Nuclear magnetic resonance image colorectal tumor segmentation method based on multi-branch guide network

Abstract

The invention provides a nuclear magnetic resonance image colorectal tumor segmentation method based on a multi-branch guide network. The method comprises the following steps: a data normalization step; a precise segmentation preprocessing step; a tumor judgment pretreatment step; a calibration step; and obtaining a prediction result. A double-branch guide structure is used, a main branch focuses on accurate segmentation of a tumor area, and a secondary branch focuses on judgment of whether a tumor exists or not. The secondary branch guides the main branch, thereby helping to reduce the false positive rate and improve the accuracy of the segmented region. The method is combined with a confidence learning method of uncertainty analysis, reduces the attention to dispute regions, enables the model to be more focused on the segmentation of main regions, and improves the overall segmentation effect.

Description

Technical Field

[0001] The present invention relates to the field of medical image technology, and more specifically, to a method for segmenting colorectal tumors in magnetic resonance imaging based on a multi-branch guided network. Background Art

[0002] At present, with the development of deep learning, it has played a vital role in the diagnosis of colorectal cancer by magnetic resonance imaging, and has significantly improved the efficiency and accuracy of diagnosis through automated image analysis. Traditional diagnostic methods rely on doctors' manual analysis of images, which is time-consuming and easily affected by subjective factors. In contrast, deep learning, especially convolutional neural network (CNN) technology, can automatically extract features from a large number of medical images to achieve early detection and treatment of tumors. In the screening, staging and treatment effect evaluation of colorectal cancer, deep learning models have shown excellent capabilities, which can not only help doctors detect tiny lesions, but also effectively reduce the misdiagnosis rate, and provide strong support for the formulation of personalized treatment plans, thereby significantly improving the patient's recovery effect.

[0003] However, the current application of deep learning in colorectal cancer image segmentation faces some bottlenecks, mainly for two reasons. First, there is a class imbalance problem in colorectal cancer image data. Most of the data comes from sick patients, resulting in a high false positive rate, which affects the robustness of the segmentation model. Secondly, due to inconsistencies in controversial areas such as transition zones when manually annotating tumor areas, the model is easily confused in these areas, resulting in poor segmentation results. Therefore, new solutions to the above problems are urgently needed. Summary of the invention

[0004] The present invention overcomes the shortcomings of the prior art and provides a method for segmenting colorectal tumors in magnetic resonance imaging based on a multi-branch guided network, which focuses on judging whether a tumor exists and improves the overall segmentation effect.

[0005] The technical solution of the present invention is as follows:

[0006] The method for segmenting colorectal tumors in magnetic resonance imaging based on a multi-branch guided network specifically includes the following steps:

[0007] S1 Data normalization step: read the patient's MRI image, normalize the acquired MRI image, and convert the normalized data into the input feature vector F input ;

[0008] S2 Precise segmentation preprocessing step: Input feature vector F input Input main branch encoder Encoder main , get the multi-dimensional feature set of the main branch image

[0009] S3 Tumor preprocessing step: Input feature vector F input Input guide sub-branch classifier Classify sub , get the sub-branch image tumor prior feature set

[0010] S4 calibration step: the main branch image multidimensional feature set C obtained in step S2 is main and the secondary branch image tumor prior feature set C obtained in step S3 sub Input feature guided module M guild , get the calibrated image feature set

[0011] S5: Get the prediction result step: The merged image feature set C guild Input decoder to get the segmentation prediction result Mask pre .

[0012] Furthermore, the feature guidance module M guild The specific processing steps are as follows:

[0013] S4.1. The lowest dimensional feature of the main branch feature set Input the feedforward artificial neural network model MLP to obtain the calibrated features And the calibrated features is with Eigenvectors of uniform size;

[0014] S4.2. Multidimensional feature set C of main branch image main The second dimension and the prior feature set C of the secondary branch image tumor sub The second dimension Calculate the corresponding feature guidance module M respectively guild The calibration attention is obtained to obtain the remaining calibration feature set S4.3, combining the calibrated image features obtained in step S4.1 and step S4.2 into a set

[0015] Furthermore, the specific processing steps of calibrating attention are as follows:

[0016] Step 4.2.1. Main branch features In the input dense convolution, i∈n represents a certain sampling stage; the convolution operation with a convolution kernel of 3×3 is performed with a step size of 1, 3, and 5 respectively. The result is restored to the feature size by the convolution operation with a convolution kernel of 1×1, and then the feature is added and merged. Its characteristic size and main branch characteristics remain unchanged;

[0017] Step 4.2.2: Features Use pooling kernels with kernels of 2×2, 3×3, 5×5, and 6×6 for pooling operations respectively, and use 1×1 convolution to restore the feature map size. The results are merged along the channel dimension to obtain new features. Its characteristic size is similar to the main branch characteristics remain unchanged;

[0018] Step 4.2.3: Use sub-branch features As a query, the feature is used as the key and value for attention calculation, and the attention weight is obtained. Perform dot multiplication to get features Step 4.2.4: Input feedforward network, expand the channel four times, calculate the depth convolution and restore it to the original size to obtain the calibrated attention feature

[0019] Furthermore, the The calculation formula for attention is:

[0020]

[0021] Among them, W represents the linear operation after flattening, keeping the number of features unchanged; Q is the query vector, K is the key vector, and V is the value vector.

[0022] Furthermore, the decoder Decoder specifically comprises: converting the calibrated image feature set C guild The highest dimension is upsampled according to the sampling stage to restore the feature size, and then the calibrated image feature set C of the corresponding dimension is used. guild The features in the last layer are restored to obtain the final segmentation prediction result Mask. pre .

[0023] Furthermore, the above process formula is expressed as follows:

[0024]

[0025] Where Up represents an upsampling operation.

[0026] Furthermore, it also includes the S6 update step: Mask the segmentation prediction result pre And the real annotation Mask gt Input uncertain region processing module M uncertain After that, after obtaining the segmentation loss of ignoring the controversial part, back propagation is used to update the entire model parameters.

[0027] Furthermore, the uncertainty processing module M uncertain , the specific processing includes the following steps:

[0028] Step 6.1: Count the segmentation prediction results pixel by pixel pre And the real annotation Mask gt The distribution number C of misclassified pixels in the , for the true label j, the number of errors predicted as i can be defined as follows:

[0029]

[0030] in Indicates the predicted category; y * Indicates the actual labeling result; t j represents the probability threshold, D(x) represents the distance from the tumor area; d x is the distance threshold, p represents the probability; is the number of predictions for class j when it is greater than the prediction probability threshold;

[0031] Step 6.2: Calculate the average probability Q of tumor region misclassification, where Q can be defined as:

[0032]

[0033] Where M is the number of all categories;

[0034] Step 6.3, mark all areas with a probability higher than the average probability Q;

[0035] Step 6.4: Calculate the segmentation loss and perform back propagation to update the model weights, ignoring the marked areas, which do not participate in the loss function calculation;

[0036] Specifically, the segmentation loss is a comprehensive weighted loss including Dice loss and cross entropy loss, and its calculation formula is:

[0037] L=λL dice +(1-λ)L ce

[0038]

[0039] In the dice loss, Pre represents the predicted area and GT represents the real labeled area, and Inter represents the intersection of the two.

[0040] The i in CE loss represents the i-th sample, c represents the classification of the sample, and y represents whether the actual classification is the current class (1 or 0). represents the classification probability; N represents the total number of samples, and C represents the total number of categories;

[0041] Step 6.5: Perform back propagation to calculate the gradient of each layer to update the main branch model weights.

[0042] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned segmentation method when executing the computer program.

[0043] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the segmentation method described above.

[0044] Compared with the prior art, the present invention has the following advantages:

[0045] The present invention proposes a method for colorectal tumor MRI image segmentation based on a multi-branch guided network. First, this method uses a dual-branch guided structure, where the main branch focuses on the precise segmentation of the tumor area, while the secondary branch focuses on the judgment of whether the tumor exists or not. The secondary branch guides the main branch to help reduce the false positive rate and improve the accuracy of the segmented area. Secondly, the confidence learning method combined with uncertainty analysis reduces the focus on controversial areas, allowing the model to focus more on the segmentation of the main area, thereby improving the overall segmentation effect.

[0046] The present invention also inputs the segmentation prediction results and the real annotations into the uncertain region processing module, obtains the segmentation loss of ignoring the disputed part, and then back-propagates to update the model. This effectively reduces the false positive rate of model prediction and reduces the suboptimal training problem caused by the disputed area. This effectively improves the accuracy and robustness of the segmentation model. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a flow chart of the segmentation method of the present invention;

[0048] Figure 2 It is a method architecture diagram of the present invention;

[0049] Figure 3 It is the guide module M of the present invention guild Structural diagram. DETAILED DESCRIPTION

[0050] The embodiments of the present invention are described in detail below, wherein the same or similar reference numerals throughout represent the same or similar elements or elements with similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention and cannot be used as a limitation of the present invention.

[0051] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art in the field to which the present invention belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless defined as herein.

[0052] The reference numerals of the steps mentioned in each embodiment are only for the convenience of description and have no substantial sequence connection. Different steps in each specific embodiment can be combined in different sequences to achieve the purpose of the invention. In addition, some structures, modules and model methods not described in detail in the present invention can be implemented by conventional technical means, so they will not be described in detail.

[0053] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments.

[0054] like Figures 1 to 3 As shown, the method for segmenting colorectal tumors in magnetic resonance imaging based on a multi-branch guided network specifically includes the following steps:

[0055] S1 Data normalization step: read the patient's MRI image, normalize the acquired MRI image, and convert the normalized data into the input feature vector F input The details are as follows:

[0056] Obtain the patient's MRI image, and take the MRI image formed by the diffusion-weighted imaging technique of the abdominal transverse high-resolution T2 image as an example. The image size is generally (C, 512, 512), where C is the number of scanning layers, and the number of image layers may be different for different patients. Perform normalization processing on the image, specifically including:

[0057] Physical normalization: By mapping the image intensity value to a uniform physical unit, the image spacing is read. When the Spacing is not 0.3 mm, it is proportionally normalized to 0.3 mm.

[0058] Z-Score standardization: Calculate the mean and variance of the image and adjust the image intensity values ​​to data with zero mean and unit variance.

[0059] After normalization, it is transformed into the input feature vector F input Taking the 32-layer size as an example, the input size is (32, 1, 3, 512, 512), and its value is between (0, 1], which is converted into a tensor array to form the input feature vector F input .

[0060] S2 Precise segmentation preprocessing step: Input feature vector F input Input main branch encoder Encoder main , get the multi-dimensional feature set of the main branch image

[0061] The main branch encoder Encoder main , the input feature vector F input Input the image feature extraction network to extract the multi-dimensional feature set of the main branch image The stage represents all sampling stages. Specifically, it generally includes four stages of sampling output:

[0062] Phase 1 is a feature vector of size (32, 256, 1, 128, 128).

[0063] Phase II is a feature vector of size (32, 512, 1, 64, 64).

[0064] Phase 3 is a feature vector of size (32, 1024, 1, 32, 32).

[0065] Stage 4 is a feature vector of size (32, 2048, 1, 16, 16).

[0066] Feature extraction network. This solution uses ResNet-50 as a feature extraction network. Naturally, any deep learning network with feature extraction function can be used as a substitute. The number of network parameters and complexity are selected according to the actual task. The sampling stage is selected as 4 stages. At the beginning of each stage, the dimension reduction block is input for dimension reduction. In this solution, the number of stages involved is selected as 4. This is because 4 stages is currently a better method.

[0067] The specific structural order of the dimensionality reduction block is: first perform convolution with a stride of 2 and a kernel of 3; then perform batch normalization; and finally activate with the ReLU activation function.

[0068] S3 Tumor preprocessing step: Input feature vector F input Input guide sub-branch classifier Classify sub , get the sub-branch image tumor prior feature set

[0069] Among them, the sub-branch classifier Classify sub , the input feature vector F inputInput classification feature extraction network to extract multi-dimensional sub-branch image tumor prior feature set Here, stage represents all sampling stages; for the classification feature extraction network, this solution selects DenseNet-121 as the classification feature extraction network. Naturally, any classification deep learning network with feature extraction function can also be used instead. The number of network parameters and complexity are selected according to the actual task.

[0070] The specific sampling stage generally includes four stages of sampling feature output:

[0071] Phase 1 is a feature vector of size (32, 256, 1, 128, 128).

[0072] Phase II is a feature vector of size (32, 512, 1, 64, 64).

[0073] Phase 3 is a feature vector of size (32, 1024, 1, 32, 32).

[0074] Stage 4 is a feature vector of size (32, 2048, 1, 16, 16).

[0075] Then the tumor prior feature set C sub The input classifier obtains the classification result of tumor presence or absence. The specific classifier structure includes global pooling, fully connected layer and activation function. Global pooling is flattened after average pooling operation with a kernel of 1. The fully connected layer outputs the target category (where tumor presence or absence is a binary classification task). The activation function is the Sigmund activation function, which converts the prediction score into a probability distribution.

[0076] The weights are updated based on the actual presence or absence of a tumor by calculating the classification result loss.

[0077] Specifically, the loss function for the classification result supervision is the cross entropy loss function, and the calculation formula is:

[0078]

[0079] Where M is the number of positive samples, N is the number of secondary samples, and p is the probability. i represents the number of samples, y represents whether the sample is a tumor, and y i =1 means the sample is labeled as positive, y i =0 means the sample is labeled as negative.

[0080] S4 calibration step: the main branch image multidimensional feature set C obtained in step S2 is mainand the secondary branch image tumor prior feature set C obtained in step S3 sub Input feature guided module M guild , get the calibrated image feature set

[0081] Feature-guided module M guild The specific processing steps are as follows:

[0082] S4.1. The lowest dimensional feature of the main branch feature set Input the feedforward artificial neural network model MLP to obtain the calibrated features And the calibrated features is with The feedforward artificial neural network model MLP is used to fit the nonlinear relationship between input and output (represented here as and ), increasing the model capacity.

[0083] S4.2. Multidimensional feature set C of main branch image main The second dimension and the prior feature set C of the secondary branch image tumor sub The second dimension Calculate the corresponding feature guidance module M respectively guild The calibration attention is obtained to obtain the remaining calibration feature set

[0084] Calibrate attention, the specific process is as follows:

[0085] Step 4.2.1. Main branch features In the input dense convolution, i∈n represents a sampling stage (note the main branch feature here Does not include the lowest dimensional features ). Use convolution kernel 3×3 to perform convolution operations with step sizes of 1, 3, and 5 respectively. Use convolution kernel 1×1 to restore the feature size of the three step size convolution operations. Add and merge the results of the three restored feature sizes to get the feature Its characteristic size and main branch characteristics Remain unchanged.

[0086] Step 4.2.2: Features Pooling operations are performed using pooling kernels with kernels of 2×2, 3×3, 5×5, and 6×6, respectively. The operation results of different pooling kernels are restored to the size of the feature map using 1×1 convolution. All the results of the restored feature map size are merged along the channel dimension to obtain new features. Its characteristic size is similar to the main branch characteristics Remain unchanged.

[0087] Step 4.2.3: Use sub-branch features As a query, the feature is used as the key and value for attention calculation, and the attention weight is obtained. Perform dot multiplication to get features The sub-branch features here Does not include the lowest dimensional features

[0088] Specifically, the The calculation formula for attention is:

[0089]

[0090] W represents the linear operation after flattening, keeping the number of features unchanged. Q is the query vector, K is the key vector, and V is the value vector. Specifically, the similarity between the query vector and the key vector is calculated to allow the model to focus on the relevant part of the input, that is, the attention weight. The attention weight is used to operate with the value vector to obtain the features that have been calibrated for attention.

[0091] Step 4.2.4: Input feedforward network, expand the channel four times, calculate the depth convolution and restore it to the original size to obtain the calibrated attention feature

[0092] S4.3, combining the calibrated image features obtained in step S4.1 and step S4.2 into a set

[0093] S5: Get the prediction result step: The merged image feature set C guild Input decoder to get the segmentation prediction result Mask pre .

[0094] The decoder Decoder specifically includes: guild The highest dimension is upsampled according to the sampling stage to restore the feature size, and then the calibrated image feature set C of the corresponding dimension is used. guild The features in the last layer are restored to obtain the final segmentation prediction result Mask. pre The above process formula is expressed as follows:

[0095]

[0096] Where Up represents an upsampling operation.

[0097] Preferably, the method further includes an updating step S6: updating the segmentation prediction result Mask preAnd the real annotation Mask gt Input uncertain region processing module M uncertain After obtaining the segmentation loss of ignoring the controversial part, back propagation updates the parameters of the entire model, which is equivalent to calculating the degree of one's own error to adjust the parameters of each step.

[0098] Real annotation Mask gt The images are manually annotated by radiologists with more than 3 years of experience, initially reviewed by radiologists with more than 5 years of experience, and finally reviewed by radiologists with more than 10 years of experience.

[0099] The uncertainty processing module M uncertain , the specific processing includes the following steps:

[0100] Step 6.1: Count the segmentation prediction results pixel by pixel pre And the real annotation Mask gt The distribution number C of misclassified pixels in the , for the true label j, the number of errors predicted as i can be defined as follows:

[0101]

[0102] in Indicates the predicted category; y * Indicates the actual labeling result; t j represents the probability threshold, D(x) represents the distance from the tumor area; d x is the distance threshold; p represents the probability. is the number of predictions for class j when it is greater than the prediction probability threshold.

[0103] Step 6.2: Calculate the average probability Q of tumor region misclassification, where Q can be defined as:

[0104]

[0105] Where M is the number of all categories.

[0106] Step 6.3: Mark all regions with probability higher than the average probability Q.

[0107] Step 6.4: Calculate the segmentation loss and perform backpropagation to update the model weights, ignoring the marked areas. The marked areas do not participate in the loss function calculation.

[0108] Specifically, the segmentation loss is a comprehensive weighted loss including Dice loss and cross entropy loss, and its calculation formula is:

[0109] L=λL dice +(1-λ)L ce

[0110]

[0111] In the dice loss, Pre represents the predicted area and GT represents the real labeled area, Inter represents the intersection of the two, and λ is a constant coefficient ranging from 0 to 1, generally set to 0.6.

[0112] The i in CE loss represents the i-th sample, c represents the classification of the sample, and y represents whether the actual classification is the current class (1 or 0). Represents the classification probability. N represents the total number of samples, and C represents the total number of categories.

[0113] Step 6.5: Perform back propagation to calculate the gradient of each layer to update the main branch model weights.

[0114] S7 model application step: fix the model parameters after step S6 and use them for colorectal tumor segmentation image processing. That is, for unknown colorectal tumor images, input the high-resolution T2 diffusion-weighted imaging magnetic resonance image of the abdomen in transverse section to obtain the corresponding tumor area in the unknown colorectal tumor image.

[0115] In one embodiment, the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the segmentation method provided in the above embodiment are implemented.

[0116] In one embodiment, the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the segmentation method provided in the above embodiment are implemented.

[0117] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0118] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the 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.

[0119] The descriptions of several embodiments of the application are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the application, and these improvements and modifications should also be regarded as within the scope of protection of the present invention. Therefore, the scope of protection of the patent of this application shall be based on the attached claims.

Claims

1. A method for colorectal tumor segmentation in magnetic resonance imaging based on a multi-branch guided network, characterized in that: The specific steps include: S1 Data normalization step: read the patient's MRI image, normalize the acquired MRI image, and convert the normalized data into the input feature vector F input ; S2 Precise segmentation preprocessing step: Input feature vector F input Input main branch encoder main , get the multi-dimensional feature set of the main branch image n∈stage; S3 Tumor preprocessing step: Input feature vector F input Input guide sub-branch classifier Classify sub , get the sub-branch image tumor prior feature set n∈stage; S4 calibration step: the main branch image multidimensional feature set C obtained in step S2 is main and the secondary branch image tumor prior feature set C obtained in step S3 sub Input feature guided module M guild , get the calibrated image feature set n∈stage; S5: Get the prediction result step: The merged image feature set C guild Input decoder to get the segmentation prediction result Mask pre .

2. The method for colorectal tumor segmentation in magnetic resonance imaging based on a multi-branch guided network according to claim 1, characterized in that: The feature guidance module M guild The specific processing steps are as follows: S4.

1. The lowest dimensional feature of the main branch feature set Input the feedforward artificial neural network model MLP to obtain the calibrated features And the calibrated features is with Eigenvectors of uniform size; S4.

2. Multidimensional feature set C of main branch image main The second dimension and the prior feature set C of the secondary branch image tumor sub The second dimension Calculate the corresponding feature guidance module M respectively guild The calibration attention is obtained to obtain the remaining calibration feature set n∈stage; S4.3, combining the calibrated image features obtained in step S4.1 and step S4.2 into a set n∈stage.

3. The method for segmenting colorectal tumors in magnetic resonance imaging based on a multi-branch guided network according to claim 2, characterized in that: The specific processing steps of calibrating attention are as follows: Step 4.2.

1. Feature the main branch In the input dense convolution, i∈n represents a certain sampling stage; the convolution operation with a convolution kernel of 3×3 is performed with a step size of 1, 3, and 5 respectively. The result is restored to the feature size by the convolution operation with a convolution kernel of 1×1, and then the feature is added and merged. Its characteristic size and main branch characteristics remain unchanged; Step 4.2.2: Features Use pooling kernels with kernels of 2×2, 3×3, 5×5, and 6×6 for pooling operations respectively, and use 1×1 convolution to restore the feature map size. The results are merged along the channel dimension to obtain new features. Its characteristic size is similar to the main branch characteristics remain unchanged; Step 4.2.3: Use sub-branch features As a query, the feature is used as the key and value for attention calculation, and the attention weight is obtained. Perform dot multiplication to get features Step 4.2.4: Input feedforward network, expand the channel four times, calculate the depth convolution and restore it to the original size to obtain the calibrated attention feature 4. The method for segmenting colorectal tumors in magnetic resonance imaging based on a multi-branch guided network according to claim 3, characterized in that: The The calculation formula for attention is: Among them, W represents the linear operation after flattening, keeping the number of features unchanged; Q is the query vector, K is the key vector, and V is the value vector.

5. The method for segmenting colorectal tumors in magnetic resonance imaging based on a multi-branch guided network according to claim 1, characterized in that: The decoder Decoder specifically comprises: guild The highest dimension is upsampled according to the sampling stage to restore the feature size, and then the calibrated image feature set C of the corresponding dimension is used. guild The features in the last layer are restored to obtain the final segmentation prediction result Mask. pre .

6. The method for segmenting colorectal tumors in magnetic resonance imaging based on a multi-branch guided network according to claim 5, characterized in that: The above process formula is expressed as follows: Where Up represents an upsampling operation.

7. The method for segmenting colorectal tumors in magnetic resonance imaging based on a multi-branch guided network according to claim 1, characterized in that: It also includes the S6 update step: Mask the segmentation prediction result pre And the real annotation Mask gt Input uncertain region processing module M uncertain After that, after obtaining the segmentation loss of ignoring the controversial part, back propagation is used to update the entire model parameters.

8. The method for segmenting colorectal tumors in magnetic resonance imaging based on a multi-branch guided network according to claim 4, characterized in that: Uncertainty processing module M uncertain , the specific processing includes the following steps: Step 6.1: Count the segmentation prediction results pixel by pixel pre And the real annotation Mask gt The distribution number C of misclassified pixels in the , for the true label j, the number of errors predicted as i can be defined as follows: in Indicates the predicted category; y * Indicates the actual labeling result; t j represents the probability threshold, D(x) represents the distance from the tumor area; d x is the distance threshold, p represents the probability; is the number of predictions for class j when it is greater than the prediction probability threshold; Step 6.2: Calculate the average probability Q of tumor region misclassification, where Q can be defined as: Where M is the number of all categories; Step 6.3, mark all areas with a probability higher than the average probability Q; Step 6.4: Calculate the segmentation loss and perform back propagation to update the model weights, ignoring the marked areas, which do not participate in the loss function calculation; Specifically, the segmentation loss is a comprehensive weighted loss including Dice loss and cross entropy loss, and its calculation formula is: L=λL dice +(1-λ)L ce In the dice loss, Pre represents the predicted area and GT represents the real labeled area, and Inter represents the intersection of the two. The i in CE loss represents the i-th sample, c represents the classification of the sample, and y represents whether the actual classification is the current class (1 or 0). represents the classification probability; N represents the total number of samples, and C represents the total number of categories; Step 6.5: Perform back propagation to calculate the gradient of each layer to update the main branch model weights.

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 steps of the segmentation method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the segmentation method according to any one of claims 1 to 8 are implemented.

Images