Chest cross section CT inclination identification method and system based on key point detection

Abstract

The invention provides a chest cross section CT inclination identification method and system based on key point detection, and relates to the technical field of image processing. Comprising the steps of obtaining a chest cross section CT image and corresponding key point coordinates; based on the key point coordinates, generating a label heat map matrix of each chest cross section CT image; building a convolutional neural network model, training the convolutional neural network model by using the chest cross section CT image to obtain a prediction heat map matrix, calculating the loss of the model, and completing the training of the model; inputting the unlabeled chest cross section CT image into the trained convolutional neural network model to obtain a prediction heat map matrix corresponding to the unlabeled chest cross section CT image; and searching the coordinate of a point with the maximum heat in the prediction heat map matrix corresponding to the unmarked chest cross section CT image, and taking the coordinate as the predicted key point coordinate. According to the invention, a technician is dynamically reminded to adjust the position by taking the calculated position deflection angle as a reference, so that the inspection efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical image processing, and in particular relates to a chest cross-sectional CT tilt recognition method and system based on key point detection. Background Art

[0002] CT (Computed Tomography) scanning is a clinical imaging examination method. As one of the most common imaging modalities in clinical diagnosis, CT can help medical service staff detect diseases and injuries in patients. It uses a series of X-rays and computer software to create detailed images of bones and soft tissues, and is widely used in the screening and diagnosis of major diseases.

[0003] Before CT scanning, technicians usually position the patient, which is done manually and relies on the technician's experience. The deviation of the cross-section caused by positioning deviation or the patient's body tilt during the organ scanning process seriously affects the imaging quality, which in turn affects the doctor's diagnosis of the disease. CT images of unqualified quality need to be corrected by technicians through post-processing. In the case of severe deviation that cannot be corrected, re-scanning is required, which increases the radiation cost to the patient's body and reduces the efficiency of diagnosis. Summary of the invention

[0004] In order to overcome the shortcomings of the above-mentioned prior art, the present invention provides a chest cross-sectional CT tilt recognition method and system based on key point detection, which utilizes a convolutional neural network to extract the key point features of the chest cross-sectional CT, calculates the patient's positioning deviation angle based on the position information of the key points in the image, and dynamically reminds the technician to adjust the positioning based on the calculated positioning deviation angle to improve the inspection efficiency.

[0005] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions:

[0006] The first aspect of the present invention provides a chest cross-sectional CT tilt recognition method based on key point detection.

[0007] The method for identifying the tilt of chest cross-sectional CT based on key point detection comprises the following steps:

[0008] Obtaining an original chest cross-sectional CT image, manually marking key points therein, and performing preprocessing to obtain a preprocessed chest cross-sectional CT image and corresponding key point coordinates;

[0009] Based on the key point coordinates, a label heat map matrix is ​​generated for each chest cross-sectional CT image;

[0010] Build a convolutional neural network model and use chest cross-sectional CT images to train the convolutional neural network model to obtain a predicted heat map matrix. Calculate the model loss based on the predicted heat map matrix and the label heat map matrix until the loss value converges and the model training is completed.

[0011] The unlabeled chest cross-sectional CT image is input into the trained convolutional neural network model to obtain the predicted heat map matrix corresponding to the unlabeled chest cross-sectional CT image;

[0012] Find the coordinates of the point with the highest heat in the predicted heat map matrix corresponding to the unlabeled chest cross-sectional CT image, which are the predicted key point coordinates;

[0013] Based on the predicted key point coordinates, the inclination angle during chest cross-sectional CT scanning is calculated to complete the inclination angle recognition.

[0014] The second aspect of the present invention provides a chest cross-sectional CT tilt recognition system based on key point detection.

[0015] The chest cross-sectional CT tilt recognition system based on key point detection includes:

[0016] The preprocessing module is configured to: obtain an original chest cross-sectional CT image, manually annotate key points therein, and perform preprocessing to obtain a preprocessed chest cross-sectional CT image and corresponding key point coordinates;

[0017] The label heat map matrix generation module is configured to: generate a label heat map matrix for each chest cross-sectional CT image based on the key point coordinates;

[0018] The training module is configured to: build a convolutional neural network model, train the convolutional neural network model using chest cross-sectional CT images to obtain a prediction heat map matrix, and calculate the loss of the model based on the prediction heat map matrix and the label heat map matrix until the loss value converges, thereby completing the training of the model;

[0019] The prediction heat map matrix calculation module is configured to: input the unlabeled chest cross-sectional CT image into the trained convolutional neural network model to obtain the prediction heat map matrix corresponding to the unlabeled chest cross-sectional CT image;

[0020] The key point coordinate determination module is configured to: find the coordinates of the point with the highest heat in the predicted heat map matrix corresponding to the unlabeled chest cross-sectional CT image, which are the predicted key point coordinates;

[0021] The tilt angle calculation module is configured to calculate the tilt angle during chest cross-sectional CT scanning based on the predicted key point coordinates to complete tilt angle recognition.

[0022] The third aspect of the present invention provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in the chest cross-sectional CT tilt identification method based on key point detection as described in the first aspect of the present invention.

[0023] The fourth aspect of the present invention provides an electronic device, including a memory, a processor, and a program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the chest cross-sectional CT tilt identification method based on key point detection as described in the first aspect of the present invention are implemented.

[0024] One or more of the above technical solutions have the following beneficial effects:

[0025] The present invention provides a chest cross-sectional CT tilt recognition method and system based on key point detection, which uses a convolutional neural network to extract key point features of the chest cross-sectional CT, calculates the patient's positioning deviation angle based on the position information of the key points in the image, and dynamically reminds the technician to adjust the positioning based on the calculated positioning deviation angle to improve the inspection efficiency.

[0026] The convolutional neural network used in the present invention does not connect convolution blocks in series like most existing solutions, but connects sub-networks from high to low resolution in parallel. The convolutional neural network designed in this way can maintain high-resolution features instead of restoring resolution through a process from low to high. Accordingly, multi-scale fusion is used to improve high-resolution representation, so that high-resolution representation also has rich feature estimation. Therefore, the heat map predicted by the convolutional neural network designed in this way is more accurate.

[0027] The invention adopts a recognition method for detecting patient positioning deviation based on key points, uses chest clinical cross-sectional CT examination sequence images, labels the sternum, vertebral body and lamina as key points for training labels of deep learning algorithm, and calculates the loss of the model based on the predicted heat map matrix and the label heat map matrix until the loss value converges, so that the trained model has higher accuracy.

[0028] The present invention divides the key points into two cases and three cases based on the predicted key point coordinates, designs calculation formulas respectively, calculates the inclination angle during chest cross-sectional CT scanning, completes inclination angle recognition, and makes the calculation more targeted.

[0029] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0031] Figure 1 This is a flow chart of the method of the first embodiment.

[0032] Figure 2 This is the overall structure diagram of the convolutional neural network model.

[0033] Figure 3 Schematic diagram of the predicted heat map matrix for predicting 2 key points.

[0034] Figure 4 Schematic diagram of the predicted heat map matrix for predicting three key points. DETAILED DESCRIPTION

[0035] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0036] It should be noted that the terms used herein are for describing specific embodiments only and are not intended to be limiting of exemplary embodiments according to the present invention.

[0037] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0038] Embodiment 1

[0039] This embodiment discloses a chest cross-sectional CT tilt recognition method based on key point detection.

[0040] like Figure 1 As shown, the chest cross-sectional CT tilt recognition method based on key point detection includes the following steps:

[0041] Obtaining an original chest cross-sectional CT image, manually marking key points therein, and performing preprocessing to obtain a preprocessed chest cross-sectional CT image and corresponding key point coordinates;

[0042] Based on the key point coordinates, a label heat map matrix is ​​generated for each chest cross-sectional CT image;

[0043] Build a convolutional neural network model and use chest cross-sectional CT images to train the convolutional neural network model to obtain a predicted heat map matrix. Calculate the model loss based on the predicted heat map matrix and the label heat map matrix until the loss value converges and the model training is completed.

[0044] The unlabeled chest cross-sectional CT image is input into the trained convolutional neural network model to obtain the predicted heat map matrix corresponding to the unlabeled chest cross-sectional CT image;

[0045] Find the coordinates of the point with the highest heat in the predicted heat map matrix corresponding to the unlabeled chest cross-sectional CT image, which are the predicted key point coordinates;

[0046] Based on the predicted key point coordinates, the inclination angle during chest cross-sectional CT scanning is calculated to complete the inclination angle recognition.

[0047] With the widespread application of artificial intelligence technology in the medical field, the research of AI technology in the medical field has progressed rapidly. If artificial intelligence technology can be used to detect whether the patient's position is normal during CT scanning, the technician can be dynamically reminded to adjust the position and improve the efficiency of the examination.

[0048] Therefore, this embodiment proposes a chest cross-sectional CT tilt recognition method based on key point detection, which specifically includes the following steps:

[0049] a) Obtain the chest cross-sectional CT image sequence data set ct_imgs, and obtain the key point data of each CT image annotated by the annotator to obtain the annotation set keypoint_jsons.

[0050] b) The CT image data after the image format conversion in a) is further preprocessed to obtain the CT image ct_imgs, with dimensions (batch_size, chanels, img_height, img_width), where batch_size is the batch size of the training data, the number of image chanels channels is n, the CT image is a multi-channel image, and img_height and img_width are the size of a single CT image, 512 × 512. The annotation set keypoint_jsons is preprocessed to obtain the training annotation keypoint_annotation.

[0051] The preprocessing steps are as follows:

[0052] Each image ct in b1.ct_imgs i Using different window widths and window positions will produce images that focus on different organs and tissues, so three windows are selected here, namely the lung window, soft tissue window, and bone window. The lung window focuses on showing the texture of the lungs, the soft tissue window is suitable for showing the condition of the mediastinum, and the bone window is suitable for showing bone tissue related to the ribs.

[0053] b2. Each image ct i The lung window, soft tissue window, and bone window are linearly mapped to generate three single-channel image CT images. i-lung ,ct i-soft ,ct i-bone .

[0054] b3. put ct i-lung ,ct i-soft ,ct i-bone Three single-channel images are fused into a multi-channel image, ct i =concat([cti-lung ,ct i-soft ,ct i-bone ]), the final ct i becomes a three-channel image.

[0055] c) Initialize model parameters and training parameters, set model training strategy, load training annotation keypoint_annotation, and load CT image data set ct_imgs.

[0056] d) Based on the labeled data read in step c), generate a heat map matrix label_mask for each CT image, whose feature dimension is (1, img_height, img_width).

[0057] e) After the model loads CT images in batches, it uses a convolutional neural network to extract features in four stages. The tensor features obtained in each stage are stage1_conv, stage2_conv, stage3_conv, and stage4_conv. The tensor features in each stage have different size changes.

[0058] f) After processing in step e), tensor features at different levels are obtained, and these features are fused to obtain richer information.

[0059] This step includes feature map downsampling (feature downsample), feature map skip connection (feature residual connection), feature map compression (feature compress), and feature map fusion (feature fusion) operations.

[0060] g) Calculate the prediction loss loss using the prediction heatmap predictionheatmap generated during model training and the label heatmap matrix label_mask for the next round of optimization iteration.

[0061] h) Use the optimizer to back-propagate the learning parameters of the convolutional neural network based on the prediction loss.

[0062] i) Repeat steps b) to h) until the loss reaches a stable convergence state, at which point the optimal weight M of the model is obtained.

[0063] j) Load the model weights obtained in step i) and input the chest cross-sectional CT image to obtain the model prediction result result, whose dimension is (3, x, y, prob), where prob is the confidence of the prediction point.

[0064] k) Calculate the deflection angle of the cross-sectional CT using the key points predicted by the model.

[0065] More specifically:

[0066] 1. In step a), the experimental data uses real clinical CT image data. Data preprocessing is required before training, which mainly includes two steps:

[0067] a-1) Image format conversion to obtain CT image data set ct_imgs. The original CT image data storage format is a dicom file, which is converted into a jpg file with default window width and window position. The default window width and window position are obtained from the metadata of dicom, which are window width field '0028|1051', window position field

[0068] '0028|1050'.

[0069] a-2) The annotator marks the key points in each CT image and generates the corresponding annotation file. The key points in the cross-sectional CT are labeled as sternum, vertebral body, and lamina, and their coordinate information in the image is annotated (x, y). All the annotated data will be reviewed by professional physicians and used for the next step.

[0070] 2. The data preprocessing in step b) mainly includes two parts: CT image and annotation.

[0071] b-1) CT images. Rename the CT images in the format of 'CT examination number_serial number_image number.jpg', such as CT01931088_SN3_000011.jpg.

[0072] b-2) CT annotation set. Read the annotation file of each image, convert it and store it into the annotation format of the COCO dataset to obtain keypoint_jsons. The converted annotation file contains 5 parts: info, licenses, annotations, categories, and image. Info stores the version information of the dataset, licenses is the copyright statement, categories are the categories of CT images, and images are all the image information in the dataset. Annotations is all the annotation information in the dataset, where image_id is the image id corresponding to the annotation, id is the unique identifier of the annotation file, and keypoints is a list of key point annotations in the format of (x, y, visible), that is, the coordinates of the annotation point and whether it is visible (occluded).

[0073] 3. Initialize model parameters and training parameters in step c) and set the model training strategy.

[0074] c-1) Load the model parameters based on ImageNet pre-trained weights.

[0075] Set the model to a 4-stage convolutional neural network, such as Figure 2 As shown, the feature map name and size of each stage change as follows:

[0076] Stage 1: This stage contains 4 residual units, each of which consists of a bottleneck of width 64, followed by a 3×3 convolutional feature map with width reduced to 32.

[0077] Stage 2: This stage contains 1 exchange block, which contains 4 residual units, each of which contains 2 3×3 convolutions at each resolution and a resolution exchange unit.

[0078] Stage 3: This stage contains 4 exchange blocks. Each exchange block contains 4 residual units, each of which contains 2 3×3 convolutions at each resolution and a resolution exchange unit.

[0079] Stage 4: This stage contains 3 exchange blocks. Each exchange block contains 4 residual units, where each unit contains 2 3×3 convolutions at each resolution and a resolution exchange unit.

[0080] c-2) Initialize the training parameters. The batch size BATCH_SIZE_PER_GPU is set to 128, the shuffle data SHUFFLE is set to true, the total number of training epochs EPOCH is set to 210, the learning rate LR is set to 0.0001, and the learning rate is decayed after 170 epochs of training. The optimizer OPTIMIZER is set to Adam, the parameter GAMMA1 is set to 0.99, and the parameter GAMMA2 is set to 0.

[0081] c-3) Set the model training strategy. Use sklearn.model_selection to divide the data set into training set: validation set = 9:1. During training, use flipped images and affine transformation to enhance the data.

[0082] The key point threshold OKS_THRE is set to 0.9. When training the loaded images, normalization is performed, the mean is [0.485, 0.456, 0.406], and the variance is [0.229, 0.224, 0.225].

[0083] 4. Step d) Generate a heat map matrix label_mask for each CT image. For each key point (x, y) of each CT image, generate a Gaussian heat map matrix centered on the point. It is necessary to set the standard deviation parameter σ of the Gaussian matrix generated by each key point and the matrix size (M*N) of the heat map. σ, M, and N are all hyperparameters.

[0084] 5. Tensor features at each stage in step e).

[0085] e-1)stage1_conv. The first stage of the model contains 4 residual units, each of which consists of a bottleneck with a width of 64, followed by a 3×3 convolution, and the width of the feature map is reduced to 32. i Input to stage1_conv. The size of the feature map output by this stage is 32×32×64, and this feature map is called stage1_conv.

[0086] e-2) stage2_conv. The second stage of the model contains 1 exchange block, which contains 4 residual units, each of which contains 2 3×3 convolutions at each resolution and a resolution exchange unit. The size of the feature map output by this stage is 16×16×96, and this feature map is called stage2_conv.

[0087] e-3) stage3_conv. The third stage of the model contains 4 exchange blocks. Each exchange block contains 4 residual units, each of which contains 2 3×3 convolutions at each resolution and a exchange unit at each resolution. The size of the feature map output by this stage is 8×8×192, and this feature map is called stage3_vonv.

[0088] e-4) stage4_conv. The fourth stage of the model contains 3 exchange blocks. Each exchange block contains 4 residual units, each of which contains 2 3×3 convolutions at each resolution and a resolution exchange unit. The size of the feature map output by this stage is 4×4×320, and this feature map is called stage4_conv.

[0089] 6. Feature fusion operation in step f). The feature fusion stage mainly extracts features at different scales and fuses these features to obtain richer information.

[0090] f-1) Downsampling.

[0091] This step is achieved through a series of convolution operations and downsampling operations to convert the high-resolution feature map into a low-resolution feature map so that the high-resolution feature map can be aligned with the low-resolution feature map in spatial size.

[0092] f-2) Skip connection.

[0093] At each stage of the convolutional neural network, skip connections are used to connect the low-resolution feature maps with the high-resolution feature maps. These connections are usually implemented by pixel-by-pixel addition.

[0094] f-3) Feature compression.

[0095] This step is usually achieved through a series of convolution operations, the purpose of which is to compress the feature map to reduce its size so that the high-resolution feature map can be connected to the low-resolution feature map.

[0096] f-4) Feature fusion.

[0097] In the feature fusion stage, feature maps of different scales need to be fused. These feature maps of different scales are usually fused by adding pixel by pixel.

[0098] 7. The loss function used in step g) is the weighted fine-tuned MSELoss, and the specific calculation expression is as follows.

[0099]

[0100] Among them, k is the number of key points, kp_pred is the model prediction heat map matrix, kp_label is the label truth matrix, weight i is the weight vector for each key point.

[0101] 8. The optimizer in step h) is set to Adam optimizer, and its momentum parameter beta1 is initialized to 0.99, the quadratic momentum parameter beta2 is initialized to 0, the numerical stability parameter epsilon is 1e-8, and the learning rate is set to 0.0001.

[0102] 9. In step k), the angle calculation is divided into two cases, namely, the CT image contains 2 key points and 3 key points.

[0103] k-1)2 key points, such as Figure 3 As shown in Figure 2, the inclination angle θ is calculated based on the coordinates of the vertebral body and lamina, and the calculation formula is:

[0104]

[0105] k-2) 3 key points, such as Figure 4 The angle θ1 is calculated based on the coordinates of the sternum and the vertebral body, and the angle θ2 is calculated based on the coordinates of the vertebral body and the lamina. The average value is taken as the inclination angle θ, and the calculation formula is:

[0106]

[0107] Among them, (x1, y1) is the coordinate of the vertebral lamina; (x2, y2) is the coordinate of the vertebral body; (x3, y3) is the coordinate of the sternum.

[0108] Embodiment 2

[0109] This embodiment discloses a chest cross-sectional CT tilt recognition system based on key point detection.

[0110] The chest cross-sectional CT tilt recognition system based on key point detection includes:

[0111] The preprocessing module is configured to: obtain an original chest cross-sectional CT image, manually annotate key points therein, and perform preprocessing to obtain a preprocessed chest cross-sectional CT image and corresponding key point coordinates;

[0112] The label heat map matrix generation module is configured to: generate a label heat map matrix for each chest cross-sectional CT image based on the key point coordinates;

[0113] The training module is configured to: build a convolutional neural network model, train the convolutional neural network model using chest cross-sectional CT images to obtain a prediction heat map matrix, and calculate the loss of the model based on the prediction heat map matrix and the label heat map matrix until the loss value converges, thereby completing the training of the model;

[0114] The prediction heat map matrix calculation module is configured to: input the unlabeled chest cross-sectional CT image into the trained convolutional neural network model to obtain the prediction heat map matrix corresponding to the unlabeled chest cross-sectional CT image;

[0115] The key point coordinate determination module is configured to: find the coordinates of the point with the highest heat in the predicted heat map matrix corresponding to the unlabeled chest cross-sectional CT image, which are the predicted key point coordinates;

[0116] The tilt angle calculation module is configured to calculate the tilt angle during chest cross-sectional CT scanning based on the predicted key point coordinates to complete tilt angle recognition.

[0117] Embodiment 3

[0118] The purpose of this embodiment is to provide a computer-readable storage medium.

[0119] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the chest cross-sectional CT tilt identification method based on key point detection as described in Example 1 of the present disclosure.

[0120] Embodiment 4

[0121] The purpose of this embodiment is to provide an electronic device.

[0122] An electronic device includes a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, the steps in the chest cross-sectional CT tilt recognition method based on key point detection as described in Example 1 of the present disclosure are implemented.

[0123] The steps involved in the apparatuses of the above embodiments 2, 3 and 4 correspond to the method embodiment 1, and the specific implementation methods can refer to the relevant description part of embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood to include any medium that can store, encode or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.

[0124] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0125] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A chest cross-sectional CT tilt recognition method based on key point detection, characterized in that: The following steps are involved: Obtaining an original chest cross-sectional CT image, manually marking key points therein, and performing preprocessing to obtain a preprocessed chest cross-sectional CT image and corresponding key point coordinates; Based on the key point coordinates, a label heat map matrix is ​​generated for each chest cross-sectional CT image; Build a convolutional neural network model and use chest cross-sectional CT images to train the convolutional neural network model to obtain a predicted heat map matrix. Calculate the model loss based on the predicted heat map matrix and the label heat map matrix until the loss value converges and the model training is completed. The unlabeled chest cross-sectional CT image is input into the trained convolutional neural network model to obtain the predicted heat map matrix corresponding to the unlabeled chest cross-sectional CT image; Find the coordinates of the point with the highest heat in the predicted heat map matrix corresponding to the unlabeled chest cross-sectional CT image, which are the predicted key point coordinates; Based on the predicted key point coordinates, the inclination angle during chest cross-sectional CT scanning is calculated to complete the inclination angle recognition.

2. The chest cross-sectional CT tilt recognition method based on key point detection according to claim 1, characterized in that: The coordinates of the sternum, vertebral body, and lamina in the original chest cross-sectional CT image are manually annotated, and the format of the original chest cross-sectional CT image and the manually annotated key points are converted to complete the preprocessing process.

3. The chest cross-sectional CT tilt recognition method based on key point detection according to claim 1, characterized in that: The label heat map matrix of each chest cross-sectional CT image is generated using Gaussian distribution, including: Define the parameters of the Gaussian distribution; Identify the coordinates of the marked key points and calculate the Gaussian distribution standard deviation of the key points; Generates a label heatmap matrix based on the standard deviation of a Gaussian distribution.

4. The chest cross-sectional CT tilt recognition method based on key point detection according to claim 1, characterized in that: The convolutional neural network model includes four stages of residual convolution modules: The residual convolution module of the first stage includes four first residual units, each of which includes a bottleneck and a subsequent convolution layer; The residual convolution module of the second stage includes 1 exchange block, the exchange block includes 4 second residual units, the second residual unit includes 2 convolution layers and a resolution exchange unit; The residual convolution module in the third stage includes 4 exchange blocks; The residual convolution module in the fourth stage includes 3 exchange blocks.

5. The chest cross-sectional CT tilt recognition method based on key point detection according to claim 1, characterized in that: The loss function of the convolutional neural network model is calculated as follows: Among them, k is the number of key points, kp_pred is the prediction heat map matrix, kp_label is the label heat map matrix, weight i is the weight vector for each key point.

6. The method for chest cross-sectional CT tilt recognition based on key point detection according to claim 4, characterized in that: Input the unlabeled chest cross-sectional CT image into the trained convolutional neural network model: Four-stage residual convolution modules are used to extract the first feature map, the second feature map, the third feature map, and the fourth feature map of different scales respectively; in each residual convolution module, the low-resolution feature map is connected to the high-resolution feature map through a jump connection; Downsampling and feature compressing the first feature map, the second feature map, the third feature map, and the fourth feature map; The first feature map, the second feature map, the third feature map and the fourth feature map after feature compression are fused to obtain a predicted heat map matrix corresponding to the unlabeled chest cross-sectional CT image.

7. The chest cross-sectional CT tilt recognition method based on key point detection according to claim 1, characterized in that: Based on the predicted key point coordinates, the inclination angle of the chest cross-sectional CT scan is calculated, including: First, distinguish the names of the key points; When two key points are predicted, the inclination angle θ is calculated according to the coordinates of the vertebral body and lamina. The calculation formula is: Among them, (x1, y1) is the coordinate of the lamina; (x2, y2) is the coordinate of the vertebral body; When three key points are predicted, the angle θ1 is calculated according to the coordinates of the vertebral body and the lamina, and the angle θ2 is calculated according to the coordinates of the sternum and the vertebral body. The average of θ1 and θ2 is taken as the inclination angle θ. The calculation formula is: Among them, (x3, y3) is the coordinate of the sternum.

8. A chest cross-sectional CT tilt recognition system based on key point detection, characterized in that: include: The preprocessing module is configured to: obtain an original chest cross-sectional CT image, manually annotate key points therein, and perform preprocessing to obtain a preprocessed chest cross-sectional CT image and corresponding key point coordinates; The label heat map matrix generation module is configured to: generate a label heat map matrix for each chest cross-sectional CT image based on the key point coordinates; The training module is configured to: build a convolutional neural network model, train the convolutional neural network model using chest cross-sectional CT images to obtain a prediction heat map matrix, and calculate the loss of the model based on the prediction heat map matrix and the label heat map matrix until the loss value converges, thereby completing the training of the model; The prediction heat map matrix calculation module is configured to: input the unlabeled chest cross-sectional CT image into the trained convolutional neural network model to obtain the prediction heat map matrix corresponding to the unlabeled chest cross-sectional CT image; The key point coordinate determination module is configured to: find the coordinates of the point with the highest heat in the predicted heat map matrix corresponding to the unlabeled chest cross-sectional CT image, which are the predicted key point coordinates; The tilt angle calculation module is configured to calculate the tilt angle during chest cross-sectional CT scanning based on the predicted key point coordinates to complete tilt angle recognition.

9. A computer-readable storage medium having a program stored thereon, characterized in that: When the program is executed by a processor, the steps in the chest cross-sectional CT tilt recognition method based on key point detection as described in any one of claims 1 to 7 are implemented.

10. An electronic device comprising a memory, a processor, and a program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the chest cross-sectional CT tilt recognition method based on key point detection as described in any one of claims 1 to 7 are implemented.

Images