parameter map.

[0011] Specifically, the loss function is: LOSS=loss_G+loss_D;

[0012] Where LOSS is the loss value of the deep learning model, loss_G is the loss value of the generator network, and loss_D is the loss value of the discriminator network; loss_D = loss_D1*α+loss_D2*(1-α) ;

[0013] Among them, loss_D1 is the loss value of the global discriminator, loss_D2 is the loss value of the local discriminator, and α is a constant coefficient greater than 0 and less than 1.

[0014] Furthermore, the generative network is a generative network with group normalization added, and the discriminative network is a discriminative network with spectral normalization added.

[0015] Furthermore, quantitative physiological parameter maps corresponding to each set of DCE-MRI images are obtained, including:

[0016] Extract the time-signal curve of any pixel point in the same set of DCE-MRI images;

[0017] Establishing a curve of the contrast agent concentration change over time at corresponding pixel points in the set of DCE-MRI images;

[0018] Fitting the time-signal curve and the change curve to obtain Ktrans values ​​of corresponding pixel points in the set of DCE-MRI images;

[0019] Repeat the above process to obtain the Ktrans values ​​of all pixels in the same set of DCE-MRI images;

[0020] Based on the Ktrans values ​​of all pixels, the Ktrans quantitative physiological parameter map corresponding to the set of DCE-MRI images is obtained.

[0021] Furthermore, before obtaining the quantitative physiological parameter maps corresponding to each set of DCE-MRI images, the method further includes:

[0022] Perform alignment and / or registration processing on each set of DCE-MRI images.

[0023] Specifically, each set of DCE-MRI images is aligned, including:

[0024] selecting any one of the set of DCE-MRI images as a reference image, and obtaining deviation information between other images in the set of DCE-MRI images and the reference image;

[0025] Other images are aligned with the reference image according to the deviation information.

[0026] Specifically, each set of DCE-MRI images is registered, including:

[0027] selecting any one of the set of DCE-MRI images as a reference image, and extracting the same feature points and / or the same feature regions of the reference image and other images in the set of DCE-MRI images;

[0028] Determining a similarity transformation model between other images and the reference image based on the same feature point and / or the same area;

[0029] The other images are registered with the reference image according to the determined similarity change model.

[0030] In a second aspect, the embodiments of this specification further provide a device for generating a magnetic resonance quantitative physiological parameter map, comprising:

[0031] an acquisition module, configured to acquire each group of DCE-MRI images and a quantitative physiological parameter map corresponding to each DCE-MRI image;

[0032] a training module, configured to use the groups of DCE-MRI images and the quantitative physiological parameter maps as training inputs to train a deep learning model until a loss function value of the deep learning model meets preset requirements, wherein the deep learning model is a generative adversarial network, the generative adversarial network including a generative network and a discriminative network, the generative network being configured to generate an output image, the discriminative network including a global discriminator and a local discriminator, the global discriminator being configured to determine the similarity between the output image and the quantitative physiological parameter map, and the local discriminator being configured to determine the similarity between a local region of interest of the output image and a corresponding local region of interest in the quantitative physiological parameter map;

[0033] The processing module is used to use the deep learning model when the loss function value meets the preset requirements as a quantitative physiological parameter map generation model, and process the DCE-MRI image to be processed to obtain a quantitative physiological parameter map.

[0034] In a third aspect, an embodiment of this specification also provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method provided by the above technical solution when executing the computer program.

[0035] In a fourth aspect, an embodiment of this specification further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method provided by the above technical solution is implemented.

[0036] By adopting the above-mentioned technical solution, the magnetic resonance quantitative physiological parameter map generation method provided in the embodiments of this specification can learn and identify complex features and patterns from a large amount of training data during the model training stage. There is no need to model based on a preset hemodynamic model, nor is there a need to manually select multiple parameters to calculate parameters. This avoids dependence on assumptions such as vascular continuity and fluid incompressibility, reduces the degree of manual intervention, and is conducive to improving the accuracy of the calculation results.

[0037] During the model usage phase, the requirements for the DCE-MRI images to be processed can be reduced. For a single DCE-MRI image or a small number of DCE-MRI images, a relatively accurate Ktrans quantitative physiological parameter map can be generated; and the efficiency of generating quantitative physiological parameter maps can be greatly improved.

[0038] In order to make the above and other purposes, features and advantages of the embodiments of this specification more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of this article or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of this article. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] FIG1 is a schematic diagram showing the steps of a method for generating a magnetic resonance quantitative physiological parameter map provided in an embodiment of this specification;

[0041] FIG2 shows a comparison diagram of a quantitative physiological parameter map obtained by using the magnetic resonance quantitative physiological parameter map generation method provided in an embodiment of this specification and a quantitative physiological parameter map obtained by using a traditional method;

[0042] FIG3 is a schematic diagram of the steps for obtaining quantitative physiological parameter maps corresponding to each set of DCE-MRI images;

[0043] FIG4 is a schematic diagram showing the steps of aligning each set of DCE-MRI images;

[0044] FIG5 is a schematic diagram showing the steps of performing registration processing on each set of DCE-MRI images;

[0045] FIG6 shows a schematic structural diagram of a magnetic resonance quantitative physiological parameter image generating device provided in an embodiment of this specification;

[0046] FIG7 shows a schematic structural diagram of a computer device provided in an embodiment of this specification.

[0047] Description of the accompanying symbols:

[0048] 61. Get module;

[0049] 62. Training module;

[0050] 63. Processing module;

[0051] 702. Computer equipment;

[0052] 704, processor;

[0053] 706. Memory;

[0054] 708, driving mechanism;

[0055] 710, input / output module;

[0056] 712. Input devices;

[0057] 714. Output device;

[0058] 716. Presentation equipment;

[0059] 718. Graphical User Interface;

[0060] 720, network interface;

[0061] 722, communication link;

[0062] 724. Communication bus. DETAILED DESCRIPTION

[0063] The following will be combined with the accompanying drawings to clearly and completely describe the technical solutions in the embodiments of this document. Obviously, the embodiments described are only part of the embodiments of this document, not all of the embodiments. Based on the embodiments of this document, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this document.

[0064] It should be noted that the terms "first," "second," and the like in the specification and claims herein and in the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or device comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0065] The embodiments of this specification provide a method for generating a magnetic resonance quantitative physiological parameter map, which can reduce manual intervention, reduce errors, and improve processing efficiency. Figure 1 is a schematic diagram of the steps of a method for generating a magnetic resonance quantitative physiological parameter map provided by an embodiment of this specification. This specification provides method operation steps as described in the embodiment or flow chart, but based on conventional or non-creative labor, more or fewer operation steps may be included. The order of steps listed in the embodiment is only one way of executing the steps among many, and does not represent the only execution order. When the system or device product is executed in practice, it can be executed in sequence or in parallel according to the method shown in the embodiment or the accompanying drawings. Specifically, as shown in Figure 1, the method may include:

[0066] S110: Acquire each group of DCE-MRI images and a quantitative physiological parameter map corresponding to each group of DCE-MRI images.

[0067] For example, a set of DCE-MRI images in the embodiments of this specification can be multiple (for example, 45) image acquisitions of the same tissue (for example, breast) of the same object at certain intervals. Before acquisition, a contrast agent (also called a contrast agent) needs to be injected, and the accumulation of the contrast agent in the tissue is observed through image acquisition (the inflow and outflow of the contrast agent is a dynamic process, from no contrast agent at the beginning to the amount of contrast agent diffused (flowed) into the tissue reaching a peak, and then slowly dissipated (flowed out) from the tissue). Repeat the above operation to obtain different sets of DCE-MRI images of different objects and different tissues.

[0068] S120: Using each group of DCE-MRI images and the quantitative physiological parameter map as training inputs, the deep learning model is trained until the loss function value of the deep learning model meets the preset requirements, the deep learning model is a generative adversarial network, the generative adversarial network includes a generative network and a discriminative network, the generative network is used to generate an output image, the discriminative network includes a global discriminator and a local discriminator, the global discriminator is used to discriminate the similarity between the output image and the quantitative physiological parameter map, and the local discriminator is used to discriminate the similarity between the local region of interest of the output image and the corresponding local region of interest in the quantitative physiological parameter map.

[0069] The generating network can be resnet, unet and unet++.

[0070] In the embodiment of this specification, the generation network is preferably unet.

[0071] The discriminator network is PatchGAN; the batch size is set to 4; the total number of training time periods is set to 200 epochs: the learning rate is set to 0.0002 for the first 100 time periods, and the learning rate gradually decreases to 0 for the remaining 100 time periods.

[0072] In the embodiments of this specification, the number of local regions of interest (ROIs) in a set of DCE-MRI images can be set to one or more according to actual needs, and the size of the local regions of interest can be set according to actual needs. Generally, a tumor area or a suspected tumor area in a DCE-MRI image can be selected as a local region of interest. Furthermore, the deep learning model is a generative adversarial network (GAN), which uses a dual discriminator network, namely a global discriminator and a local discriminator, which can improve the accuracy of the judgment of the generation effect of the output image, and is conducive to improving the quality of the quantitative physiological parameter map obtained by the subsequent trained quantitative physiological parameter map generation model.

[0073] S130: Using the deep learning model when the loss function value meets the preset requirements as a quantitative physiological parameter map generation model, and processing the DCE-MRI image to be processed to obtain a quantitative physiological parameter map.

[0074] As shown in Figure 2, Figure 2 (a) is a DCE-MRI image to be processed; Figure 2 (b) is a quantitative physiological parameter map obtained by using the magnetic resonance quantitative physiological parameter map generation method provided in the embodiment of this specification; Figure 2 (c) is a quantitative physiological parameter map obtained by using the traditional method. Comparing Figure 2 (b) and Figure 2 (c), it can be seen that the traditional quantitative physiological parameter map generation method is easily interfered by noise (motion artifacts). The quantitative physiological parameter map generation method provided in the embodiment of this specification adopts a deep learning model, and the deep learning model can learn from a large amount of data, and identify and eliminate useless information (such as noise) in the learning process. The quantitative physiological parameter map generation model finally obtained by iterative optimization can remove the interference of noise and improve the generation quality of the quantitative physiological parameter map.

[0075] Moreover, after the training of the quantitative physiological parameter map generation model is completed, the requirements for processing DCE-MRI images can be reduced to a certain extent. For example, the number of DCE-MRI images can be reduced (that is, the corresponding quantitative physiological parameter maps can be generated based on less than 45 images), which reduces the workload.

[0076] The magnetic resonance quantitative physiological parameter map generation method provided in the embodiments of this specification obtains a trained quantitative physiological parameter map generation model through a generation network and a dual discriminator network, and uses it to generate quantitative physiological parameter maps. This can reduce errors caused by manual participation and improve the accuracy of the generated quantitative physiological parameter maps. At the same time, there is no need to perform a large amount of DCE-MRI image acquisition work, modeling work based on hemodynamic models, etc., which greatly reduces the workload and improves the efficiency of quantitative physiological parameter map generation.

[0077] It should be noted that the quantitative physiological parameter map generation method provided in the embodiments of this specification is to generate corresponding quantitative physiological parameter images for the DCE-MRI images to be processed. In some other feasible embodiments, imaging data such as computed tomography, ultrasound imaging, and positron emission tomography can also be processed to generate quantitative physiological parameter maps.

[0078] Furthermore, in the embodiment of this specification, the loss function is: LOSS=loss_G+loss_D;

[0079] Where LOSS is the loss of the deep learning model, loss_G is the loss of the generator network, and loss_D is the loss of the discriminator network. The generator loss and the discriminator loss are independent of each other but constrained by each other.

[0080] Specifically, loss_D=loss_D1*α+loss_D2*(1-α) ;

[0081] Among them, loss_D1 is the loss value of the global discriminator, loss_D2 is the loss value of the local discriminator, and α is a constant coefficient greater than 0 and less than 1.

[0082] In some optional embodiments, the value of α is 0.5, that is, the global discriminator and the local discriminator have the same weight.

[0083] It should be noted that when training the deep learning model in the embodiments of this specification, a separate alternating iterative training method is used. That is, the generative network is trained first. During this process, the parameters of the discriminant network remain unchanged, so that the output image generated by the generative network is as similar as possible to the quantitative physiological parameter map in the training data, and the local region of interest of the output image is as similar as possible to the local region of interest corresponding to the quantitative physiological parameter map. After multiple iterative trainings, the parameters of the generative network are fixed, and the discriminant network is trained to make the discriminant network's judgment results on the similarity between the output image and the quantitative physiological parameter map, and the judgment results on the similarity between the local region of interest of the output image and the local region of interest corresponding to the quantitative physiological parameter map more accurate. Finally, the generative network and the discriminant network are trained alternately until the training is completed.

[0084] Furthermore, in the embodiment of this specification, the generative network is a generative network with group normalization added, and the discriminative network is a discriminative network with spectral normalization added.

[0085] The generative network consists of convolutional layers, normalization layers, and activation layers. The normalization layer is a group normalization (GN) layer, which performs group normalization on the input DCE-MRI images. During training, group normalization divides each channel into several groups and calculates the mean and standard deviation of the feature maps within each group for each input data point. This ensures that the feature maps of each group have the same statistical characteristics, thereby reducing covariate shift in the features within the group, accelerating training and improving model performance.

[0086] Similarly, the global discriminator and local discriminator of the discriminant network include a convolution layer, a normalization layer, and an activation layer, wherein the normalization layer is a spectral normalization (SN) layer. In the embodiment of this specification, the spectral normalization method is as follows:

[0087] For the weight matrix W of each layer of the discriminator, calculate its left singular vector and right singular vector, u and v respectively; through singular value decomposition, the spectral norm of the weight matrix is ​​obtained as: ||W||=max|u T Wv||;

[0088] Among them, u T is the transpose of u.

[0089] Finally, the weight matrix W is normalized by dividing it by the largest singular value.

[0090] In addition to the above singular value method, for each weight matrix W, the upper bound sigma of its spectral norm can also be solved by the power iteration algorithm. The specific steps are:

[0091] The transpose matrix W of the weight matrix W T Repeatedly multiplying a random vector x and then normalizing it to get a new vector y until the difference between y and the vector of the previous iteration is less than a threshold. Finally, the value of sigma is set to the inner product of y and x when the power iteration converges.

[0092] Finally, the weight matrix W is divided by sigma for normalization.

[0093] The magnetic resonance quantitative physiological parameter map generation method of the embodiment of this specification improves the computational efficiency of the model and enhances the scalability and robustness of the model by adding a group-normalized generative network; and limits the singular values ​​of the weight matrix by adding a spectral-normalized discriminant network to avoid the vanishing or exploding gradient of the weights, thereby improving the stability and generalization ability of the model, and ultimately helping to improve the quality of the quantitative physiological parameter map generated by the quantitative physiological parameter map generation model.

[0094] As shown in FIG3 , step S110 of obtaining a quantitative physiological parameter map corresponding to each set of DCE-MRI images further includes:

[0095] S310: Extracting a time-signal curve of any pixel point in the same set of DCE-MRI images.

[0096] Optionally, before extracting the time-signal curve, the DCE-MRI image may be preprocessed such as baseline correction and denoising.

[0097] S320: Establish a curve of the change of the contrast agent concentration over time at the corresponding pixel points in the set of DCE-MRI images.

[0098] Specifically, the relationship between the contrast agent concentration in tissue and time can be established based on the single-compartment pharmacokinetic model: C(t) = Ktrans∫[AIF(t')-C(t')]dt'

[0099] Where C(t) is the contrast agent concentration at a pixel at time t, Ktrans is the transfer constant in the tissue, AIF(t') is the AIF curve value at time t', C(t') is the contrast agent concentration at a pixel at time t', and AIF is the arterial input function (AIF). In the embodiments of this specification, a large blood vessel in the tissue is preferably used as the AIF, or a pre-measured average AIF curve (based on population-based AIF) is used.

[0100] S330: Fitting the time-signal curve and the change curve to obtain Ktrans values ​​of corresponding pixel points in the set of DCE-MRI images.

[0101] Specifically, a method such as a nonlinear least squares (NLS) method or a linear least squares (LLS) method may be used to fit the time-signal curve and the change curve of each pixel point.

[0102] S340: Repeat the above process to obtain the Ktrans values ​​of all pixels in the same set of DCE-MRI images.

[0103] S350: Obtain a Ktrans quantitative physiological parameter map corresponding to the set of DCE-MRI images based on the Ktrans values ​​of all pixels.

[0104] Ktrans represents the rate at which the contrast agent flows from the blood vessels into the interstitial tissue, which is a comprehensive expression of perfusion and penetration. It can be understood as the transfer (rate) constant of the contrast agent flowing from the blood vessels into the interstitial tissue, which can be used to display the vascular permeability of different areas in the tissue, and can provide technical support for subsequent data analysis, tumor diagnosis and treatment, etc. It should be noted that in the embodiment of this specification, the quantitative physiological parameter map used as the training data for the deep learning model is the Ktrans quantitative physiological parameter map. In some other feasible embodiments, the quantitative physiological parameter map used as the training data for the deep learning model can also be the Kep quantitative physiological parameter map (Kep is the rate at which the contrast agent flows out of the tissue from the interstitial tissue), the ve quantitative physiological parameter map (ve is the proportion of the interstitial tissue), etc. After the model training is completed, the processed quantitative physiological parameter map is adapted to the training data.

[0105] Preferably, in the embodiment of this specification, before obtaining the quantitative physiological parameter map corresponding to each group of DCE-MRI images in step S110, the method further includes:

[0106] Perform alignment and / or registration processing on each set of DCE-MRI images.

[0107] As shown in FIG4 , the alignment process of each set of DCE-MRI images may include the following steps:

[0108] S410: Select any one of the set of DCE-MRI images as a reference image, and obtain deviation information between other images in the set of DCE-MRI images and the reference image.

[0109] S420: Align other images with the reference image according to the deviation information.

[0110] For example, based on the deviation information, other images can be aligned with the reference image through transformation operations such as translation, rotation, or scaling. During DCE-MRI image acquisition, the subject may move, or the position of the image acquisition point may change due to factors such as breathing, resulting in inaccurate input data or inability to analyze. In the embodiments of this specification, alignment of each set of DCE-MRI images can improve data accuracy and reliability.

[0111] As shown in FIG5 , each set of DCE-MRI images is subjected to registration processing, including:

[0112] S510: Select any one of the set of DCE-MRI images as a reference image, and extract the same feature points and / or the same feature regions of the reference image and other images in the set of DCE-MRI images.

[0113] Feature points and feature regions may be significant and unique objects in the DCE-MRI image, and may be, for example, closed boundary regions, edge regions, line intersections, etc. After selecting appropriate feature points and / or feature regions, the feature points and / or feature regions in the other image are matched with the corresponding feature points and / or feature regions in the reference image, so that the other image is correlated with the reference image.

[0114] S520: Determine a similarity transformation model between other images and the reference image based on the same feature point and / or the same area.

[0115] That is, determine the scope and method of the transformation.

[0116] S530: Registering other images with the reference image according to the determined similarity change model.

[0117] It should be noted that in the embodiments of this specification, registration processing is performed on two (or more) consecutive images from the same set of DCE-MRI images. In other embodiments, registration can also be performed on two (or more) DCE-MRI images from different groups, representing the same tissue of the same subject. Registration can also be performed between different modal images of the same tissue of the same subject, for example, a CT image can be registered with a DCE-MRI image.

[0118] Registration processing can compare images collected by different acquisition groups or different devices. Through the registration operation, these images can be transformed into a unified coordinate system, thereby achieving more accurate comparison and analysis.

[0119] In actual operation, alignment processing and registration processing can be used in combination. In the embodiment of this specification, by performing alignment and registration processing operations on the collected DCE-MRI images, the positions and directions of the DCE-MRI images and the local areas of interest of the DCE-MRI images are correctly aligned, thereby improving the accuracy of the calculated Ktrans value and providing a reliable basis for subsequent data analysis and clinical applications.

[0120] In some feasible embodiments, after performing alignment and / or registration processing on each set of DCE-MRI images, the following steps may also be performed:

[0121] An interpolation operation is performed on the aligned DCE-MRI image and / or the registered DCE-MRI image to generate a new image with the same pixel spacing and direction, that is, to increase the amount of training input data.

[0122] In summary, the magnetic resonance quantitative physiological parameter map generation method provided in the embodiments of this specification can learn and identify complex features and patterns from a large amount of training data during the model training phase, eliminating the need for modeling based on a preset hemodynamic model, thereby avoiding reliance on assumptions such as vascular continuity and fluid incompressibility. Furthermore, because deep learning models can automatically learn parameters from data, there is no need to manually select multiple parameters to calculate perfusion parameters, thereby reducing the degree of manual intervention and avoiding inaccurate calculation results due to improper parameter selection.

[0123] When using a trained deep learning model, the Quantitative Physiological Parameter Map Generation Model, to generate quantitative physiological parameter maps, it can avoid extensive mathematical calculations and analysis, reducing computational complexity while significantly improving data processing efficiency. Furthermore, the trained model reduces the requirements for the DCE-MRI images to be processed. The Quantitative Physiological Parameter Map Generation Model can generate accurate results for a single DCE-MRI image or a small number of DCE-MRI images.

[0124] As shown in FIG6 , the embodiment of this specification further provides a device for generating a magnetic resonance quantitative physiological parameter map, comprising:

[0125] an acquisition module 61 for acquiring each group of DCE-MRI images and a quantitative physiological parameter map corresponding to each DCE-MRI image;

[0126] A training module 62 is configured to use the DCE-MRI image and the quantitative physiological parameter map as training inputs to train a deep learning model until the loss function value of the deep learning model meets a preset requirement, wherein the deep learning model is a generative adversarial network, the generative adversarial network includes a generative network and a discriminative network, the generative network is configured to generate an output image, the discriminative network includes a global discriminator and a local discriminator, the global discriminator is configured to determine the similarity between the output image and the quantitative physiological parameter map, and the local discriminator is configured to determine the similarity between a local region of interest of the output image and a corresponding local region of interest in the quantitative physiological parameter map.

[0127] The processing module 63 is used to use the deep learning model when the loss function value meets the preset requirements as a quantitative physiological parameter map generation model, and process the DCE-MRI image to be processed to obtain a quantitative physiological parameter map.

[0128] The beneficial effects achieved by the device provided in the embodiments of this specification are consistent with the beneficial effects achieved by the above-mentioned method and will not be repeated here.

[0129] As shown in FIG7 , a computer device is provided in an embodiment of this specification. The apparatus for generating a magnetic resonance quantitative physiological parameter image in this specification may be a computer device in this embodiment, which performs the method for generating a magnetic resonance quantitative physiological parameter image provided in an embodiment of this specification. The computer device 702 may include one or more processors 704, such as one or more central processing units (CPUs), each of which may implement one or more hardware threads. The computer device 702 may also include any memory 706 for storing any type of information, such as code, settings, data, etc. For example, and without limitation, the memory 706 may include any one or more combinations of the following: any type of RAM, any type of ROM, a flash memory device, a hard disk, an optical disk, etc. More generally, any memory may use any technology to store information. Furthermore, any memory may provide volatile or non-volatile retention of information. Furthermore, any memory may represent a fixed or removable component of the computer device 702. In one embodiment, when the processor 704 executes associated instructions stored in any memory or combination of memories, the computer device 702 may perform any operation of the associated instructions. The computer device 702 also includes one or more drive mechanisms 708 for interacting with any storage, such as a hard disk drive mechanism, an optical disk drive mechanism, and the like.

[0130] The computer device 702 may also include an input / output module 710 (I / O) for receiving various inputs (via input devices 712) and for providing various outputs (via output devices 714). A specific output mechanism may include a presentation device 716 and an associated graphical user interface (GUI) 718. In other embodiments, the input / output module 710 (I / O), input devices 712, and output devices 714 may not be included, and the computer device 702 may simply be a computer device in a network. The computer device 702 may also include one or more network interfaces 720 for exchanging data with other devices via one or more communication links 722. One or more communication buses 724 couple the components described above together.

[0131] The communication link 722 may be implemented in any manner, for example, via a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication link 722 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.

[0132] Corresponding to the method in FIG. 1 and FIG. 3 to FIG. 5 , the embodiments of this specification further provide a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the above method are executed.

[0133] The embodiments of this specification also provide a computer-readable instruction, wherein when a processor executes the instruction, the program therein causes the processor to execute the method shown in Figures 1 and 3 to 5.

[0134] The embodiments of this specification also provide a computer program product, including at least one instruction or at least one program segment, which is loaded and executed by a processor to implement the method shown in Figures 1 and 3 to 5.

[0135] It should be understood that in the various embodiments of this specification, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this specification.

[0136] It should also be understood that in the embodiments of this specification, the term "and / or" is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. Furthermore, the character " / " in this specification generally indicates that the associated objects are in an "or" relationship.

[0137] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this specification can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the embodiments of this specification.

[0138] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0139] In the several embodiments provided in the embodiments of this specification, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or can be electrical, mechanical or other forms of connection.

[0140] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of this specification.

[0141] In addition, the functional units in the various embodiments of this specification may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0142] 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 storage medium. Based on this understanding, the technical solution of the embodiment of this specification is essentially 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, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of this specification. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0143] Specific embodiments are used in this specification to illustrate the principles and implementation methods of this specification. The description of the above embodiments is only used to help understand the methods and core ideas of this specification. At the same time, for those skilled in the art, based on the ideas of this specification, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the embodiments of this specification.

Claims

1. A method for generating a magnetic resonance quantitative physiological parameter map, characterized in that: include: Acquire each group of DCE-MRI images and a quantitative physiological parameter map corresponding to each group of DCE-MRI images; Using the groups of DCE-MRI images and the quantitative physiological parameter map as training inputs, training the deep learning model until the loss function value of the deep learning model meets the preset requirements, the deep learning model is a generative adversarial network, the generative adversarial network includes a generative network and a discriminative network, the generative network is used to generate an output image, the discriminative network includes a global discriminator and a local discriminator, the global discriminator is used to discriminate the similarity between the output image and the quantitative physiological parameter map, and the local discriminator is used to discriminate the similarity between the local region of interest of the output image and the corresponding local region of interest in the quantitative physiological parameter map; The deep learning model when the loss function value meets the preset requirements is used as a quantitative physiological parameter map generation model, and the DCE-MRI image to be processed is processed to obtain a quantitative physiological parameter map.

2. The method for generating a magnetic resonance quantitative physiological parameter map according to claim 1, characterized in that: The loss function is: LOSS = loss_G + loss_D; Wherein, LOSS is the loss value of the deep learning model, loss_G is the loss value of the generator network, and loss_D is the loss value of the discriminator network; loss_D=loss_D1*α+loss_D2*(1-α) ; Among them, loss_D1 is the loss value of the global discriminator, loss_D2 is the loss value of the local discriminator, and α is a constant coefficient greater than 0 and less than 1.

3. The method for generating a magnetic resonance quantitative physiological parameter map according to claim 2, characterized in that: The generative network is a generative network with group normalization added, and the discriminative network is a discriminative network with spectral normalization added.

4. The method for generating a magnetic resonance quantitative physiological parameter map according to claim 1, characterized in that: Obtain quantitative physiological parameter maps corresponding to each set of DCE-MRI images, including: Extract the time-signal curve of any pixel point in the same set of DCE-MRI images; Establishing a curve of the contrast agent concentration change over time at corresponding pixel points in the group of DCE-MRI images; Fit the time-signal curve and the change curve to obtain the corresponding pixel points in the group of DCE-MRI images Ktrans value; Repeat the above process to obtain the Ktrans values ​​of all pixels in the same set of DCE-MRI images; Based on the Ktrans values ​​of all pixels, the Ktrans quantitative physiological parameter map corresponding to the group of DCE-MRI images is obtained.

5. The method for generating a magnetic resonance quantitative physiological parameter map according to claim 1, characterized in that: Before obtaining the quantitative physiological parameter maps corresponding to each group of DCE-MRI images, the method further includes: Each group of DCE-MRI images is aligned and / or registered.

6. The method for generating a magnetic resonance quantitative physiological parameter map according to claim 5, characterized in that: Each group of DCE-MRI images is aligned, including: Select any one of the set of DCE-MRI images as a reference image, and obtain deviation information between other images in the set of DCE-MRI images and the reference image; According to the deviation information, other images are aligned with the reference image.

7. The method for generating a magnetic resonance quantitative physiological parameter map according to claim 5, characterized in that: Each group of DCE-MRI images is registered, including: Select any one of the set of DCE-MRI images as a reference image, and extract the same feature points and / or the same feature regions of the reference image and other images in the set of DCE-MRI images; Determining a similarity transformation model between other images and the reference image according to the same feature point and / or the same area; The other images are registered with the reference image according to the determined similarity change model.

8. A magnetic resonance quantitative physiological parameter map generating device, characterized in that: include: An acquisition module, used for acquiring each group of DCE-MRI images and a quantitative physiological parameter map corresponding to each DCE-MRI image; A training module is used to use the groups of DCE-MRI images and the quantitative physiological parameter maps as training inputs to train the deep learning model until the loss function value of the deep learning model meets the preset requirements, wherein the deep learning model is a generative adversarial network, the generative adversarial network includes a generative network and a discriminative network, the generative network is used to generate an output image, the discriminative network includes a global discriminator and a local discriminator, and the global discriminator is used to for determining the similarity between the output image and the quantitative physiological parameter map, the local discriminator is used to determine the similarity between the local region of interest of the output image and the corresponding local region of interest in the quantitative physiological parameter map; The processing module is used to use the deep learning model when the loss function value meets the preset requirements as a quantitative physiological parameter map generation model, and process the DCE-MRI image to be processed to obtain a quantitative physiological parameter map.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Systems and methods for positron emission tomography image reconstruction

    CN110298897A

  • Method and system for reconstructing dynamic contrast enhanced nuclear magnetic resonance image

    CN113052937A

  • Deformable medical image registration method and system

    CN113763442A

  • Motion corrected tracer kinetics mapping using MRI

    CN114424079A

  • Method and system for automatically characterizing liver tissue of a patient, computer program and electronically readable storage medium

    EP3863022A1

Cited By

  • Primary base alignment guided personalized soft mask aggregation federal segmentation system and method

    CN121366127A