Detection method, device and equipment based on lumbar vertebra region in MRI (Magnetic Resonance Imaging) image

Abstract

The embodiment of the invention discloses a detection method, device and equipment based on a lumbar vertebra region in an MRI image, and the method comprises the steps: firstly obtaining a lumbar vertebra MRI image data set of a to-be-detected patient, inputting the obtained MRI image data set into a YOLOv5 model, and carrying out the target detection; the YOLOv5 automatically extracts the ROI related to the lumbar vertebra, and generates a feature image data set. And inputting the feature image data set output by the YOLOv5 into the Mix-inresNet model, carrying out deep classification on the feature image data set by the Mix-inresNet model, and outputting a classification result data set. Soft voting processing is carried out on classification results, and classification results of different models are combined. And outputting a final scoring result to assist a doctor to diagnose the lumbar disease. Through automatic image processing and analysis, the time for a doctor to manually check and analyze an image is shortened, and the working efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image detection, and in particular to a detection method, device and equipment based on a lumbar spine region in MRI images. Background Art

[0002] Lumbar disease refers to various diseases and problems that affect the lumbar spine, usually related to the bones, discs, nerves, muscles or ligaments in the lower part of the spine. These diseases may cause low back pain, numbness in the lower limbs, muscle weakness or other symptoms. Lumbar disease includes: lumbar disc herniation, lumbar spinal stenosis, lumbar degeneration, lumbar spondylolisthesis, scoliosis and lumbar muscle strain.

[0003] When diagnosing lumbar spine diseases, imaging examinations are often performed first, using X-rays, magnetic resonance imaging (MRI), CT scans, bone scans, etc. to obtain imaging images of the lumbar spine. The doctor then uses the medical imaging images to diagnose whether the lumbar spine has a disease.

[0004] As for MRI, it can show soft tissue structures in detail, such as intervertebral discs, spinal cord, nerve roots and surrounding ligaments. After the doctor gets the MRI (magnetic resonance imaging) results of the lumbar spine, he will conduct a detailed analysis and diagnosis based on the specific manifestations of the image.

[0005] Doctors often evaluate the lumbar discs, nerve roots, etc. in the lumbar spine MRI to determine lumbar disease.

[0006] With the development of image recognition technology, some image technologies will be used to segment medical images to obtain clearer medical images and help doctors better view and analyze lumbar images. However, existing image recognition analysis only uses target detection to extract features from lumbar images, resulting in poor accuracy and susceptibility to noise interference, making it difficult for doctors to diagnose the condition. Summary of the invention

[0007] Based on this, it is necessary to propose a detection method, device and equipment based on the lumbar spine area in MRI images to address the above problems.

[0008] A method for detecting a lumbar region based on an MRI image, the method comprising:

[0009] Acquire an MRI image dataset of the lumbar spine of a patient to be tested;

[0010] Constructing a YOLOv5 model, inputting the lumbar MRI image dataset into the YOLOv5 model to obtain a feature image dataset;

[0011] Constructing a Mix-inresNet model, inputting the feature image data set into the Mix-inresNet model, and the Mix-inresNet model outputs a classification result data set;

[0012] The Mix-inresNet model performs soft voting on the classification result dataset and outputs the scoring results to assist doctors in lumbar spine examinations.

[0013] In at least one embodiment of the present application, the step of constructing a YOLOv5 model, inputting the lumbar MRI image dataset into the YOLOv5 model, and obtaining a feature image dataset comprises:

[0014] The YOLOv5 model extracts the features of the central spinal canal, lateral recess, neural foramen, and intervertebral disc from the MRI image dataset of the lumbar spine to obtain the feature image dataset, wherein the feature image dataset includes: each detected ROI bounding box in the MRI image dataset of the lumbar spine, a classification result dataset, a ROI image, and a confidence score.

[0015] In at least one embodiment of the present application, the steps of constructing a Mix-inresNet model, inputting the feature image dataset into the Mix-inresNet model, and the Mix-inresNet model outputting a classification result dataset include:

[0016] The ROI image is input into the Mix-inresNet model, and the Mix-inresNet model classifies the ROI image into normal, mild, moderate, and severe categories to obtain a classified result data set.

[0017] In at least one embodiment of the present application, the method further includes:

[0018] The MRI images of the lumbar spine of the patient to be tested are labeled to obtain a labeled data set.

[0019] In at least one embodiment of the present application, the step of constructing a Mix-inresNet model, inputting the feature image dataset into the Mix-inresNet model, and the Mix-inresNet model outputting a classification result dataset further includes:

[0020] Construct the training set, validation set, and test set of the Mix-inresNet model, and divide the images and labels of the original dataset into the training set, validation set, and test set in a ratio of 8:1:1, so that the training set accounts for 80% of the total dataset, and the validation set and test set each account for 10% of the total dataset.

[0021] In at least one embodiment of the present application, the Mix-inresNet model includes a backbone network module, which integrates a mixed convolutional layer, an average pooling layer, a dropout layer, and a softmax layer;

[0022] The hybrid convolutional layers include: depthwise separable convolution, dilated convolution, and standard convolution;

[0023] The backbone network module performs multi-scale processing and parallel processing on the hybrid convolution layer, average pooling layer, and dimensionality reduction module to obtain the ROI image features after parallel processing.

[0024] In at least one embodiment of the present application, the detection method based on the lumbar region in the MRI image further includes:

[0025] The Mix-inresNet model also includes a self-attention module, which is before the average pooling layer;

[0026] The output of the self-attention module is calculated as follows:

[0027] F g ∈R(C′×H×W)F h ∈R(C′×H×W)F g F h G∈R(C′×N)H∈R(C′×N)N=H×WO∈R(C′×N);

[0028] O = softmax((G T )*H / sqrt(d))*H;

[0029] Get the final feature map.

[0030] In at least one embodiment of the present application, the detection method based on the lumbar region in the MRI image further includes:

[0031] Receive the result correction data of the external input Mix-inresNet model to train the Mix-inresNet model.

[0032] A detection device based on the lumbar region in an MRI image, applied to any one of the above-mentioned detection methods based on the lumbar region in an MRI image, the detection device based on the lumbar region in an MRI image comprising:

[0033] A data acquisition module, used to acquire an MRI image data set of the lumbar spine of a patient to be tested;

[0034] YOLOv5 model, used for feature extraction of lumbar spine MRI image dataset;

[0035] Mix-inresNet model, which processes feature image datasets and outputs scoring results;

[0036] The detection device based on the lumbar region in the MRI image performs the following steps:

[0037] Acquire an MRI image dataset of the lumbar spine of a patient to be tested;

[0038] Constructing a YOLOv5 model, inputting the lumbar MRI image dataset into the YOLOv5 model to obtain a feature image dataset;

[0039] Constructing a Mix-inresNet model, inputting the feature image data set into the Mix-inresNet model, and the Mix-inresNet model outputs a classification result data set;

[0040] The Mix-inresNet model performs soft voting on the classification result dataset and outputs the scoring results to assist doctors in lumbar spine examinations.

[0041] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the following steps:

[0042] Acquire an MRI image dataset of the lumbar spine of a patient to be tested;

[0043] Constructing a YOLOv5 model, inputting the lumbar MRI image dataset into the YOLOv5 model to obtain a feature image dataset;

[0044] Constructing a Mix-inresNet model, inputting the feature image data set into the Mix-inresNet model, and the Mix-inresNet model outputs a classification result data set;

[0045] The Mix-inresNet model performs soft voting on the classification result dataset and outputs the scoring results to assist doctors in lumbar spine examinations.

[0046] Implementing the embodiments of the present invention will have the following beneficial effects:

[0047] The detection method, device and equipment based on the lumbar region in MRI images in this embodiment first obtains the lumbar MRI image dataset of the patient to be detected, and inputs the obtained MRI image dataset into the YOLOv5 model for target detection. YOLOv5 automatically extracts the ROI related to the lumbar spine and generates a feature image dataset. The feature image dataset output by YOLOv5 is input into the Mix-inresNet model, and the Mix-inresNet model performs in-depth classification of the feature image dataset and outputs the classification result dataset. The classification results are soft-voted and combined with the classification results of different models. The final scoring results are output to assist doctors in diagnosing lumbar diseases. Through automated image processing and analysis, the time for doctors to manually view and analyze images is reduced, thereby improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative work.

[0049] in:

[0050] Figure 1 is a flow chart of a method for detecting a lumbar region based on MRI images in one embodiment;

[0051] Figure 2 is another flow chart of a method for detecting a lumbar region based on MRI images in one embodiment;

[0052] Figure 3 is another flow chart of a method for detecting a lumbar region based on MRI images in an embodiment;

[0053] Figure 4 A full flow chart of a detection method for the lumbar region based on MRI images in one embodiment;

[0054] Figure 5 is a structural block diagram of a detection device based on the lumbar region in MRI images in one embodiment;

[0055] Figure 6 is a structural block diagram of a computer device in one embodiment;

[0056] Figure 7 It is the MRI characteristic image in the scoring result.

[0057] 200. A detection device for the lumbar region in MRI images; 210. A data acquisition module; 220. A YOLOv5 model; 230. A Mix-inresNet model. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] A method for detecting a lumbar region based on an MRI image, the method comprising:

[0060] S101, obtaining an MRI image dataset of the lumbar spine of a patient to be tested;

[0061] S102, constructing a YOLOv5 model, inputting the lumbar MRI image dataset into the YOLOv5 model, and obtaining a feature image dataset;

[0062] S103, constructing a Mix-inresNet model, inputting the feature image data set into the Mix-inresNet model, and the Mix-inresNet model outputs a classification result data set;

[0063] S104, Mix-inresNet model and soft voting on the classification result data set, output scoring results to assist doctors in lumbar spine examination.

[0064] Please refer to Figure 1-4 In this embodiment, first, a lumbar MRI image dataset of the patient to be detected is obtained, and the obtained MRI image dataset is input into the YOLOv5 model for target detection.

[0065] YOLOv5 automatically extracts lumbar spine-related ROIs and generates feature image datasets.

[0066] Input the feature image dataset output by YOLOv5 into the Mix-inresNet model.

[0067] The Mix-inresNet model performs in-depth classification of feature image datasets and outputs classification result datasets.

[0068] The classification results are soft-voted and the classification results of different models are combined.

[0069] Output the final scoring results to assist doctors in diagnosing lumbar diseases.

[0070] Through automated image processing and analysis, the time doctors spend manually reviewing and analyzing images is reduced, thus improving work efficiency.

[0071] The combination of YOLOv5 and Mix-inresNet models can improve the recognition rate of lumbar diseases and reduce the probability of misdiagnosis and missed diagnosis.

[0072] The scoring results and classification information provided can help doctors make better decisions, especially in complex cases, and provide valuable reference information.

[0073] It should be noted that, first, an MRI image dataset taken of a patient is obtained, and the MRI image dataset is an MRI image of the lumbar region.

[0074] A Yolov5 model is constructed, and the MRI image dataset of the lumbar spine is input into the Yolov5 model to obtain a feature image dataset.

[0075] The Yolov5 model output includes the features of each region of interest (ROI) in the MRI image, specifically: the bounding box of the detected ROI, the classification result for each ROI, the confidence score and the feature image.

[0076] Next, the feature image dataset extracted by YOLOv5 is input into the Mix-inresNet model for further processing.

[0077] The Mix-inresNet model adopts a mixed convolution method (depthwise separable convolution, dilated convolution, and standard convolution) and enhances feature extraction through a self-attention mechanism.

[0078] The Mix-inresNet model classifies each ROI image and outputs the classification results.

[0079] Through deeper learning, the Mix-inresNet model is able to classify the detected ROIs in detail, helping doctors quickly identify the severity of the lesions (normal, mild, moderate, severe).

[0080] The classification results of different models are combined and the weighted average method is used to improve the classification accuracy.

[0081] Finally, the scoring results of each detected ROI are output to assist doctors in making clinical judgments.

[0082] Through the soft voting mechanism, the possible deviation of a single model can be reduced, the reliability of the overall diagnosis can be improved, and the decision-making efficiency of doctors in the diagnosis of lumbar diseases can be improved.

[0083] The scoring results include MRI characteristic images, corresponding scores and levels.

[0084] According to the feature proportion of the lesion characteristics, the classification result data set includes normal ROI images, mild ROI images, moderate ROI images and severe ROI images, so as to assist doctors in making judgments on the disease and remind doctors of the image information that needs attention, so as to assist doctors in making quick judgments on the lumbar MRI images of the patients to be tested.

[0085] In at least one embodiment of the present application, the step of constructing a YOLOv5 model, inputting the lumbar MRI image dataset into the YOLOv5 model, and obtaining a feature image dataset comprises:

[0086] S201, the YOLOv5 model extracts the features of the central spinal canal, lateral recess, neural foramen and intervertebral disc of the lumbar MRI image dataset to obtain the feature image dataset, wherein the feature image dataset includes: each detected ROI bounding box in the lumbar MRI image dataset, the classification result dataset, the ROI image and the confidence score.

[0087] In this embodiment, the YOLOv5 model processes the input MRI image through a convolutional neural network to automatically detect multiple feature areas in the image, including the central spinal canal, lateral recess, neural foramen, and intervertebral disc.

[0088] The YOLOv5 model identifies the bounding box of each ROI based on the learned features and generates the corresponding classification label and confidence score.

[0089] The detected ROI bounding box, classification results, ROI image and confidence score are integrated into a feature image dataset for subsequent analysis.

[0090] The YOLOv5 model is used to automatically detect targets in lumbar MRI images, significantly reducing the workload of doctors in manually reviewing images and improving efficiency.

[0091] Using the YOLOv5 target detection algorithm, key lumbar structural features can be more accurately identified and located, reducing the possibility of misdiagnosis and missed diagnosis.

[0092] The YOLOv5 model has a faster detection speed and is suitable for real-time or near real-time clinical applications, which improves work efficiency.

[0093] The output feature image dataset contains not only the bounding box and classification information of the ROI, but also the corresponding confidence score, which helps doctors make more scientific diagnostic decisions.

[0094] The generated ROI images and classification results provide a basis for subsequent in-depth analysis, and the Mix-inresNet model can be further used for refined classification or more complex analysis.

[0095] It should be further noted that in the detection method based on the lumbar spine region in MRI images, all standard MRI sequences were acquired using fractional readout fast spin echo (frFSE) sequences, and the output images were formatted with a uniform resolution of 512x512 pixels. The routine clinical lumbar spine MRI imaging study was performed using a Signa HDx 1.5T scanner (GE Healthcare).

[0096] In parallel, routine clinical lumbar spine MRI imaging studies were performed on the external test set using an Optima MR360 1.5T scanner (GE Healthcare).

[0097] When training the YOLOv5 model, professionals first annotated the lumbar MRI images to mark the ROI images. The annotating method was to mark the central canal and lateral recess along the axial T2 MRI, the neural foramen along the sagittal T1 MRI, and the lumbar intervertebral disc along the sagittal T2 MRI. Then, professional clinicians graded the annotated data sets to train the YOLOv5 model and the Mix-inresNet model.

[0098] In at least one embodiment of the present application, the steps of constructing a Mix-inresNet model, inputting the feature image dataset into the Mix-inresNet model, and the Mix-inresNet model outputting a classification result dataset include:

[0099] S301. Input the ROI image into the Mix-inresNet model. The Mix-inresNet model classifies the ROI image into normal, mild, moderate and severe categories to obtain a classified result data set.

[0100] Please refer to Figure 1-4 ,In this implementation, first, a Mix-inresNet model is constructed and ,configured to integrate multiple convolutional layer structures to improve the ,feature extraction and classification capabilities of ROI images.

[0101] Input the ROI image in the feature image dataset extracted by the YOLOv5 model into the Mix-inresNet model, ensuring that the format and size of the image meet the model requirements.

[0102] The Mix-inresNet model performs forward propagation on the input ROI image and extracts deep features through multi-layer convolution and pooling operations.

[0103] Applying activation functions such as ReLU introduces non-linearity, enabling the model to learn complex feature representations.

[0104] In the output layer, the feature map is converted into category probability through the Softmax function, and the category of each ROI (normal, mild, moderate, severe) is finally determined.

[0105] The Mix-inresNet model outputs a classification result dataset, which contains the classification label of each ROI image for subsequent analysis and clinical reference.

[0106] The Mix-inresNet model uses a variety of convolutional structures and deep learning algorithms to more accurately classify ROIs in lumbar MRI images, thereby improving the accuracy of classification.

[0107] The automated classification process significantly increases processing speed and reduces the time doctors spend manually analyzing images, thereby improving work efficiency.

[0108] The model can subdivide the classification results into normal, mild, moderate and severe according to the severity of the disease, providing richer information to help doctors formulate treatment plans.

[0109] By generating a classification result dataset, the Mix-inresNet model provides doctors with a reliable basis and enhances the confidence and accuracy of clinical diagnosis.

[0110] The feature image dataset extracted by YOLOv5 is input into the Mix-inresNet model, which effectively utilizes the previous detection results and improves the efficiency of the overall diagnosis process.

[0111] It should be noted that this detection method based on the lumbar spine area in MRI images uses a soft voting method to integrate the lumbar spine image scoring results of a single patient, and uses NLG technology to convert the results into a detailed reference report to assist doctors in making judgments on the patient's lumbar spine.

[0112] In at least one embodiment of the present application, the method further includes:

[0113] The MRI images of the lumbar spine of the patient to be tested are annotated to obtain a lumbar spine MRI image dataset.

[0114] Please refer to Figure 1-4 In this embodiment, MRI images of the lumbar spine are collected from the patient to be tested.

[0115] Use medical image annotation tools to annotate the collected MRI images. The specific steps include:

[0116] Doctors identify and label key structures in each MRI image.

[0117] Draw a bounding box for each marked region and assign a corresponding classification label.

[0118] Organize the labeled images into a dataset, ensuring that each image has its corresponding bounding box and classification label for subsequent training, validation, and testing of the model.

[0119] Provide high-quality training data for subsequent deep learning models (such as YOLOv5, Mix-inresNet, etc.) to ensure that the model can effectively learn and identify different categories of lumbar diseases.

[0120] It should be noted that the lumbar spine MRI image dataset includes bounding boxes and classification labels (central spinal canal, lateral recess, neural foramen, and intervertebral disc).

[0121] In at least one embodiment of the present application, the step of constructing a Mix-inresNet model, inputting the feature image dataset into the Mix-inresNet model, and the Mix-inresNet model outputting a classification result dataset further includes:

[0122] Construct the training set, validation set, and test set of the Mix-inresNet model, and divide the images and labels of the original dataset into the training set, validation set, and test set in a ratio of 8:1:1, so that the training set accounts for 80% of the total dataset, and the validation set and test set each account for 10% of the total dataset.

[0123] Please refer to Figure 1-4 ,In this implementation, we start to build a Mix-inresNet model that ,integrates multiple convolutional layers and attention mechanisms to ,optimize image classification capabilities.

[0124] The feature image dataset extracted by the YOLOv5 model is input into the Mix-inresNet model for feature extraction and classification.

[0125] From the original labeled data set, the data is divided into training set, validation set and test set in a ratio of 8:1:1.

[0126] Make sure each dataset contains images and their corresponding labels to facilitate subsequent model training and evaluation.

[0127] Use the training set to train the Mix-inresNet model and adjust the model parameters.

[0128] After each training cycle, the validation set is used to evaluate the model performance and hyperparameters are adjusted based on the results.

[0129] Use the test set to perform a final evaluation of the model to obtain the model's performance on unseen data and ensure its reliability and effectiveness.

[0130] The Mix-inresNet model improves the classification accuracy of lumbar MRI images and reduces the misdiagnosis rate through learning with high-quality training sets.

[0131] Reasonable division of training, validation, and test sets ensures the evaluation of the model at different stages, promotes the effective adjustment of model parameters, and improves performance.

[0132] By training and evaluating on different datasets, the model can better adapt to new data and improve its reliability in practical applications.

[0133] The output classification results provide doctors with fast and accurate diagnostic information, facilitating the clinical examination and treatment of lumbar diseases.

[0134] It should be noted that the Mix-inresNet model classifies the input ROI image, and the output result dataset includes the classification label of each ROI (such as normal, mild, moderate, and severe).

[0135] The images and labels of the original dataset are divided in a ratio of 8:1:1, as follows:

[0136] Training set (80%): used for model training and parameter tuning.

[0137] Validation set (10%): used to evaluate performance and adjust hyperparameters during model training.

[0138] Test set (10%): used to finally evaluate the generalization ability of the model and test its performance on unseen data.

[0139] In at least one embodiment of the present application, the Mix-inresNet model includes a backbone network module, which integrates a mixed convolutional layer, an average pooling layer, a dropout layer, and a softmax layer;

[0140] The hybrid convolutional layers include: depthwise separable convolution, dilated convolution, and standard convolution;

[0141] The backbone network module performs multi-scale processing and parallel processing on the hybrid convolution layer, average pooling layer, and dimensionality reduction module to obtain the ROI image features after parallel processing.

[0142] Please refer to Figure 1-4 ,In this implementation, a Mix-inresNet model is constructed, the backbone network module is integrated, and the mixed convolutional layer, average pooling layer, Dropout layer and Softmax layer are configured.

[0143] The extracted ROI image is input into the backbone network module for feature processing.

[0144] The input ROI image is convolved to extract various image features through different types of convolutions (depthwise separable, extended, standard).

[0145] The convolutional feature map is downsampled to reduce the spatial dimension of the feature map and extract more representative features.

[0146] A certain proportion of neurons are randomly discarded during the training process to enhance the generalization ability of the model.

[0147] The final feature output is converted into category probability distribution to provide a basis for subsequent classification decisions.

[0148] The ROI image features after multi-scale and parallel processing are obtained for subsequent classification and analysis.

[0149] The hybrid convolution layer combines multiple convolution techniques to effectively extract complex image features and improve classification accuracy.

[0150] Multiple convolution and pooling operations of different scales are performed simultaneously, and the results are connected in parallel. This multi-scale parallel strategy is used to capture and integrate image features of different scales and directions.

[0151] In the feature extraction stage of the backbone network, the Mix-inresNet model adopts a mixed convolution method, integrating depthwise separable convolution, dilated convolution, and standard convolution in parallel connections. The depthwise separable convolution module consists of two layers: depthwise convolution and pointwise convolution. Pointwise convolution is a simple 1×1 convolution used to form a linear combination of the outputs from the depth layer. The depthwise convolution with one filter for each input channel can be expressed as:

[0152] ;

[0153] For depthwise convolution kernels of different sizes, filters are applied to channels in F to produce channels of filtered output feature maps. The main advantage of depthwise separable convolution is that it can significantly reduce the complexity and computational cost of the model.

[0154] A further module of hybrid convolution is dilated convolution, which introduces a dilation factor that enables the convolution kernel to skip input elements when applied, achieving the purpose of detecting larger scale content. Specifically, given a dilation factor, the dilated convolution operation is defined as:

[0155] (F*lk)(p)=∑s+lt=pF(s)k(t);

[0156] F is the input, k is the convolution kernel, and s and t are the sliding variable values ​​during the entire operation.

[0157] Applying dilated convolution can expand the receptive field (also called the receptive field) of the convolutional neural network, enabling the network to perceive a wider range of information to help the model acquire richer environmental information.

[0158] In hybrid convolution, features processed by depthwise separable convolution, unfolded convolution, and standard convolution are combined. A deeper, wider range, and higher level of abstraction can be achieved in the mixture of information at different levels, scopes, and abstractions. This in turn facilitates the extraction of richer and more adaptive image representations. The combination of these three types of convolution can extract richer features while effectively controlling computing resources, thereby balancing computational efficiency and performance.

[0159] It should be further explained that the depthwise separable convolution is mainly used to extract low-level features in images, such as edges, corners, and simple textures. The 1x1 convolution is used to linearly combine the features of all channels to capture the relationship between channels, significantly reducing the number of parameters and computational complexity.

[0160] Its structure contains small-scale convolution kernels, and the output is added to the input through residual connections.

[0161] The formula is as follows:

[0162] Branch_1=Conv(1x1)(x)

[0163] Branch_2=Conv(3x3)(Conv(1x1)(x))

[0164] Branch_3=Conv(3x3)(Conv(3x3)(Conv(1x1)(x)))

[0165] InceptionOutput_A=[Branch_1,Branch_2,Branch_3]

[0166] y_A=x+alpha*Conv(1x1)(InceptionOutput_A).

[0167] Dilated convolution is used to capture mid-level features, such as larger structural information and contextual information. These features help the model understand more complex patterns in the image, especially when dealing with blurred edges and object boundaries.

[0168] The expanded convolution introduces a dilation factor (dilation rate) to skip input elements when the convolution kernel is applied, so that the receptive field of the convolution kernel is increased, so that it can "see" a wider area of ​​the image.

[0169] Its structure contains medium-sized convolutional kernels, and the output is added to the input through a residual connection.

[0170] The formula is as follows:

[0171] Branch_1=Conv(1x1)(x)

[0172] Branch_2=Conv(7x1)(Conv(1x7)(Conv(1x1)(x)))

[0173] InceptionOutput_B=[Branch_1,Branch_2]

[0174] y_B=x+alpha*Conv(1x1)(InceptionOutput_B).

[0175] Standard convolution is mainly used to extract high-level features, such as complex shapes of objects and specific visual patterns, comprehensively identify complex patterns and object shapes, and provide support for classification decisions.

[0176] This enables the Mix-inresNet model to effectively extract features at different levels, thereby improving the detection and classification capabilities of the lumbar spine region in MRI images.

[0177] The Block-C module is used to extract high-level features. Its structure contains a larger-scale convolution kernel and adds the output to the input through a residual connection.

[0178] The formula is as follows:

[0179] Branch_1=Conv(1x1)(x)

[0180] Branch_2=Conv(3x1)(Conv(1x3)(Conv(1x1)(x)))

[0181] InceptionOutput_C=[Branch_1,Branch_2]

[0182] y_C=x+alpha*Conv(1x1)(InceptionOutput_C).

[0183] Here, x is the input tensor, which is represented as a three-dimensional tensor of R^H x W x C, where H represents the height, W represents the width, and C represents the number of channels.

[0184] Conv(kxk) is a kxk convolution operation, where k represents the size of the convolution kernel. For example, Conv(3x3) represents a 3x3 convolution kernel.

[0185] Alpha is a scaling factor used to adjust the influence of the residual connection part and is usually set to a small value, such as alpha = 0.1.

[0186] The channel concatenation operation concatenates the outputs of the parallel branches along the channel dimension.

[0187] y_A, y_B, y_C are the output tensors of the depthwise separable convolution, unfolded convolution, and standard convolution modules, with the same dimensions as the input tensor x.

[0188] It should be further explained that the Mix-inresNet model also includes a dimensionality reduction module, which includes ReductionA and ReductionB modules. By reducing the spatial dimension or number of channels of the feature map, the computational complexity is reduced and more representative features are provided for the subsequent feature extraction layer.

[0189] The ReductionA module is usually used to significantly reduce the spatial dimension of the feature map while retaining some channel information. It combines multiple parallel convolution operations and pooling operations, and finally obtains the output feature map by splicing.

[0190] The formula is as follows:

[0191] Branch_1=MaxPool(3x3,stride=2)(x)

[0192] Branch_2=Conv(3x3,stride=2)(x)

[0193] Branch_3=Conv(1x1)(x)->Conv(3x3)(Branch_3)

[0194] Branch_4=Conv(1x1)(x)->Conv(3x3)(Branch_4)->Conv(3x3,stride=2)(Branch_4)

[0195] ReductionA_Output=[Branch_1, Branch_2, Branch_3, Branch_4]

[0196] Among them, x is the input tensor, ReductionA_Output is the output after dimensionality reduction and feature extraction operations through different paths, and finally the outputs of these branches are spliced ​​together in the channel dimension.

[0197] The ReductionB module is usually used to further reduce the spatial dimension and number of channels of the feature map. It combines more complex convolution operations and pooling operations and is suitable for the middle and late stages of the network.

[0198] The formula is as follows:

[0199] Branch_1=MaxPool(3x3,stride=2)(x)

[0200] Branch_2=Conv(1x1)(x)->Conv(3x3,stride=2)(Branch_2)

[0201] Branch_3=Conv(1x1)(x)->Conv(7x1)(Branch_3)->Conv(1x7)(Branch_3)->Conv(3x3,stride=2)(Branch_3)

[0202] ReductionB_Output=[Branch_1,Branch_2,Branch_3]

[0203] Among them, x is the input tensor, ReductionB_Output is the output after dimensionality reduction and feature extraction operations through different paths, and finally the outputs of these branches are spliced ​​together in the channel dimension.

[0204] Here, x is the input tensor, which is represented as a three-dimensional tensor of R^H x W x C, where H represents the height, W represents the width, and C represents the number of channels.

[0205] MaxPool(3x3,stride=2): Maximum pooling operation, using a 3x3 pooling kernel and a sliding window with a stride of 2, usually used to reduce the spatial dimensions (H and W) by half.

[0206] Conv(kxk, stride=s): convolution operation, using a convolution kernel of kxk and a stride of s. stride=2 is usually used to reduce the spatial dimension.

[0207] ReductionA_Output and ReductionB_Output: are the outputs of the ReductionA and ReductionB modules respectively. They are formed by concatenating the outputs of the branches after feature extraction and dimensionality reduction operations through different paths.

[0208] In at least one embodiment of the present application, the detection method based on the lumbar region in the MRI image further includes:

[0209] The Mix-inresNet model also includes a self-attention module, which is before the average pooling layer;

[0210] The output of the self-attention module is calculated as follows:

[0211] F g ∈R(C′×H×W)F h ∈R(C′×H×W)F g F h G∈R(C′×N)H∈R(C′×N)N=H×WO∈R(C′×N); O=softmax((G T )*H / sqrt(d))*H;

[0212] Get the final feature map.

[0213] C, H, and W represent the channel count, height, and width of the feature map, respectively.

[0214] OF resizes it and restores it to the original feature dimension through linear convolution, and then adds it to the original feature map to obtain the final feature map.

[0215] In this embodiment, in the Mix-inresNet model, the self-attention module is integrated as a part, and the integrated self-attention module is located before the average pooling layer.

[0216] The feature maps after convolution and other processing layers are input into the self-attention module.

[0217] The self-attention module generates attention weights by calculating the similarity or correlation between each position in the feature map.

[0218] According to the calculated weights, the input features are weighted to highlight important features and suppress background noise.

[0219] The feature map processed by the self-attention module is passed to the average pooling layer.

[0220] The final feature map used for classification contains features optimized by self-attention.

[0221] The self-attention mechanism enables the model to dynamically adjust feature weights based on the input data, thereby adapting to different types of images and task requirements.

[0222] The final output feature map provides richer and more useful features for subsequent classification or detection, promoting the accuracy and efficiency of medical image analysis.

[0223] It should be noted that the constructed self-attention module first generates two new feature mappers through convolution operation, and then we flatten them along the spatial dimension to obtain and respectively.

[0224] It should be further explained that the average pooling layer in the Mix-inresNet model is used to reduce the spatial size (width and height) of the feature map to reduce the amount of calculation and aggregate information. The role of average pooling is to smooth the feature map by averaging the local area, thereby extracting features with smooth transitions while retaining certain spatial information.

[0225] For an input feature map X, assuming its size is H×W and the size of the pooling window is k h ×k w , the step length is s, X[i×s+m, j×s+n] is the pixel value of the input feature map in the pooling window. Then each element y of the output feature map Y i，j It can be calculated by the following formula:

[0226]

[0227] In at least one embodiment of the present application, the detection method based on the lumbar region in the MRI image further includes:

[0228] Receive the result correction data of the external input Mix-inresNet model to train the Mix-inresNet model.

[0229] Please refer to Figure 1-4 In this embodiment, the result correction data of the Mix-inresNet model is received from an external source (such as a clinician or a data management system).

[0230] The corrected data is organized and integrated into the training data set to facilitate subsequent model training.

[0231] Retrain the Mix-inresNet model using the training set containing the corrected data and update the model’s weights and parameters.

[0232] During training, the model will use the correction data to adjust its classification decisions so that its output is more consistent with actual clinical outcomes.

[0233] After training is complete, the model is evaluated against new data to ensure that its performance has been effectively improved.

[0234] If necessary, new correction data can be continuously received and the above process can be repeated to continuously optimize the model.

[0235] By introducing external result correction data, the model can learn the actual classification rules more accurately, improving the detection and classification capabilities of lumbar MRI images, thereby improving classification accuracy and enhancing model robustness.

[0236] It should be noted that the activation function ReLU retains the positive gradient by directly setting the part of the input less than 0 to 0, which partially alleviates the gradient disappearance problem.

[0237] The mathematical expression of the ReLU function is: f(x) = max(0, x)

[0238] in:

[0239] x is the input value.

[0240] When x≥0, output f(x)=x.

[0241] When x<0, output f(x)=0.

[0242] The ReLU function outputs all negative values ​​as 0, and leaves positive values ​​unchanged.

[0243] In model training, the loss function is the cross-entropy loss function. In addition, in order to improve the training process, the model also introduces an auxiliary classifier to provide additional gradient signals to enhance feature extraction capabilities. The loss function and its formula in the Mix-inresNet model are as follows:

[0244]

[0245] Where N is the number of samples, y i is the actual label, is the probability distribution predicted by the model, is the cross entropy loss of the main classifier, is the cross entropy loss of the auxiliary classifier, use In the cross entropy loss formula, α is the weight coefficient of the auxiliary loss.

[0246] A detection device 200 based on a lumbar region in an MRI image is applied to any one of the above-mentioned detection methods based on a lumbar region in an MRI image, and the detection device 200 based on a lumbar region in an MRI image comprises:

[0247] A data acquisition module 210 is used to acquire an MRI image data set of the lumbar spine of the patient to be tested;

[0248] YOLOv5 model 220, used for feature extraction of lumbar spine MRI image dataset;

[0249] Mix-inresNet model 230, which processes the feature image dataset and outputs the scoring results;

[0250] The detection device based on the lumbar region in the MRI image performs the following steps:

[0251] Acquire an MRI image dataset of the lumbar spine of a patient to be tested;

[0252] Constructing a YOLOv5 model, inputting the lumbar MRI image dataset into the YOLOv5 model to obtain a feature image dataset;

[0253] Constructing a Mix-inresNet model, inputting the feature image data set into the Mix-inresNet model, and the Mix-inresNet model outputs a classification result data set;

[0254] The Mix-inresNet model performs soft voting on the classification result dataset and outputs the scoring results to assist doctors in lumbar spine examinations.

[0255] Please refer to Figure 5 In this embodiment, first, the detection device 200 based on the lumbar region in the MRI image obtains the lumbar MRI image dataset of the patient to be detected through the data acquisition module 210, and inputs the obtained MRI image dataset into the YOLOv5 model 220 for target detection. The YOLOv5 model 220 automatically extracts the ROI related to the lumbar spine and generates a feature image dataset. The feature image dataset output by the YOLOv5 model is input into the Mix-inresNet model 230, and the Mix-inresNet model 230 performs in-depth classification of the feature image dataset and outputs the classification result dataset. The classification results are soft-voted and combined with the classification results of different models. The final scoring result is output to assist doctors in diagnosing lumbar diseases. Through automated image processing and analysis, the time for doctors to manually view and analyze images is reduced, thereby improving work efficiency.

[0256] Please refer to Figure 6 , a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following steps:

[0257] Acquire an MRI image dataset of the lumbar spine of a patient to be tested;

[0258] Constructing a YOLOv5 model, inputting the lumbar MRI image dataset into the YOLOv5 model to obtain a feature image dataset;

[0259] Constructing a Mix-inresNet model, inputting the feature image data set into the Mix-inresNet model, and the Mix-inresNet model outputs a classification result data set;

[0260] The Mix-inresNet model performs soft voting on the classification result dataset and outputs the scoring results to assist doctors in lumbar spine examinations.

[0261] In this embodiment, first, a lumbar MRI image dataset of the patient to be detected is obtained, and the obtained MRI image dataset is input into the YOLOv5 model for target detection. YOLOv5 automatically extracts the ROI related to the lumbar spine and generates a feature image dataset. The feature image dataset output by YOLOv5 is input into the Mix-inresNet model, and the Mix-inresNet model performs in-depth classification of the feature image dataset and outputs the classification result dataset. The classification results are soft-voted and combined with the classification results of different models. The final scoring results are output to assist doctors in diagnosing lumbar diseases. Through automated image processing and analysis, the time for doctors to manually view and analyze images is reduced, thereby improving work efficiency.

[0262] 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 program can be stored in a non-volatile computer-readable storage medium. When the 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).

[0263] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above 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.

[0264] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A detection method for the lumbar region based on MRI images, characterized in that: The detection method based on the lumbar region in the MRI image comprises: Acquire an MRI image dataset of the lumbar spine of a patient to be tested; Constructing a YOLOv5 model, inputting the lumbar MRI image dataset into the YOLOv5 model to obtain a feature image dataset; Constructing a Mix-inresNet model, inputting the feature image data set into the Mix-inresNet model, and the Mix-inresNet model outputs a classification result data set; The Mix-inresNet model performs soft voting on the classification result dataset and outputs the scoring results to assist doctors in lumbar spine examinations.

2. The method for detecting the lumbar region based on MRI images according to claim 1, characterized in that: The step of constructing the YOLOv5 model, inputting the lumbar MRI image dataset into the YOLOv5 model, and obtaining the feature image dataset comprises: The YOLOv5 model extracts the features of the central spinal canal, lateral recess, neural foramen, and intervertebral disc from the MRI image dataset of the lumbar spine to obtain the feature image dataset, wherein the feature image dataset includes: each detected ROI bounding box in the MRI image dataset of the lumbar spine, a classification result dataset, a ROI image, and a confidence score.

3. The method for detecting the lumbar region based on MRI images according to claim 1, characterized in that: The steps of constructing a Mix-inresNet model, inputting the feature image data set into the Mix-inresNet model, and the Mix-inresNet model outputting a classification result data set include: The ROI image is input into the Mix-inresNet model, and the Mix-inresNet model classifies the ROI image into normal, mild, moderate, and severe categories to obtain a classified result data set.

4. The method for detecting the lumbar region based on MRI images according to claim 1, characterized in that: The detection method based on the lumbar region in the MRI image also includes: The MRI images of the lumbar spine of the patient to be tested are labeled to obtain a labeled data set.

5. The method for detecting the lumbar region based on MRI images according to claim 1, characterized in that: The step of constructing a Mix-inresNet model, inputting the feature image data set into the Mix-inresNet model, and the Mix-inresNet model outputting a classification result data set also includes: Construct the training set, validation set, and test set of the Mix-inresNet model, and divide the images and labels of the original dataset into the training set, validation set, and test set in a ratio of 8:1:1, so that the training set accounts for 80% of the total dataset, and the validation set and test set each account for 10% of the total dataset.

6. The method for detecting the lumbar region based on MRI images according to claim 1, characterized in that: The Mix-inresNet model includes a backbone network module, which integrates a mixed convolutional layer, an average pooling layer, a dropout layer, and a softmax layer; The hybrid convolutional layers include: depthwise separable convolution, dilated convolution, and standard convolution; The backbone network module performs multi-scale processing and parallel processing on the hybrid convolution layer, average pooling layer, and dimensionality reduction module to obtain the ROI image features after parallel processing.

7. The method for detecting the lumbar region based on MRI images according to claim 6, characterized in that: The detection method based on the lumbar region in the MRI image also includes: The Mix-inresNet model also includes a self-attention module, which is before the average pooling layer; The output of the self-attention module is calculated as follows: F g ∈R(c′×H×w)F h ∈R(c′×H×w)F g F h G∈R(c′×N)H∈R(c′×N)N=H×WO∈R(C′×N); <h2 style=";text-align:left;direction:ltr">0=softmax((G<h2 style=";text-align:left;direction:ltr"> T <h2 style=";text-align:left;direction:ltr"> )*H / sqrt(d))*H; Get the final feature map.

8. The method for detecting the lumbar region based on MRI images according to claim 6, characterized in that: The detection method based on the lumbar region in the MRI image also includes: Receive the result correction data of the external input Mix-inresNet model to train the Mix-inresNet model.

9. A detection device based on the lumbar region in MRI images, applied to the detection method based on the lumbar region in MRI images as claimed in any one of claims 1 to 8, characterized in that: The detection device based on the lumbar region in the MRI image comprises: A data acquisition module, used to acquire an MRI image data set of the lumbar spine of a patient to be tested; YOLOv5 model, used for feature extraction of lumbar spine MRI image dataset; Mix-inresNet model, processes feature image dataset and outputs scoring results.

10. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the detection method of the lumbar region based on MRI images as claimed in any one of claims 1 to 8.

Images