Automatic detection method and system for cervical plexus neuropathy

Abstract

The present invention discloses an automatic detection method and system for cervical plexus neuropathy, which belongs to the field of medical image processing technology. The method combines the coronal image of MRI of the neck, constructs an automatic detection model for cervical plexus neuropathy based on spatially aware sparse Transformer and trains the labeled data to obtain a trained network model; the trained model is used to test the unlabeled images to achieve accurate segmentation of the cervical plexus nerve area and binary classification of abnormal or normal cervical plexus nerves. The present invention can segment the cervical plexus nerve area with high throughput and realize automatic detection of cervical plexus neuropathy, and has strong robustness and good generalization ability. The automatic detection method of cervical plexus neuropathy of the present invention can significantly improve the accuracy and efficiency of cervical plexus neuropathy detection, provide a powerful auxiliary tool for clinical diagnosis, and is expected to fill the technical gap in this field.

Description

Technical Field

[0001] The present invention relates to an automatic detection method and a detection system for cervical plexus neuropathy, and belongs to the technical field of medical image processing. Background Art

[0002] Neck and shoulder pain is a very common clinical condition, usually attributed to a variety of causes such as cervical spondylosis, cervical fasciitis, neck and shoulder muscle strain, and frozen shoulder. However, there is also a lesser-known peripheral sensory neuropathy, namely cervical plexus entrapment syndrome. For this lesion, clinical testing usually requires the use of imaging techniques such as magnetic resonance imaging (MRI) to determine the location and extent of the lesion. Although this lesion may cause intractable neck and shoulder pain, it is easily missed in clinical practice, which has a serious impact on the patient's quality of life.

[0003] In recent years, deep learning technology, with its powerful data processing and pattern recognition capabilities, has rapidly emerged in the medical field, becoming a major force driving advancements in medical technology. In particular, deep learning has demonstrated unprecedented potential and broad application prospects in the critical area of medical lesion detection. Through training and optimization on massive amounts of medical data, deep learning algorithms can accurately capture and analyze subtle changes in medical images, providing doctors with more accurate and efficient diagnostic support.

[0004] Deep learning has been particularly successful in image analysis and automated diagnosis. It not only significantly improves lesion detection accuracy but also significantly shortens diagnostic time, reducing physician workload. This technology has already achieved impressive initial results in the detection of various neurological lesions. For example, in the identification of lesions in complex neural structures such as the brachial plexus and choroid plexus, deep learning algorithms, with their exceptional feature extraction capabilities, have successfully helped physicians detect many early-stage lesions that are difficult to detect with traditional methods, buying patients valuable time for treatment.

[0005] However, despite significant progress in the field of neurological lesion detection, deep learning applications in the specific area of cervical plexus lesion detection remain largely unexplored. As one of the body's most important neural structures, lesions of the cervical plexus can severely impact patients' daily lives and health. However, due to the complexity and diversity of cervical plexus lesions and the relative scarcity of existing medical data, the research and application of deep learning algorithms in cervical plexus lesion detection face numerous challenges. Therefore, there is an urgent need to increase research investment in related fields and collect more high-quality cervical plexus lesion data to promote breakthroughs and applications of deep learning technology in cervical plexus lesion detection. Summary of the Invention

[0006] In order to improve the accuracy and efficiency of cervical plexus neuropathy detection, the present invention provides an automatic cervical plexus neuropathy detection method and detection system. The technical solution is as follows:

[0007] A first object of the present invention is to provide a method for automatically detecting cervical plexus neuropathy, comprising:

[0008] Step 1: Acquire cervical MRI images and perform preprocessing;

[0009] Step 2: Use the cervical plexus nerve estimation module to process the cervical MRI image, preliminarily locate the cervical plexus nerves, and obtain a rough map containing their location information;

[0010] Step 3: Use the bidirectional feature propagation module to correct the deviation in the process of extracting cervical plexus nerve position information and improve the ability to aggregate information from MRI sequences;

[0011] The bidirectional feature propagation module uses a feature-aware alignment module to generate aggregated features based on the cervical plexus feature encoder and propagates them to the previous and next layer sequence flows;

[0012] Step 4: Achieve high performance based on spatially aware sparse Transformer while exploiting distal information in MRI sequences;

[0013] The spatially aware sparse Transformer uses a spatially aware attention layer to capture the features of distal information of the MRI layer sequence based on aggregated features and generate refined features;

[0014] Step 5: Use the cervical plexus feature decoder to predict the segmentation result of the cervical plexus region based on the refined features;

[0015] Step 6: Use the classification diagnosis module to perform abnormality prediction based on refined features to achieve binary classification of cervical plexus nerve abnormality or normality.

[0016] Optionally, step 2 includes:

[0017] Step 21: Average pooling is performed on each layer of the 2D image of the 3D neck MRI image to obtain a downsampled 3D neck MRI layer sequence.

[0018] Step 22: According to Estimating forward sequence flow using the Opencv package in Python and backward sequence flow

[0019] Step 23: Based on the forward sequence flow and backward sequence flow The cervical plexus estimation module generates a non-normalized coarse map for each layer sequence

[0020]

[0021] A t =1-B t

[0022] Among them, O 1→0 =0,O T→T+1 = 0, i and t represent the channel and step length of laminar flow respectively, A t It's B t The refined image obtained after normalization operation can realize the preliminary positioning of the cervical plexus nerve position information.

[0023] Optionally, step 3 includes:

[0024] Step 31: Input each layer of the 2D image of the 3D cervical MRI image into the cervical plexus nerve feature encoder to obtain features of different scales, and the bidirectional feature propagation module corresponds to different propagation branches based on the different levels of features extracted by the encoder;

[0025] Step 32: Assuming that the current layer sequence is the tth layer, during the forward propagation process, for the jth propagation branch, the aggregated features of the current layer sequence Obtained by:

[0026]

[0027] Among them, FAM stands for Feature-Aware Alignment Module, represents the aggregated features of the t-th layer sequence of the j-1th branch, and Represent the features generated by the previous layer and the first two layers of sequences, O t→t-1 Represents the sequence flow from the previous layer to the current layer, O t→t-2 Represents the sequence flow from the first two layers to the current layer, W represents the reverse registration operation, and A t-1 and A t-2 Represent the fine graphs of the previous layer and the first two layers of sequence respectively;

[0028] The above process proceeds forward in sequence according to the layer sequence until t = T;

[0029] The backward propagation process is similar to the forward propagation process, but in the opposite direction.

[0030] Optionally, the processing of the spatially aware sparse Transformer includes:

[0031] Step 41: Given the aggregated features finally obtained in step 3 A soft partitioning operation is used to partition each aggregated feature into overlapping blocks of size p×p with a partitioning step size of s.

[0032] Step 42: Concatenate the segmented features to generate block embedding

[0033] Step 43: Downsample the coarse image B by average pooling with a window size of p×p and a step size of s to obtain

[0034] Step 44: The generated block embedding z is transformed through three separate linear layers to obtain and Where M and N represent the number of blocks divided in the height and width domain values respectively, and C z Indicates the number of channels;

[0035] Step 45: Divide into m×n non-overlapping windows to generate partition features Where m×n and h×w are the number and size of windows respectively;

[0036] Step 46: Pool the global vector g using the block embedding z and depthwise convolution k and g v Generated by:

[0037] g k =l k (DC(z))

[0038] g v =l v (DC(z))

[0039] Among them, l k and l v represents a linear layer, DC stands for depthwise convolution;

[0040] Next, g k Repeat until G k , g v Repeat until G v , respectively

[0041]

[0042] Step 47: Perform a sparse operation on the distal sequence to ensure that the spatial perception attention is focused only on the cervical plexus region. First, perform a maximum pooling operation on the distal sequence. Downsampling to generate a rough window image Then, the distal sparse mask of the window is obtained as follows:

[0043]

[0044] Among them U t,i,j represents the coarse image at window (i, j) of the t-th layer sequence, θ is the threshold for considering the relevant window as the window where the coarse image is located, Q t Each element Q in t,i,j It is a binary variable used to determine whether the window is the window where the rough image is located. For E q 、E k and E v The distal sparse mask of The clipping function Clip sets S to l; then, the distal sparse embedding feature I is generated using the following method q , I k and I v :

[0045]

[0046] Concat represents the concatenation operation; if S i,j = 0, indicating that the window position indexed by i, j in the layer sequence does not contain the coarse image, and this window position is excluded; and where m s and n s Represents the number of selected windows within the m and n domain values respectively;

[0047] Step 48: In the layer sequence domain, select the window where the rough image is located as the query space to ensure that the spatial perception attention is only focused on the cervical plexus area; given the distal sparse embedding feature I q , spatially sparse embedding y q Generates the following:

[0048]

[0049] y q =Concat(H q )

[0050] in Top(K q ,·) means finding the Kth q Operations on large elements; for I q For each window located at i,j in the layer sequence domain, we selectively select the K windows that contain the highest proportion of coarse images. q windows;

[0051] Step 49: In contrast to the query space, the key / value space selects distal sparse embedding features I k ,Iv The fine area containing the cervical plexus; given I k and I v , spatial sparse embedding feature y k and y v Generates the following:

[0052]

[0053] y k =Concat(H k )

[0054]

[0055] y v =Concat(H v )

[0056] in

[0057] Step 410: Spatially sparse query embedding y q Reshaped into Similarly, the spatially sparse key / value embedding y k and y v Reshaped into and For m s n s For each window in , the self-attention is calculated as follows:

[0058]

[0059] Introducing multi-head self-attention in the spatially aware sparse Transformer to obtain output embedding

[0060] z s =MSA(Y q ,Y k ,Y v ).

[0061] Optionally, the cervical plexus feature encoder includes four sublayers, each sublayer includes a feedforward neural network, and residual connection and layer normalization are applied after each sublayer; the feedforward neural network includes a convolution block Conv1×1, an activation function GELU and a deformable convolution block DConv connected in sequence.

[0062] Optionally, the activation function GELU is defined as follows:

[0063]

[0064] where Φ(x) is the cumulative distribution function of the standard normal distribution and erf(·) is the error function.

[0065] Optionally, the deformable convolution block DConv is defined as follows:

[0066]

[0067] Where F(x,y) represents the input feature map, F(x,y) represents the deformation feature map, K represents the total number of sampling points, k represents the enumeration sampling point, w k represents the learnable weight of the kth sampling point, (x+Δx k ,y+Δy k ) represents the offset coordinates of the sampling point.

[0068] A second object of the present invention is to provide an automatic detection system for cervical plexus neuropathy, the system being applied to any of the above-mentioned automatic detection methods for cervical plexus neuropathy, the system comprising:

[0069] an image acquisition module configured to acquire a neck MRI image;

[0070] a cervical plexus nerve estimation module, configured to process the cervical MRI image, preliminarily locate the cervical plexus nerves, and obtain a rough map containing their position information;

[0071] The bidirectional feature propagation module is configured to use the feature-aware alignment module to generate aggregated features based on the cervical plexus feature encoder and propagate them to the previous and next layer sequence streams;

[0072] The spatially aware sparse Transformer is configured to use a spatially aware attention layer to capture the features of distal information in the MRI layer sequence based on the aggregated features and generate refined features;

[0073] a cervical plexus nerve feature decoder, configured to predict a segmentation result of a cervical plexus nerve region based on the refined features;

[0074] The classification diagnosis module is configured to perform abnormality prediction based on refined features to achieve binary classification of abnormal or normal cervical plexus nerves.

[0075] A third object of the present invention is to provide an electronic device, characterized in that it includes a memory and a processor;

[0076] The memory is used to store computer programs;

[0077] The processor is configured to implement the automatic detection method for cervical plexus neuropathy as described in any one of the above items when executing the computer program.

[0078] The fourth object of the present invention is to provide a computer-readable storage medium, characterized in that a computer program is stored on the storage medium, and when the computer program is executed by a processor, the automatic detection method for cervical plexus neuropathy as described in any one of the above items is implemented.

[0079] The beneficial effects of the present invention are:

[0080] Based on cervical MRI image input, this method accurately segments the cervical plexus region, enabling automatic detection of cervical plexus lesions. It utilizes a cervical plexus estimation module and a bidirectional feature propagation module to precisely locate the cervical plexus nerves. Furthermore, it utilizes a spatially aware sparse Transformer to accurately extract cervical plexus nerve features. Through extensive validation and expanded application scenarios, the method for automatic cervical plexus lesion detection provided by this invention has demonstrated strong robustness and good generalization capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0082] Figure 1 A schematic diagram of the basic flow of a method for automatic detection of cervical plexus lesions based on spatially aware sparse Transformer provided in one embodiment of the present invention.

[0083] Figure 2 A schematic diagram of the overall structure of a method for automatic detection of cervical plexus lesions based on spatially aware sparse Transformer provided in one embodiment of the present invention.

[0084] Figure 3 A schematic structural diagram of a bidirectional feature propagation module provided in one embodiment of the present invention.

[0085] Figure 4 A schematic structural diagram of a feature-aware alignment module provided in one embodiment of the present invention.

[0086] Figure 5 A schematic diagram of the structure of a spatially aware sparse Transformer provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0087] To make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0088] Example 1:

[0089] This embodiment provides a method for automatically detecting cervical plexus neuropathy, characterized in that the method includes:

[0090] Step 1: Acquire cervical MRI images and perform preprocessing;

[0091] Step 2: Use the cervical plexus nerve estimation module to process the cervical MRI image, preliminarily locate the cervical plexus nerves, and obtain a rough map containing their location information;

[0092] Step 3: Use the bidirectional feature propagation module to correct the deviation in the process of extracting cervical plexus nerve position information and improve the ability to aggregate information from MRI sequences;

[0093] The bidirectional feature propagation module uses the feature-aware alignment module to generate aggregated features based on the cervical plexus feature encoder and propagate them to the previous and next layer sequence streams;

[0094] Step 4: Achieve high performance based on spatially aware sparse Transformer while exploiting distal information in MRI sequences;

[0095] The spatially aware sparse Transformer uses a spatially aware attention layer to capture the features of distal information in the MRI layer sequence based on aggregated features and generate refined features;

[0096] Step 5: Use the cervical plexus feature decoder to predict the segmentation result of the cervical plexus region based on the refined features;

[0097] Step 6: Use the classification diagnosis module to perform abnormality prediction based on refined features to achieve binary classification of cervical plexus nerve abnormality or normality.

[0098] Example 2:

[0099] This embodiment provides a method for automatically detecting cervical plexus neuropathy. Figure 1-Figure 5 , also introduced in detail the training process of different module neural networks, the specific implementation process is as follows:

[0100] Step 1: Obtain MRI images of the neck.

[0101] Step 11: All patients underwent cervical plexus screening MRI using a 3.0T MRI device (Siemens MAGNETOM Skyra) to obtain 3D STIR SPACE coronal images in DICOM format. The detailed parameters are as follows:

[0102] TR = 3000 ms, TE = 272 ms, TI = 230 ms, matrix = 211x384, slice thickness = 1.3 mm, slice spacing = 0, voxel size = 0.5x0.5x1.3 mm, echo interval = 4.07 ms, parallel acquisition acceleration factor = 2, phase encoding direction is head-foot direction, number of scanning layers is 56, and the scanning range is from the posterior edge of the vertebral body to the anterior edge of the vertebral body, including the entire course of the cervicobrachial plexus on both sides and the shoulder joint.

[0103] Step 12: Construct training and test sets based on each 2D image layer of the 3D cervical MRI. Load the training set images into ITK-SNAP software to annotate the cervical plexus regions, which will serve as labels for subsequent segmentation network training. All pixels within the region of interest (RoI) are set to 1, and all pixels outside the RoI are set to 0, resulting in a binary brightfield mask image.

[0104] Step 13: Perform spatial interpolation, windowing enhancement and histogram equalization preprocessing on the neck MRI image.

[0105] Step 2: Use the cervical plexus nerve estimation module to process the cervical MRI image to preliminarily locate the position information of the cervical plexus nerve, which specifically includes the following steps:

[0106] Step 21: Average pooling is performed on each layer of the 2D image of the 3D neck MRI to obtain a downsampled 3D neck MRI layer sequence.

[0107] Step 22: According to Using the Opencv package in Python, estimate the forward sequence flow and backward sequence flow

[0108] Step 23: Cervical plexus estimation module is based on and Generate unnormalized coarse images for each layer sequence

[0109]

[0110] A t =1-B t

[0111] Among them, O 1→0 =0,O T→T+1 = 0, i and t represent the channel and step length of laminar flow respectively, A t It's B t The refined image obtained after normalization operation can realize the preliminary positioning of the cervical plexus nerve position information.

[0112] Step 3: Use the bidirectional feature propagation module to correct the deviation in the process of extracting cervical plexus nerve position information and improve the ability to aggregate information from MRI sequences. Specifically, it includes the following:

[0113] Step 31: Input each layer of 2D image of the 3D neck MRI into the cervical plexus nerve feature encoder to obtain features of four different scales;

[0114] The cervical plexus feature encoder consists of four sublayers, each of which contains a feedforward neural network (FFN). Each sublayer is followed by a residual connection and layer normalization. The FFN consists of a convolutional block (Conv1×1), an activation function (GELU) (Gaussian Error Linear Unit), and a deformable convolution block (DConv3×3).

[0115] The activation function GELU is defined as follows:

[0116]

[0117] where Φ(x) is the cumulative distribution function of the standard normal distribution and erf(·) is the error function.

[0118] The deformable convolution block DConv is defined as follows:

[0119]

[0120] Where F(x,y) represents the input feature map, F(x,y) represents the deformation feature map, K represents the total number of sampling points, k enumerates the sampling points, and w k represents the learnable weight of the kth sampling point, (x+Δx k ,y+Δy k ) represents the offset coordinates of the sampling point.

[0121] Step 32: The bidirectional feature propagation module uses the Feature-aware Alignment Module (FAM) to generate aggregated features F and propagate them to the previous and next layers. FAM selectively integrates information from the fine map guided by the coarse map to align features in adjacent layers to accurately locate the cervical plexus in the current layer, avoiding interference from features in unrelated regions of adjacent layers during bidirectional feature propagation.

[0122] like Figure 3As shown in the figure, the bidirectional feature propagation module corresponds to different propagation branches based on the different level features extracted by the encoder, ensuring the effective transmission and fusion of cervical plexus nerve position information between different levels. Assuming that the current layer sequence is the tth layer, in the forward propagation process, for the jth propagation branch, the aggregated features of the current layer sequence are It can be obtained by:

[0123]

[0124] in, represents the aggregated features of the t-th layer sequence of the j-1th branch, and Represent the features generated by the previous layer and the first two layers of sequences, O t→t-1 Represents the sequence flow from the previous layer to the current layer, O t→t-2 Represents the sequence flow from the first two layers to the current layer, W represents the reverse registration operation, and A t-1 and A t-2 Representing the fine graphs of the previous layer and the first two layers of sequence, respectively. The above process continues sequentially along the layer sequence until t = T. The backward propagation process is similar to the forward propagation process, but in the opposite direction. Through forward and backward propagation, the model can acquire information from different sequence flow directions, reducing information loss or inaccuracy that may occur due to unidirectional propagation, and improving the accuracy and completeness of feature propagation.

[0125] The structure of the FAM module is as follows Figure 4 As shown, first, respectively and O t→t-1 and O t→t-2 , registration features and and A t-1 and A t-2 Splicing; then, use the ordinary convolution layer and the deformable convolution layer to splice the features and Perform multi-level processing and extraction to generate the final aligned current layer sequence aggregate features Among them, the fine map serves as the basic mask of the deformable convolution layer and is introduced into the deformable convolution layer as an additional condition to generate the offset and mask, ensuring that only the precise positioning information of the cervical plexus nerves is effectively propagated and utilized during the convolution process, thereby improving the accuracy of feature alignment.

[0126] Step 4: Achieve high performance based on spatially aware sparse Transformer while exploiting distal information in MRI sequences.

[0127] The spatially aware sparse Transformer module filters out the features of irrelevant regions in the layer sequence based on the coarse image B, and uses the spatially aware attention layer to capture the features of the distal information of the MRI layer sequence based on F to generate refined features.

[0128] Step 41: Spatially Aware Sparse Transformer Figure 5 As shown, given the final aggregated features obtained in step 3 A soft partitioning operation is used to partition each aggregated feature into overlapping blocks of size p×p with a partitioning step of s.

[0129] Step 42: Concatenate the segmented features to generate block embedding

[0130] Step 43: Downsample the coarse image B by average pooling with a window size of p×p and a step size of s to obtain

[0131] Step 44: The generated block embedding z is transformed through three separate linear layers to obtain and Where M and N represent the number of blocks divided in the height and width domain values respectively, and C z Represents the abbreviation p 2 C represents the number of channels.

[0132] Step 45: Divided into m×n non-overlapping windows to generate partition features where m×n and h×w are the number and size of windows respectively.

[0133] Step 46: Pool the global vector g using the block embedding z and depth-wise convolution (DC) k and g v Generated by:

[0134] g k =l k (DC(z))

[0135] g v =l v (DC(z))

[0136] Among them, l k and l v represents a linear layer,

[0137] Next, g k Repeat until G k , gv Repeat until G v , respectively

[0138] Step 47: Perform a sparse operation on the distal sequence to ensure that the spatial perception attention is focused only on the cervical plexus region. First, perform a maximum pooling operation on the distal sequence. Downsampling to generate a rough window image Then, the distal sparse mask of the window is obtained as follows:

[0139]

[0140] Among them, U t,i,j represents the coarse image at window (i, j) of the t-th layer sequence, θ is the threshold for considering the relevant window as the window where the coarse image is located, Q t Each element Q in t,i,j It is a binary variable used to determine whether the window is the window where the rough image is located. For E q 、E k and E v The distal sparse mask of The clipping function Clip sets S to l; then, the distal sparse embedding feature I is generated using the following method q , I k and I v :

[0141]

[0142] Concat represents the concatenation operation; if S i,j = 0, indicating that the window position indexed by i, j in the layer sequence does not contain the coarse image, and this window position is excluded; and where m s and n s Represents the number of selected windows within the domain values of m and n respectively.

[0143] Step 48: In the layer sequence domain, select the window where the rough image is located as the query space to ensure that the spatial perception attention is only focused on the cervical plexus area; given the distal sparse embedding feature I q , spatially sparse embedding y q Generates the following:

[0144]

[0145] y q =Concat(H q )

[0146] in Top(K q ,·) means finding the Kth q Operations on large elements; for I q For each window located at i,j in the layer sequence domain, we selectively select the K windows that contain the highest proportion of coarse images. q windows; specifically, in the query space, the top 50% of features are selected and flattened for each query window.

[0147] Step 49: In contrast to the query space, the key / value space selects distal sparse embedding features I k ,I v The fine area containing the cervical plexus; given I k and I v , spatial sparse embedding feature y k and y v Generates the following:

[0148]

[0149] y k =Concat(H k )

[0150]

[0151] y v =Concat(H v )

[0152] in Specifically, in the key / value space, the top 50% of features are selected and a flattening operation is performed on each key / value window.

[0153] Step 410: Spatially sparse query embedding y q Reshaped into Similarly, the spatially sparse key / value embedding y k and y v Reshaped into and For m s n s For each window in , the self-attention is calculated as follows:

[0154]

[0155] Introducing Multi-head Self-Attention (MSA) into the spatially aware sparse Transformer to obtain output embedding

[0156] z s =MSA(Yq ,Y k ,Y v )

[0157] Step 411: Due to the high similarity in texture between adjacent layer sequences, in each spatially-aware sparse Transformer, the layer sequences are selected alternately with a step size of 2; in the spatially-aware sparse Transformer module composed of multiple spatially-aware sparse Transformers, the odd-numbered spatially-aware sparse Transformers select the odd-numbered layer sequences, while the even-numbered spatially-aware sparse Transformers select the even-numbered layer sequences, thereby utilizing the information between the layer sequences while reducing redundant calculations and reducing the size of the key / value space by 50%.

[0158] After applying the sparse strategy to eliminate unnecessary and redundant windows, the self-attention layer is used to extract fusion features for the remaining windows. In particular, for unselected windows (those with a low proportion of coarse images), a comprehensive attention calculation is performed on the features within the entire window, and then the features are restored to their original size through interpolation. Subsequently, these features are aggregated through a soft combination operation and serve as the input of the next spatially aware sparse Transformer module. The output of the final spatially aware sparse Transformer is represented as

[0159] Step 5: The feature decoder of the cervical plexus nerve is input into the decoder. The feature decoder adopts a U-net-like structure, combines the multi-scale features of the feature encoder, forms a feature map through channel fusion and upsampling, and finally restores it to a mask map. The upsampling rate in the four sub-layers is 2, and there is a residual connection after each sub-layer.

[0160] Step 6: The input classification diagnosis module includes a normalization layer, a global pooling layer, and a fully connected layer, which are used to achieve binary classification of abnormal or normal cervical plexus nerves.

[0161] Step 7: Use the training sample set to train the automatic detection model for cervical plexus neuropathy. The specific formula of the training loss function L is as follows:

[0162]

[0163] Among them, S(·) refers to the Softmax function; N represents the number of samples, that is, the number of pixels in each image; C represents the number of categories, is the predicted pixel of category k, for An example of is the mask pixel of category k, which is a C×1 one-hot encoding vector, that is, the value of the position corresponding to the label is 1, and the others are 0; w k Represents the loss weight of category k; adjustment parameter α=[α 1 ,α 1 ,...,α k ], where α k represents the most critical noise weight of the kth class; s k represents the total number of pixels of category k in all images in the training set, represents the total number of pixels in all images from the training set; N(0,σ 2 ) has a mean of 0 and a variance of σ 2 Gaussian noise.

[0164] Step 8: Input the unlabeled cervical MRI images in the test sample set into the trained cervical plexus nerve lesion detection model, and output the segmentation mask of the cervical plexus nerve area predicted by the model and the lesion prediction results.

[0165] Example 3:

[0166] This embodiment provides an automatic detection system for cervical plexus neuropathy, which is applied to the automatic detection method for cervical plexus neuropathy of the first or second embodiment, including:

[0167] The image acquisition module is configured to acquire MRI images of the neck and implement labeling of the cervical plexus nerve area.

[0168] The cervical plexus nerve estimation module is configured to process the cervical MRI image, preliminarily locate the cervical plexus nerves, and obtain a rough map containing the position information of the cervical plexus nerves.

[0169] The bidirectional feature propagation module is configured to use the feature-aware alignment module to generate aggregated features based on the cervical plexus feature encoder and propagate them to the previous and next layer sequence flows.

[0170] The spatially aware sparse Transformer is configured to use a spatially aware attention layer to capture the features of distal information of the MRI layer sequence based on the aggregated features and generate refined features.

[0171] The cervical plexus nerve feature decoder is configured to predict a segmentation result of the cervical plexus nerve region based on the refined features.

[0172] The classification diagnosis module is configured to perform abnormality prediction based on refined features to achieve binary classification of abnormal or normal cervical plexus nerves.

[0173] Example 4:

[0174] In order to verify and illustrate the technical effect of the method of the present invention, this example compares the manual and traditional clinical model evaluation methods with the method of the present invention to verify the actual effect of the method.

[0175] The traditional clinical model evaluation method screens out clinical predictive factors by performing univariate and multivariate logistic regression analysis on patients' clinical data, and constructs single logistic regression and nested logistic regression prediction models based on these factors.

[0176] The manual assessment method detected potential cervical plexopathy by instructing five radiologists with more than 10 years of radiology experience to independently review neck MRI images (the entire range of slices for each patient); the window level and width could be freely adjusted, but the radiologists were blinded to any other clinical and radiological information; if at least one slice was considered to have cervical plexopathy, the case was diagnosed with cervical plexopathy.

[0177] The comparison results of the method of the present invention with manual and traditional clinical model evaluation methods are shown in Table 1 below:

[0178] Table 1: Comparison results between the present invention and traditional solutions

[0179]

[0180] From the above comparison data, it can be seen that the method of the present invention is superior to the manual and traditional clinical model evaluation methods in accuracy and efficiency. The traditional clinical model evaluation method is only applicable to specific images and cannot be promoted on a large scale. The manual evaluation method and the method of the present invention have a wide range of applications, but the manual evaluation method is inferior to the method of the present invention in other data. The comparison results show that the method of the present invention can quickly, efficiently, accurately and automatically detect potential cervical plexus neuropathy.

[0181] Some steps in the embodiments of the present invention may be implemented using software, and the corresponding software program may be stored in a readable storage medium, such as a CD or a hard disk.

[0182] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for automatically detecting cervical plexus neuropathy, characterized in that: The method comprises: Step 1: Acquire cervical MRI images and perform preprocessing; Step 2: Use the cervical plexus nerve estimation module to process the cervical MRI image, preliminarily locate the cervical plexus nerves, and obtain a rough map containing their location information; Step 3: Use the bidirectional feature propagation module to correct the deviation in the process of extracting cervical plexus nerve position information and improve the ability to aggregate information from MRI sequences; The bidirectional feature propagation module uses a feature-aware alignment module to generate aggregated features based on the cervical plexus feature encoder and propagates them to the previous and next layer sequence flows; Step 4: Achieve high performance based on spatially aware sparse Transformer while exploiting distal information in MRI sequences; The spatially aware sparse Transformer uses a spatially aware attention layer to capture the features of distal information of the MRI layer sequence based on aggregated features and generate refined features; Step 5: Use the cervical plexus feature decoder to predict the segmentation result of the cervical plexus region based on the refined features; Step 6: Use the classification diagnosis module to predict abnormalities based on refined features and achieve binary classification of abnormal or normal cervical plexus nerves; The step 2 includes: Step 21: Average pooling is performed on each layer of the 2D image of the 3D neck MRI image to obtain a downsampled 3D neck MRI layer sequence. Step 22: According to Estimating forward sequence flow using the Opencv package in Python and backward sequence flow Step 23: Based on the forward sequence flow and backward sequence flow The cervical plexus estimation module generates a non-normalized coarse map for each layer sequence A t =1-B t Among them, O 1→0 =0,O T→T+1 = 0, i and t represent the channel and step length of laminar flow respectively, A t It's B t The refined image obtained by normalization operation can achieve the preliminary positioning of the cervical plexus nerve position information; The step 3 includes: Step 31: Input each layer of the 2D image of the 3D cervical MRI image into the cervical plexus nerve feature encoder to obtain features of different scales, and the bidirectional feature propagation module corresponds to different propagation branches based on the different levels of features extracted by the encoder; Step 32: Assuming that the current layer sequence is the tth layer, during the forward propagation process, for the jth propagation branch, the aggregated features of the current layer sequence Obtained by: Among them, FAM stands for Feature-Aware Alignment Module, represents the aggregated features of the t-th layer sequence of the j-1th branch, and Represent the features generated by the first layer and the first two layers of sequences, O t→t-1 Represents the sequence flow from the previous layer to the current layer, O t→t-2 Represents the sequence flow from the first two layers to the current layer, W represents the reverse registration operation, and A t-1 and A t-2 Represent the fine graphs of the previous layer and the first two layers of sequence respectively; The above process proceeds in sequence according to the layer sequence until t = T; The backward propagation process is similar to the forward propagation process, but in the opposite direction.

2. The automatic detection method for cervical plexus neuropathy according to claim 1, characterized in that: The cervical plexus nerve feature encoder includes four sublayers, each sublayer includes a feedforward neural network, and residual connection and layer normalization are applied after each sublayer; the feedforward neural network includes a convolution block Conv1×1, an activation function GELU and a deformable convolution block DConv connected in sequence.

3. The automatic detection method for cervical plexus neuropathy according to claim 2, characterized in that: The activation function GELU is defined as follows: where Φ(x) is the cumulative distribution function of the standard normal distribution and erf(·) is the error function.

4. The automatic detection method for cervical plexus neuropathy according to claim 2, characterized in that: The deformable convolution block DConv is defined as follows: Where F(x+Δx k ,y+Δy k ) represents the input feature map, represents the deformation feature map, K represents the total number of sampling points, k represents the enumeration sampling point, w k represents the learnable weight of the kth sampling point, (x+Δx k ,y+Δy k ) represents the offset coordinates of the sampling point.

5. An automatic detection system for cervical plexus neuropathy, characterized in that: The system is applied to the automatic detection method for cervical plexus neuropathy according to any one of claims 1 to 4, and the system comprises: an image acquisition module configured to acquire a neck MRI image; a cervical plexus nerve estimation module, configured to process the cervical MRI image, preliminarily locate the cervical plexus nerves, and obtain a rough map containing their position information; The bidirectional feature propagation module is configured to use the feature-aware alignment module to generate aggregated features based on the cervical plexus feature encoder and propagate them to the previous and next layer sequence streams; The spatially aware sparse Transformer is configured to use a spatially aware attention layer to capture the features of distal information in the MRI layer sequence based on the aggregated features and generate refined features; a cervical plexus nerve feature decoder, configured to predict a segmentation result of a cervical plexus nerve region based on the refined features; The classification diagnosis module is configured to perform abnormality prediction based on refined features to achieve binary classification of abnormal or normal cervical plexus nerves.

6. An electronic device, characterized in that: including memory and processor; The memory is used to store computer programs; The processor is configured to implement the method for automatically detecting cervical plexus lesions according to any one of claims 1 to 4 when executing the computer program.

7. A computer-readable storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed by the processor, the automatic detection method for cervical plexus neuropathy according to any one of claims 1 to 4 is implemented.

Images