Multi-parameter MRI medical image fusion method based on conditional diffusion probability model

Abstract

The method comprises the following steps: S101, splicing Gaussian noise of a current step and a medical image pair to be fused to obtain a three-channel tensor, and inputting the three-channel tensor into a trained noise predictor to output predicted noise; the medical image pair is an MRI image with different parameters; S102, performing single-step reverse denoising on the predicted noise to obtain a denoised image of the current step; S103, when it is judged that the current step reaches a preset step, outputting the denoised image of the current step to obtain a required medical fusion image, otherwise, setting the denoised image as Gaussian noise of a next step, and returning to step S101. The application can effectively perform image fusion on a prostate multi-parameter MRI image, can not only enhance the recognition and observation of prostate structure information, but also is beneficial to accurately positioning a suspected lesion area.

Description

Technical Field

[0001] The present invention relates to the field of medical images, and in particular to a multi-parameter MRI medical image fusion method based on a conditional diffusion probability model. Background Art

[0002] Magnetic resonance imaging (MRI) is often used to examine prostate-related diseases because it can provide rich soft tissue information. Due to the physical limitations of imaging technology, a single sensor imaging mode can only reflect the characteristics of tissues or organs in certain aspects. Medical imaging modalities can be divided into two categories: anatomical images and functional images. Different medical imaging modes can provide complementary information on different types of organs and tissues, reduce the cost of multi-source data storage, and enhance decision-making execution capabilities. Therefore, the research on the fusion of multi-parameter information will be of great significance to medical imaging diagnosis and treatment. The fusion of anatomical imaging and functional images can not only effectively determine the severity of the patient's illness, but also accurately locate the lesion.

[0003] However, because medical image fusion is a process that reduces image capacity by inputting dual or even multi-parameter images and outputting a single image, some image information is inevitably lost after fusion. Therefore, the goal of medical image fusion is to remove as much redundant information as possible from each parameter image, reduce feature aliasing at the same location in the image, preserve complementary information, and generate a high-quality fused image.

[0004] From an application perspective, image fusion belongs to a branch of image generation. Generative adversarial networks (GANs) have been used as a method for image fusion since their application in image generation. While GAN-based image fusion models have produced satisfactory fused images, they are plagued by several issues, including unstable training processes and mode collapse. These challenges result in irrational distribution and low quality of the generated fused images, severely impacting the practicality of GAN-based methods.

[0005] In recent years, the denoising diffusion probability model (DDPM) has received widespread attention. It has achieved great success in image generation due to its good mathematical interpretability and high-quality generation results. However, in image fusion, the basic diffusion model cannot achieve direct image fusion due to the lack of image ground truth, which poses a significant challenge to the current application of diffusion models in image fusion.

[0006] An existing DDPM-based image fusion method is the Denoising Diffusion Model for Multi-Modality Image Fusion (DDFM), which utilizes an unconditionally pre-trained diffusion model with a scoring-based approach. This approach relies on the priors provided by the pre-trained diffusion model, meaning that this diffusion-based method does not require training for the image fusion task. It achieves image fusion through a post-designed score matching optimization process. The diffusion parameters pre-trained for image generation may be inappropriate and unsuitable for image fusion. Furthermore, the use of a pre-trained network makes it difficult to modify the network structure, further limiting the scope of this method's application. Summary of the Invention

[0007] In view of this, the embodiments of the present disclosure provide a multi-parameter MRI medical image fusion method based on a conditional diffusion probability model, which at least partially solves the problems existing in the prior art.

[0008] An embodiment of the present invention provides a multi-parameter MRI medical image fusion method, which includes:

[0009] S101, concatenating the Gaussian noise of the current step with the medical image pair to be fused to obtain a three-channel tensor, and inputting the three-channel tensor into a trained noise predictor to output predicted noise; wherein the medical image pair is an MRI image with different parameters; during the training of the noise predictor, using a provisional ground truth image as input to the noise predictor reduces the task difficulty of the entire framework from generating a desired fused image from Gaussian noise to shifting the distribution of the provisional ground truth image to the desired fused image distribution;

[0010] S102, performing single-step reverse denoising on the predicted noise to obtain a denoised image of the current step number;

[0011] S103, when it is determined that the current number of steps reaches the preset number of steps, output the denoised image of the current number of steps to obtain the required medical fusion image, otherwise set the denoised image to the Gaussian noise of the next number of steps, and return to step S101.

[0012] Preferably, in step S101, if the current step number is 1, the Gaussian noise is randomly generated Gaussian noise.

[0013] Preferably, the training process of the noise predictor includes: obtaining a source image pair as a training set, and using a simple combination method to generate a temporary true value image from the source image pair; adding noise to the temporary true value image through a forward diffusion process to generate a noisy image and corresponding noise; splicing the noisy image and the source image pair into a three-channel tensor, and inputting it into the noise predictor for training until the preset training conditions are met.

[0014] Preferably, the temporary true value image is represented as follows:

[0015]

[0016] in: is a temporary substitute for the true value image; Represents a simple combination function; I DWI ,I T2 Represents a source image pair.

[0017] Preferably, a random value t is set between 1 and T, and a Gaussian noise is randomly generated The noise image generated by the forward diffusion process is expressed as:

[0018]

[0019] in, represents a noise image; represents the noise addition table, α t =1-β t , β t is the variable that adds the variance of the noise to the data at time t.

[0020] Preferably, when training the noise predictor, the method further includes:

[0021] The predicted noise output by the noise predictor is subjected to loss calculation to obtain a total loss L, and the total loss L is subjected to gradient descent back propagation to optimize the noise predictor; wherein the loss function includes the denoising loss L diff With the guidance loss L guide ; The formula for the total loss L is as follows:

[0022] L=L guide +L diff

[0023]

[0024] L guide =L SSIM +L int +L grad

[0025] in:

[0026] L SSIM is the structural similarity loss, and

[0027] L int is the strength loss, and

[0028] L gradis the edge contour loss, and

[0029] The desired fusion image The estimated value of

[0030] Preferably, in step S102, the denoised image obtained by the single-step reverse denoising process Expressed as:

[0031]

[0032] in:

[0033] is the standard deviation at time t,

[0034] z:

[0035] An embodiment of the present invention further provides a multi-parameter MRI medical image fusion device, comprising:

[0036] a predicted noise output unit configured to concatenate the Gaussian noise of the current step with the medical image pair to be fused to obtain a three-channel tensor, and input the three-channel tensor into a trained noise predictor to output predicted noise; wherein the medical image pair is an MRI image with different parameters; during the training of the noise predictor, using a provisional ground truth image as input to the noise predictor reduces the difficulty of the entire framework from generating a desired fused image from Gaussian noise to shifting the distribution of the provisional ground truth image to the desired fused image distribution;

[0037] a single-step reverse denoising unit, configured to perform single-step reverse denoising on the predicted noise to obtain a denoised image of the current step number;

[0038] The judgment unit is used to output the denoised image of the current step number to obtain the required medical fusion image when it is judged that the current step number reaches the preset step number; otherwise, the denoised image is set to the Gaussian noise of the next step number and the predicted noise output unit is notified.

[0039] An embodiment of the present invention further provides a multi-parameter MRI medical image fusion device, comprising:

[0040] at least one processor; and,

[0041] a memory communicatively connected to the at least one processor; wherein,

[0042] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the above-mentioned multi-parameter MRI medical image fusion method.

[0043] In one of the aforementioned embodiments, MRI medical images of the same patient with different parameters are combined to create a new image. This new image preserves the complementary information between the images with different parameters. By using a temporary ground truth image and an improved noise predictor, the fusion performance of prostate images is improved, which can assist doctors in better identifying and observing lesions, thereby improving the efficiency and accuracy of physicians' diagnoses and providing more timely and effective treatment for prostate patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0045] Figure 1 This is a flowchart of the multi-parameter MRI medical image fusion method provided in the first embodiment of the present invention.

[0046] Figure 2 The training process and reasoning flow chart of the multi-parameter MRI medical image fusion method provided in the first embodiment of the present invention;

[0047] Figure 3(a) shows Figure 2 The specific framework implementation diagram of the training process;

[0048] Figure 3(b) shows Figure 2 The specific framework implementation diagram of the reasoning process;

[0049] Figure 4 It is the structural diagram of the noise predictor;

[0050] Figure 5 Set up graphs for each layer of the noise predictor;

[0051] Figure 6 The following is a comparison chart of the fusion results of three pairs of source images and the subjective effects of other methods;

[0052] Figure 7 The following is a comparison chart of the fusion results of three pairs of source images and the objective evaluation indicators of other methods;

[0053] Figure 8 This is a schematic structural diagram of a multi-parameter MRI medical image fusion device provided in the first embodiment of the present invention. DETAILED DESCRIPTION

[0054] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0055] The following describes the embodiments of the present disclosure through specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure.

[0056] See also Figures 1 to 3(b) A first embodiment of the present invention provides a multi-parameter MRI medical image fusion method, which can be performed by a multi-parameter MRI medical image fusion device (hereinafter referred to as a fusion device), and in particular, is performed by one or more processors in the fusion device to implement the following steps:

[0057] S101 , concatenating the Gaussian noise of the current step number with the medical image pair to be fused to obtain a three-channel tensor, and inputting the three-channel tensor into a trained noise predictor to output predicted noise.

[0058] In this embodiment, the fusion device may be a computing device with data processing capabilities, such as a laptop computer, a desktop computer, a tablet computer, a workstation, or a server.

[0059] In this embodiment, for the Gaussian noise of the current step number, if the current step number is 1, the Gaussian noise is a randomly generated Gaussian noise that satisfies If the current step number is not 1, the Gaussian noise is the denoised image generated at the previous step number. For example, if the current step number is 5, the Gaussian noise is the denoised image generated at step number 4, and so on.

[0060] In this embodiment, the medical image pair is MRI images with different parameters, such as different scanning time, resolution, contrast, etc.

[0061] In this embodiment, after obtaining the Gaussian noise and the medical image pair to be fused, they are spliced ​​to obtain a three-channel tensor, and then the three-channel tensor is input into a trained noise predictor to output the predicted noise.

[0062] Before this, the noise predictor needs to be trained. The specific training process is as follows:

[0063] First, source image pairs as training sets are obtained, and the source image pairs are combined using a simple method to generate temporary ground-truth images.

[0064] In this embodiment, since the temporary ground truth image can essentially be considered a low-quality fused image, the simple combination method used here should not be complex and should strive to save computing power. For example, the corresponding pixel average or maximum value retention can be used. This embodiment uses average retention, that is, each pixel retains the average value of the corresponding position of the pixels in the source image pair. The temporary ground truth image is represented as follows:

[0065]

[0066] in: is a temporary substitute for the true value image; Represents a simple combination function; I DWI ,I T2 Represents a source image pair.

[0067] Then, the temporary true value image is denoised by a forward diffusion process to generate a noisy image and corresponding noise;

[0068] Here, set T=1000, randomly select t between 1 and T, and randomly generate a Gaussian noise The noise image can be expressed as follows according to the forward diffusion process formula:

[0069]

[0070] in, represents a noise image; represents the noise addition table, α t =1-β t , β t is the variable that adds the variance of the noise to the data at time t.

[0071] Finally, the noise image and the source image are concatenated into a three-channel tensor and input into the noise predictor for training until the preset training conditions are met.

[0072] Specifically, the noise map and the source image pair are concatenated in the channel dimension into a three-channel tensor input to the noise predictor ∈ θ () for training, the noise predictor receives not only the three-channel tensor but also the time t and outputs the predicted noise

[0073] The structure of the noise predictor can be as follows: Figure 4As shown, the specific structure of the noise predictor of this embodiment is improved based on DiT in Scalable Diffusion Models with Transformers to adapt to the medical image fusion task. The specific change is that the label embedding vector used for classification in the original model that is irrelevant to the image fusion task is deleted, leaving only the time step vector t. In addition, the use of the original structure will cause the reverse denoising process to be confined to each patch block. Since the reverse denoising process is not a perfect inverse process of adding noise in the forward diffusion process, residual noise will inevitably remain. This causes the fused image to exhibit the same residual noise in each grid area of ​​the patch block size. To solve this problem, the Patchify layer is modified to use a vector that matches the number of elements in the patch block to receive information from each patch. And a residual convolution layer is added before the Patchify layer and after the corresponding Reshape layer to expand the receptive field. This ensures that the denoising process acts evenly on the entire image, rather than being confined to each block. See the settings of each network layer of the noise predictor for details. Figure 5 All Conv layers have a kernel size of 3, a stride of 1, and a padding of 1, followed by a batch normalization layer (BN) and a ReLU activation function. The number of DiT-Blocks (N) is 4, and the number of multi-head self-attention heads is 6. The embedding layer and other internal settings of the DiT-Block remain the same as the original settings.

[0074] In this embodiment, loss calculation may be performed on the predicted noise to obtain a total loss, and then gradient descent back propagation may be performed on the total loss L to optimize the noise predictor.

[0075] Specifically, the loss function is divided into two parts: denoising loss L diff With the guidance loss L guide . Thus, the total loss L is expressed as follows:

[0076] L=L guide +L diff ;

[0077] in:

[0078]

[0079] L guide =L SSIM +L int +L grad

[0080] L SSIM is the structural similarity loss, and

[0081] L intis the strength loss, and

[0082] L grad is the edge contour loss, and

[0083] The desired fusion image The estimated value of

[0084] In this embodiment, the above steps are repeated cyclically, and the training is stopped after a preset number of epochs on the training set, and the trained noise predictor ∈ θ ().

[0085] In this embodiment, during the training process of the noise predictor, by using a temporary true value image as the input of the noise predictor, the task difficulty of the entire framework is reduced from generating the desired fused image from Gaussian noise to shifting the distribution of the temporary true value image to the desired fused image distribution, and the problem of being unable to achieve direct image fusion due to the lack of groundtruth is solved.

[0086] In addition, by using the above-mentioned improved DiT as the noise predictor, the problems of insufficient receptive field and global feature loss of the existing diffusion model UNet noise predictor are solved.

[0087] S102, performing single-step reverse denoising on the predicted noise to obtain a denoised image of the current step number.

[0088] In this embodiment, the predicted noise is subjected to a single-step reverse denoising process to obtain a denoised image. The formula for the reverse denoising process is as follows:

[0089]

[0090] in:

[0091] is the standard deviation at time t,

[0092] z:

[0093] S103, when it is determined that the current number of steps reaches the preset number of steps, output the denoised image of the current number of steps to obtain the required medical fusion image, otherwise set the denoised image to the Gaussian noise of the next number of steps, and return to step S101.

[0094] In this embodiment, the denoising image is used Instead of the Gaussian noise in step S102 Calculate again, and repeat this cycle t=T,T-1,...,1 until t=1, and the output denoised image is This is the required medical fusion image.

[0095] To further understand this embodiment, the application of this embodiment will be described below with practical examples.

[0096] 1. Experimental Dataset

[0097] Prostate MRI images of 552 patients provided by a city people's hospital were used as the original dataset. Sequences with different parameters were aligned. After all slices were extracted, 10,000 slices were randomly selected as the training set and 100 slices as the validation set. Each slice was a 320×320 8-bit BMP image.

[0098] 2. Evaluation indicators

[0099] This study uses five objective evaluation indicators to quantitatively evaluate the fusion performance of the algorithm, namely:

[0100] 2.1 Evaluation indicators based on mutual information and gradient similarity (Q AB / F ).

[0101] Q AB / F It is an evaluation index based on mutual information and gradient similarity. Gradient information is an important reflection of image structure information. By comparing the gradient information of the fused image with the source image, the degree to which the fused image retains structural information such as edges and textures can be evaluated. The retention of brightness or intensity information of the fused image is also important. The performance of the fused image in intensity information is measured by mutual information or correlation coefficient. Gradient similarity and intensity similarity are combined and weighted to calculate Q. AB / F , if Q AB / F A higher value indicates that the fused image performs better in preserving the source image information. AB / F The overall calculation formula is as follows:

[0102] Q AB / F =α·Q A / F +β·Q B / F

[0103] in:

[0104] Q A / F : The similarity between the fused image F and the source image A,

[0105] Q B / F : The similarity between the fused image F and the source image B,

[0106] α, β: Balance the weights of the two similarity indicators to satisfy α + β = 1.

[0107] in, is the gradient strength of pixel (i, j) in images A and B, is the local gradient similarity, T is the smoothing factor to avoid the denominator being zero, usually T=1e -6 ,

[0108] 2.2 Sum of the Correlations of Differences (SCD)

[0109] SCD evaluates how well the fused image retains the detail information of the source images by calculating the correlation between the differential information between the source images and the differential information between the fused image and each source image. If the fused image F has a high correlation with the differential information of both source images A and B, it means that the fused image effectively preserves the details and structural characteristics of the source images. The SCD calculation formula is as follows:

[0110] SCD=r(ΔA,ΔF)+r(ΔB,ΔF)

[0111] in:

[0112] r(ΔA, ΔF), r(ΔB, ΔF): are the differential information correlations between the source images A and B and the fused image F. The differential correlation is usually defined as the Pearson correlation coefficient, and its formula is: Cov(ΔX,ΔY) is the covariance of the differential information ΔX and ΔY, σ ΔX ,σ ΔY is the standard deviation of the difference information.

[0113] 2.3 Structural Similarity Index SSIM (Structural Similarity Index Measure)

[0114] SSIM is a classic indicator for measuring image quality. It provides image similarity evaluation results that are consistent with human perception by combining brightness, contrast, and structural similarity. Its complete formula is:

[0115]

[0116] in:

[0117] μ x ,μ y : are the means of images x and y respectively.

[0118] σ x,σ y : are the standard deviations of image x and y respectively.

[0119] σ xy : Covariance of images x and y.

[0120] C1, C2: constants used to avoid the denominator being zero.

[0121] 2.4 Mutual Information (MI)

[0122] Mutual information (MI) is an image quality evaluation metric based on information theory that measures the amount of information shared between two images. It is often used in tasks such as image fusion and image registration to assess whether the fused image retains information from the source images. A high mutual information between two images indicates that they share more information and are more similar; conversely, a low mutual information indicates a weaker correlation. Mutual information is defined as the relationship between the joint probability distribution of two images and the marginal probability distributions of each image. The specific formula is as follows:

[0123]

[0124] in:

[0125] X, Y: pixel values ​​of the two images.

[0126] p(x,y): joint probability distribution of images X and Y.

[0127] p(x): marginal probability distribution of image X.

[0128] p(y): marginal probability distribution of image Y.

[0129] 2.5 Correlation Coefficient CC

[0130] The correlation coefficient (CC) is a statistical metric used to quantify the degree of similarity between two images. It reflects the degree of correlation between them by calculating the linear correlation between corresponding pixel values ​​in the two images. The CC value range is [-1, 1]. CC = 1 indicates that the two images are completely positively correlated (the linear relationship is positive). CC = -1 indicates that the two images are completely negatively correlated (the linear relationship is negative). CC = 0 indicates that the two images are uncorrelated.

[0131] In image evaluation, a higher CC value (close to 1) usually indicates a higher similarity between two images. The calculation formula of the correlation coefficient is:

[0132]

[0133] in:

[0134] X={x1,x2,…,x N}: A set of pixel values ​​of the first image.

[0135] Y={y1,y2,…,y N}: A set of pixel values ​​of the second image.

[0136] N: total number of pixels.

[0137] μ X : the average pixel value of the first image X,

[0138] μ Y : The average pixel value of the second image Y,

[0139] 3. Experimental design and results analysis

[0140] This study conducts qualitative and quantitative experimental comparisons between this embodiment and seven commonly used image fusion methods, including NSST-PAPCNN, IFCNN, U2Fusion, DDcGAN, SwinFusion, Cddfuse, and DDFM. The comparison of the fusion results of the three pairs of DWI-MRT2 images in the test set is shown in the figure below. Figure 6 As shown. Here we are more concerned about the preservation of intensity, edge contours and structural features. Among them, NSST-PAPCNN over-emphasized the preservation of gradients, resulting in pseudo-structure enhancement on pair-2; IFCNN produced some blurring at locations with large edge changes; U2Fusion lost a lot of texture details and almost only preserved the intensity; DDcGAN had high intensity on pair-1, low intensity on pair-2, and lost some texture details on pair-3; DDFM lost texture details on all three pairs of images, but the intensity was still preserved; it is worth noting that the differences between SwinFusion, CDDFuse and the method proposed in this embodiment are almost imperceptible visually, and there are differences only in quantitative analysis, as shown in the figure. Figure 7 shown.

[0141] In summary, this embodiment combines MRI medical images of the same patient with different parameters to construct a new image. This new image preserves the complementary information between the images with different parameters. By using a temporary ground truth image and an improved noise predictor, the fusion performance of prostate images is improved, which can assist doctors in better identifying and observing lesions, thereby improving the efficiency and accuracy of physicians' diagnoses and providing more timely and effective treatment for prostate patients.

[0142] See also Figure 8The second embodiment of the present invention further provides a multi-parameter MRI medical image fusion device, which includes:

[0143] A predicted noise output unit 210 is configured to concatenate the Gaussian noise of the current step with the medical image pair to be fused to obtain a three-channel tensor, and input the three-channel tensor into a trained noise predictor to output predicted noise; wherein the medical image pair is an MRI image with different parameters; during the training of the noise predictor, using a provisional ground truth image as input to the noise predictor reduces the difficulty of the entire framework from generating a desired fused image from Gaussian noise to shifting the distribution of the provisional ground truth image to the desired fused image distribution;

[0144] A single-step reverse denoising unit 220 is configured to perform single-step reverse denoising on the predicted noise to obtain a denoised image of the current step number;

[0145] The judgment unit 230 is used to output the denoised image of the current step number to obtain the required medical fusion image when it is judged that the current step number reaches the preset step number; otherwise, the denoised image is set to the Gaussian noise of the next step number and the predicted noise output unit is notified.

[0146] A third embodiment of the present invention further provides a multi-parameter MRI medical image fusion device, comprising:

[0147] at least one processor; and,

[0148] a memory communicatively connected to the at least one processor; wherein,

[0149] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the above-mentioned multi-parameter MRI medical image fusion method.

[0150] The various technical features of the above-described embodiments can be combined arbitrarily, and the execution order of the method steps is not restricted. In order to make the description concise, not all possible combinations of the various technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0151] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A multi-parameter MRI medical image fusion method, characterized in that: include: S101, concatenate the Gaussian noise of the current step and the medical image pair to be fused to obtain a three-channel tensor, and input the three-channel tensor into a trained noise predictor to output predicted noise; wherein, the medical image pair is an MRI image with different parameters; during the training process of the noise predictor, using a temporary true value image as the input of the noise predictor reduces the task difficulty of the entire framework from generating a desired fused image from Gaussian noise to shifting from the temporary true value image distribution to the desired fused image distribution; the noise predictor is improved based on DiT in Scalable Diffusion Models with Transformers to adapt to the medical image fusion task, and the label embedding vector used for classification that is irrelevant to the image fusion task is deleted, leaving only the time step, the Patchify layer uses a vector matching the number of elements in the patch block to receive information from each patch, and a residual convolution layer is added before the Patchify layer and after the corresponding Reshape layer to expand the receptive field; the temporary true value image is represented as follows: in: is a temporary true value image; F sc () indicates a simple combination method; I DWI ,I T2 represents the source image pair; Assume that t is randomly selected between 1 and T, and a Gaussian noise ò~N(0,I) is randomly generated. Then the noise image generated by the forward diffusion process is expressed as: in, represents a noise image; represents the noise addition table, α t =1-β t , β t is the variable that adds the noise variance to the data at time t; S102, performing single-step reverse denoising on the predicted noise to obtain a denoised image of the current step number; the single-step reverse denoising process obtains a denoised image Expressed as: in: is the standard deviation at time t, z:z~N(0,I)ift>1,elsez=0;ò θ is the noise predictor; S103, when it is determined that the current number of steps reaches the preset number of steps, output the denoised image of the current number of steps to obtain the required medical fusion image, otherwise set the denoised image to the Gaussian noise of the next number of steps, and return to step S101.

2. The multi-parameter MRI medical image fusion method according to claim 1, characterized in that: In step S101 , if the current step number is 1, the Gaussian noise is randomly generated Gaussian noise.

3. The multi-parameter MRI medical image fusion method according to claim 1, characterized in that: The training process of the noise predictor includes: Obtaining source image pairs as training sets, and generating temporary true value images using a simple combination method for the source image pairs; Noising the temporary true value image through a forward diffusion process to generate a noisy image and corresponding noise; The noise-added image and the source image are concatenated into a three-channel tensor and input into a noise predictor for training until a preset training condition is met.

4. The multi-parameter MRI medical image fusion method according to claim 3, characterized in that: When training the noise predictor, also include: The predicted noise output by the noise predictor is subjected to loss calculation to obtain a total loss L, and the total loss L is subjected to gradient descent back propagation to optimize the noise predictor; wherein the loss function includes the denoising loss L diff With the guidance loss L guide ; The formula for the total loss L is as follows: L=L guide +L diff L guide =L SSIM +L int +L grad in: L SSIM is the structural similarity loss; L int is the loss of strength; L grad is the edge contour loss; The desired fusion image The estimated value of

Images