System for fully automatically analyzing chest CT body tissue components

Abstract

The invention discloses a system for fully automatically analyzing chest CT body tissue components, which relates to the technical field of medical diagnosis equipment, can automatically select L1 slices meeting requirements and quantitatively analyze the muscle and fat area and density of a target layer, and specifically comprises three modules: a positioning module for positioning a target L1 slice on a chest CT image; the segmentation module is used for segmenting skeletal muscle and adipose tissue of an axial slice corresponding to L1 on the chest CT image; and the automatic measurement module is used for automatically measuring the body composition of the clinical chest CT image. In a word, the method not only improves the efficiency and precision of measuring the human body components on the chest CT, but also fills the blank of the conventional technology of automatically screening the L1 single slice by a machine.

Description

Technical Field

[0001] The present invention relates to the technical field of medical diagnostic equipment, and in particular to a fully automatic system for analyzing body tissue components in chest CT. Background Art

[0002] Assessment of body tissue composition throughout the body is important for a variety of clinical and research applications. It is widely accepted that body composition can independently influence health. For example, reduced skeletal muscle mass is associated with poorer quality of life, increased risk of falls and fractures, and has been considered a strong predictor of cardiovascular events and mortality risk. Reduced skeletal muscle mass is an independent risk factor for prolonged hospitalization in elderly patients with proximal femur fractures and death in patients with mechanical ventilation in the intensive care unit (ICU), colorectal cancer, and renal transplantation. Studies have shown that the mass of adipose tissue can significantly affect the incidence of cardiovascular and metabolic diseases and various cancers, as well as the clinical outcomes of lung transplant patients. In addition, recent studies have shown that the same type of adipose tissue distributed in different anatomical locations, such as subcutaneous adipose tissue and visceral adipose tissue, may have different effects on health and disease states, making it necessary to quantify and analyze these body components separately. Therefore, an accurate, practical, and efficient method for quantifying body composition may bring far-reaching clinical benefits.

[0003] Previously, there have been many methods for quantifying body composition, such as anthropometry, including body mass index (BMI), skinfold thickness, waist circumference, etc. These are simple to operate, fast and easy to obtain, and have been widely used to assess obesity. However, these measurement methods do not provide information about the individual contribution of each tissue type to body composition, and are limited in measuring changes in human body composition. Currently, most imaging-based methods require human-computer interaction to quantify different tissues. However, when processing chest CT images of a large number of subjects, interactive methods are obviously impractical. Although related inventions have provided automated measurement software, existing automated methods either focus only on improving the accuracy of chest CT image segmentation networks, or use fully automatic selection and segmentation neural networks previously developed and verified for L3 slices. Summary of the invention

[0004] In order to solve the deficiencies mentioned in the above background technology, the purpose of the present invention is to provide a fully automatic chest CT body tissue composition analysis system, which can automatically select the L1 section that meets the requirements and perform quantitative analysis on the muscle, fat area and density of the target layer.

[0005] In a first aspect, the purpose of the present invention can be achieved by the following technical solution: a fully automatic system for analyzing chest CT body tissue composition, comprising:

[0006] A positioning module, a segmentation module and an automatic measurement module; the positioning module is used to collect chest CT scan images, identify and sort the anatomical features of all vertebrae in the chest CT, obtain CT sequence images that may be predicted to be L1, find the sequence with the longest transverse process spacing in this sequence as the L1 sequence, input the processed L1 sequence CT images into a pre-established ResNet-50 model, train to obtain an L1 positioning model, send the CT image of the best L1 slice to the segmentation module, and send the L1 positioning model to the automatic measurement module;

[0007] The segmentation module is used to divide the CT image of the best L1 slice into skeletal muscle and fat tissue to obtain the divided L1 slice, input the divided L1 slice into a pre-established 3D U-Net+ model, output the optimal segmentation model, and send the optimal segmentation model to the automatic measurement module;

[0008] The automatic measurement module is used to collect chest CT images to be processed, input the chest CT images to be processed into the L1 positioning model to obtain a single optimal LI slice, input the single optimal LI slice into the optimal segmentation model to obtain skeletal muscle, subcutaneous fat and visceral fat, use skeletal muscle, subcutaneous fat and visceral fat to calculate the quantity and average muscle attenuation, and obtain body tissue composition measurement results.

[0009] In combination with the first aspect, in some implementations of the first aspect, the system further includes: a process in which the positioning module acquires a chest CT scan image:

[0010] The chest CT slices that have been randomly flipped vertically and affine transformed are input into the positioning model. The model automatically identifies all the anatomical features of the cervical, thoracic, and lumbar vertebrae, and selects the sequence that may be L1 based on the unique anatomical features of the L1 vertebra. Then, the CT sequence with the longest inter-transverse process spacing is selected from the L1 sequence as the optimal L1 sequence. Finally, it is further processed by the positioning model.

[0011] In combination with the first aspect, in some implementations of the first aspect, the system further includes: a process in which the positioning module processes the CT image of the best L1 slice:

[0012] The data was processed on the Verse20 dataset, and the CT image of the best L1 slice and the slices connected above and below were used as positive samples. The remaining slices were randomly sampled as negative samples, so that the ratio of positive samples to negative samples was 1:5.

[0013] In combination with the first aspect, in some implementations of the first aspect, the system further includes: a pre-established ResNet-50 model of the positioning module is as follows:

[0014] The expression of ResNet-50 can be expressed as:

[0015] [H(x)=F(x,{W_i})+x]

[0016] in:

[0017] (H(x)) is the output of the network.

[0018] (x) is the input to the network.

[0019] (F(x,{W_i})) is the residual function, which represents the result of the input (x) after being transformed through a series of layers, and ({W_i}) represents the set of weights in the network.

[0020] (+x) is a skip connection that adds the input (x) directly to the output of the residual function (F(x,{W_i})).

[0021] In combination with the first aspect, in certain implementations of the first aspect, the system further includes: the segmentation module divides the CT image of the best L1 slice into skeletal muscle and adipose tissue including background, skeletal muscle, subcutaneous fat and visceral fat, and the division is based on the spatial distribution of skeletal muscle and adipose tissue and tissue radiation attenuation characteristics.

[0022] In combination with the first aspect, in some implementations of the first aspect, the system further includes: the pre-established 3D U-Net+ model of the segmentation module includes a 3D encoder, a 3D decoder, and an output layer.

[0023] In combination with the first aspect, in some implementations of the first aspect, the system further includes: the 3D encoder is composed of convolution blocks, each convolution block contains two 3D convolution layers and a 3D maximum pooling layer, after the convolution layer, each convolution block is downsampled by a 2×2×2 maximum pooling layer, and the output of each convolution block is transmitted to the corresponding 3D decoder part through a skip connection;

[0024] The 3D decoder consists of convolution blocks, each of which includes a 3D upsampling layer and two 3D convolution layers. After upsampling, each convolution block uses two convolution kernels and is also equipped with BN and ReLU activation functions. The upsampled feature map is concatenated with the skip connection from the corresponding convolution block of the encoder.

[0025] The output layer adopts a 3D convolutional layer to map the output of the last convolutional block of the 3D decoder to the number of target categories.

[0026] In combination with the first aspect, in some implementations of the first aspect, the system further includes: a loss function constructed by the pre-established 3DU-Net+ model is as follows:

[0027] For a chest CT image I of size H×W, a multi-class cross entropy loss function is combined with a Dice loss function to segment the background, skeletal muscle, subcutaneous fat, and visceral fat, as shown in formula (1):

[0028]

[0029] Among them, C = 4 represents background, skeletal muscle, subcutaneous fat, and visceral fat;

[0030] ω c represents the weight of the c-th type of organization;

[0031] Indicates the gold standard value of pixel i belonging to the cth class label;

[0032] Indicates the prediction result of pixel i being predicted as the cth class label;

[0033] H and W represent the height and width of the 2D axial image, respectively.

[0034] In combination with the first aspect, in some implementations of the first aspect, the system further includes: counting pixel proportions of skeletal muscle, subcutaneous fat, visceral fat, and background, and then setting a small weight for skeletal muscle with a small proportion, and setting a large weight for subcutaneous and visceral fat with a large proportion, as shown in formula (2).

[0035]

[0036] Where H, W and D represent the height, width and depth of the two-dimensional image;

[0037] N c Represents the pixel count statistics of the c-th label.

[0038] In combination with the first aspect, in certain implementations of the first aspect, the system further includes: the process of calculating the quantity and average muscle attenuation using skeletal muscle, subcutaneous fat, and visceral fat is as follows:

[0039] The calculation expression of skeletal muscle, subcutaneous fat and visceral fat area is: [A=sum_{i=1}^{N}p_i\timesa_i]

[0040] Where (p_i) is the classification probability that pixel (i) belongs to a specific tissue and (a_i) is the area of ​​pixel (i).

[0041] Calculation of average muscle attenuation values ​​for skeletal muscle, subcutaneous fat and visceral fat:

[0042] For each pixel, if it is classified as skeletal muscle, its CT value is recorded, and the average of the CT values ​​of all skeletal muscle pixels is calculated.

[0043] Expression: [mu=frac{sum_{i=1}^{M}v_i}{M}]

[0044] Where (v_i) is the CT value of pixel (i) and (M) is the total number of skeletal muscle pixels.

[0045] Beneficial effects of the present invention:

[0046] The present invention can accurately locate the target L1 slice by fully automatically analyzing chest CT images through a deep learning network, which is crucial for the subsequent diagnosis of skeletal muscle system diseases. Secondly, the ResNet-50 classification model is used for slice positioning to ensure the speed and accuracy of positioning and improve the overall performance of the system. Thirdly, the 3D U-Net+ architecture is used for image segmentation, with the advantages of simple network structure, easy training and optimization, while the jump connection retains more image details and improves the accuracy of segmentation. These improvements are conducive to the early diagnosis and treatment of skeletal muscle system diseases (such as sarcopenia and muscle fatty degeneration), and improve the efficiency and accuracy of clinical applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 It is the overall framework diagram of the system of the present invention;

[0049] Figure 2 The best first lumbar vertebra slice selected from the chest CT image of the present invention;

[0050] Figure 3 This is a schematic diagram of the positioning model training of the present invention;

[0051] Figure 4 This is a schematic diagram of the division of skeletal muscle, subcutaneous fat and visceral fat in the present invention;

[0052] Figure 5 Schematic diagram of the 3D segmentation network of the present invention;

[0053] Figure 6 The following are the muscle fat segmentation results of 3 physical examination subjects of the present invention;

[0054] Figure 7 This is a flow chart of the application of the system of the present invention. DETAILED DESCRIPTION

[0055] 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.

[0056] Embodiment 1:

[0057] like Figure 1 As shown, a fully automatic system for analyzing chest CT body tissue composition includes:

[0058] Positioning module, segmentation module and automatic measurement module;

[0059] The positioning module is used to collect chest CT scan images, perform anatomical feature recognition and positioning on the chest CT scan images, obtain multiple CT images predicted to be L1, process the multiple CT images predicted to be L1 slices, obtain multiple CT images that may be the best L1 slices after processing, input the multiple CT images that may be the best L1 slices after processing into a pre-established ResNet-50 model, train to obtain an L1 positioning model, locate and determine the multiple CT images that may be the best L1 slices based on the L1 positioning model, obtain a single CT image of the best L1 slice, send the single CT image of the best L1 slice to the segmentation module, and send the L1 positioning model to the automatic measurement module;

[0060] First, the patient is given a chest CT scan, and the resulting CT image includes the cervical spine, thoracic spine, and all L1. Then determine the location of the best L1 slice. First, process the data on the Verse20 dataset, take the best L1 slice and several slices connected above and below as positive samples, and randomly sample the remaining slices as negative samples to ensure a positive-negative sample ratio of 1:5. Then, train the L1 localization model obtained on the ResNet-50 model, and select the layer with the highest prediction probability from the 5-15 best layers as the final L1 slice. The L1 localization model is tested in the test set, and the results are shown in Table 1.

[0061] Table 1 Test results of the positioning model on 248 healthy people undergoing physical examinations

[0062]

[0063] Specifically, the specific operation process of the positioning module:

[0064] Positioning preprocessing: The data is processed on the Verse20 dataset, the best L1 slice and several slices connected above and below are used as positive samples, and the remaining slices are randomly sampled (10 slices are randomly selected) as negative samples, ensuring that the positive-negative sample ratio is 1:5;

[0065] The localization model was trained on the first lumbar vertebra slices of 200 physical examination subjects using the ResNet-50 model, and the slice with the highest prediction probability was selected from the 5-15 best slices as the final L1 slice. Figure 3 .

[0066] The pre-built ResNet-50 model of the positioning module is as follows:

[0067] The expression of ResNet-50 can be expressed as:

[0068] [H(x)=F(x,{W_i})+x]

[0069] in:

[0070] (H(x)) is the output of the network.

[0071] (x) is the input to the network.

[0072] (F(x,{W_i})) is the residual function, which represents the result of the input (x) after being transformed through a series of layers, and ({W_i}) represents the set of weights in the network.

[0073] (+x) is a skip connection that adds the input (x) directly to the output of the residual function (F(x,{W_i})).

[0074] In ResNet-50, the residual function (F(x,{W_i})) is usually composed of multiple residual blocks, each of which can be expressed as:

[0075] [F(x)=text{ReLU}(text{BN}(text{Conv}(x))+text{BN}(text{Conv}(text{ReLU}(text{BN}(text{Conv}(x))))))

[0076] in:

[0077] (text{ReLU}) is the activation function.

[0078] (text{BN}) is batch normalization.

[0079] (text{Conv}) is the convolution operation.

[0080] Each residual block usually contains 3 convolutional layers, where the stride of the first and third convolutional layers is 1 to maintain the size of the feature map, and the stride of the second convolutional layer is 2 for downsampling.

[0081] The structure of the ResNet-50 model is roughly as follows:

[0082] 1. A 7x7 convolutional layer with a stride of 2, followed by a max pooling layer.

[0083] 2. Three residual block sequences, each sequence contains several residual blocks.

[0084] 3. The number of residual blocks in each sequence is 3, 4, and 6 respectively.

[0085] 4. After each sequence, there is usually an average pooling layer with a stride of 2 for downsampling.

[0086] 5. The last layer is a fully connected layer for classification.

[0087] The segmentation module is used to divide the CT image of the best L1 slice into skeletal muscle and fat tissue to obtain the divided L1 slice, input the divided L1 slice into a pre-established 3D U-Net+ model, output the optimal segmentation model, and send the optimal segmentation model to the automatic measurement module;

[0088] The segmentation module extracts four types of labels from the automatically selected L1 single slice, namely background, skeletal muscle, subcutaneous fat and visceral fat. The four categories are divided based on the spatial distribution of skeletal muscle and adipose tissue and the characteristics of tissue radiation attenuation; the L1 axial slices on the automatically selected chest CT images are used as the input for training the segmentation network, and the output is the four types of labels for the segment area; after training, the optimal segmentation model is obtained; here, the segmentation network adopts an innovative 3D U-Net+ network architecture proposed by the present invention, and the model is divided into two main parts: encoder and decoder.

[0089] Specifically, the segmentation module

[0090] The slices belonging to L1 obtained by the positioning module are divided into skeletal muscle and fat tissue, including L1 axial skeletal muscle (see Figure 4 Label2), subcutaneous fat and visceral fat (see Figure 4 Label3 and Label4);

[0091] Segmentation preprocessing: The window level of all DICOM files was reset to the range of -190 to 150HU to ensure that the required information of the image can be accurately obtained within this range. At the same time, data enhancement operations were performed, including random XY flip, 90-degree rotation, ±10-degree rotation around the XY axis, and random cropping;

[0092] Constructing the segmentation network architecture: The method is to use the 3D U-Net+ model innovatively proposed by the present invention (see Figure 5 ), which is a 3D convolutional neural network (CNN) technology based on deep learning, and is designed to achieve fully automatic organ segmentation. The 3D U-Net+ model inherits and expands the U-Net architecture of traditional medical image segmentation to more effectively extract and fuse multi-scale feature information of images. The model is divided into two main parts: the encoder and the decoder, which work closely together through jump connections to achieve accurate image segmentation.

[0093] in:

[0094] 3D encoder design

[0095] Convolutional block composition: The encoder consists of four carefully designed convolutional blocks, each of which contains two 3D convolutional layers and one 3D maximum pooling layer.

[0096] Max pooling layer: After the convolutional layer, each convolutional block is downsampled by a 2×2×2 max pooling layer with a stride of 2 to reduce the spatial dimension of the feature map while retaining the most important feature information;

[0097] Skip connection: In order to preserve spatial detail information, the output of each convolutional block is passed to the corresponding decoder part through a skip connection, laying the foundation for subsequent feature fusion and detail reconstruction;

[0098] In particular, at the beginning of the second convolutional block, the present invention innovatively introduces a 4×4×4 maximum pooling layer. This design aims to perform deeper feature extraction on the input data, capture significant features in the image by selecting the maximum value in the local area, and provide a more abstract and compact feature representation for subsequent processing.

[0099] 3D decoder design

[0100] Convolution block composition: The decoder also consists of four convolution blocks, each of which includes a 3D upsampling layer and two 3D convolution layers.

[0101] Upsampling layer: In the first convolutional block of the decoder, we pass a 2×2×2 upsampling layer to increase the spatial dimension of the feature map and recover the details that may be lost during the downsampling process.

[0102] Convolutional layer details: After upsampling, each convolution block uses two 3×3×3 convolution kernels and is also equipped with BN and ReLU activation functions to further refine the feature representation.

[0103] Feature fusion: By concatenating the upsampled feature maps with the skip connections from the corresponding convolutional blocks of the encoder, the comprehensive utilization of cross-level features is achieved. This fusion strategy not only enhances the model's ability to extract multi-scale features of input data, but also significantly improves the model's ability to represent complex structures and detailed information.

[0104] When constructing the 3D U-Net+ model, at the beginning of the second convolutional block of the encoder, the present invention carefully designs a 4×4×4 size maximum pooling layer, which follows the first convolutional layer. The introduction of this maximum pooling layer aims to effectively extract deep features from the input data, and capture the most significant and important information in the image by selecting the maximum value in each local area. Such an operation not only reduces the dimension of the data, but also helps the network focus on the most discriminative features, providing a more compact and abstract feature representation for subsequent network layers. Subsequently, the feature map of the second convolutional block processed by the maximum pooling layer is fused with the feature map of the fourth convolutional block. This feature fusion strategy realizes the comprehensive utilization of cross-level features by combining feature information from different convolutional blocks and different levels. This integration not only enhances the model's ability to capture multi-scale features of input data, but also improves the model's ability to represent complex structures and detailed information.

[0105] Output layer design

[0106] The output layer uses a 3D convolutional layer, which maps the output of the last convolutional block of the decoder to the number of target categories. Specifically, the number of output channels is reduced to a dimension that matches the number of target categories through a 1×1×1 convolution kernel, and the Softmax activation function is used to output the probability that each voxel belongs to a different category. In the present invention, the output layer can accurately distinguish between background, skeletal muscle, subcutaneous fat, and visceral fat tissue.

[0107] Constructing the loss function

[0108] For a chest CT image I of size H×W, the commonly used multi-class cross entropy loss function in medical image segmentation tasks is combined with the Dice loss function to segment the background, skeletal muscle, subcutaneous fat and visceral fat, as shown in formula (1):

[0109]

[0110] Among them, C = 4 represents background, skeletal muscle, subcutaneous fat, and visceral fat;

[0111] ω c represents the weight of the c-th type of organization;

[0112] Indicates the gold standard value of pixel i belonging to the cth class label;

[0113] Indicates the prediction result of pixel i being predicted as the cth class label.

[0114] H and W represent the height and width of the 2D axial image, respectively.

[0115] The size of skeletal muscle, subcutaneous fat, visceral fat and background is very different, which means that there is a class imbalance problem that causes the segmentation framework to be unstable. Therefore, during the training process, in the loss function, it is necessary to penalize low-confidence predictions (such as Label2) by setting weights. Specifically, first, in the training image, the pixel ratios of skeletal muscle, subcutaneous fat, visceral fat and background are counted, and then a small weight is set for skeletal muscle with a small ratio, and a large weight is set for subcutaneous and visceral fat with a large ratio, as shown in formula (2).

[0116]

[0117] Where H, W and D represent the height, width and depth of the two-dimensional image;

[0118] N c Represents the pixel count statistics of the c-th label;

[0119] Therefore, from ω c The prior statistics of ensure the class-balanced optimization of the loss function.

[0120] The automatic measurement module is used to collect chest CT images to be processed, input the chest CT images to be processed into the L1 positioning model to obtain a single optimal LI slice, input the single optimal LI slice into the optimal segmentation model to obtain skeletal muscle, subcutaneous fat and visceral fat, use skeletal muscle, subcutaneous fat and visceral fat to calculate the quantity and average muscle attenuation, and obtain body tissue composition measurement results.

[0121] The automatic measurement module uses the positioning model and segmentation model trained by the first two modules, takes the new chest CT image and the corresponding L1 position as input, and sets the HU intervals in advance, including skeletal muscle [-29, 150], visceral fat [-150, -50], and subcutaneous fat [-190, -30]. The amount and average HU of skeletal muscle, subcutaneous fat, and visceral fat can be calculated based on the deep learning model. Finally, automatic measurement of body composition can be achieved.

[0122] The automatic measurement module includes:

[0123] After positioning preprocessing, the new chest CT image is input into the trained optimal positioning model to obtain a single optimal L1 slice;

[0124] The obtained single best L1 slice was preprocessed for segmentation and then input into the segmentation optimal model to obtain skeletal muscle, subcutaneous fat, and visceral fat;

[0125] At the same time, the single best L1 slice was threshold processed to obtain the corresponding areas of skeletal muscle, subcutaneous fat and visceral fat corresponding to L1;

[0126] The quantity and average muscle attenuation of the obtained skeletal muscle, subcutaneous fat and visceral fat are calculated to achieve automatic measurement of body composition.

[0127] The calculation of the amount and average muscle attenuation using skeletal muscle, subcutaneous fat, and visceral fat is as follows:

[0128] Calculation of skeletal muscle, subcutaneous fat and visceral fat area:

[0129] For each pixel, if its classification probability exceeds a certain threshold (e.g. 0.5), the pixel is considered to belong to the tissue. The total number of pixels in each category is calculated and then multiplied by the physical area of ​​the pixel to get the number of each category. Expression: [A = sum_{i = 1}^{N}p_i\times a_i]

[0130] Where (p_i) is the classification probability that pixel (i) belongs to a specific tissue and (a_i) is the area of ​​pixel (i).

[0131] Calculation of average muscle attenuation values ​​for skeletal muscle, subcutaneous fat and visceral fat:

[0132] For each pixel, if it is classified as skeletal muscle, its CT value is recorded, and the average of the CT values ​​of all skeletal muscle pixels is calculated.

[0133] Expression: [mu=frac{sum_{i=1}^{M}v_i}{M}]

[0134] Where (v_i) is the CT value of pixel (i) and (M) is the total number of skeletal muscle pixels.

[0135] Specifically, the present invention is further described below by way of embodiments:

[0136] The present invention is further described below with reference to examples and a system overall framework diagram.

[0137] Taking the clinical original images collected from the clinic as an example, the application process of the present invention for automatically measuring body components is as follows: Figure 7 shown.

[0138] Module 1 is the screening of L1 axial slices. First, the clinical CT image set of 248 healthy subjects undergoing physical examinations was preprocessed for positioning, that is, the three-dimensional data set was saved as an image with the extension "DICOM format", and then randomly flipped vertically and affine transformed. All slices were input into the positioning model trained with the data set of 200 healthy subjects undergoing physical examinations, and the prediction results of L1 slices were obtained, as shown in Table 1. Accuracy represents accuracy, Allowable error represents allowable error, and Averageerror represents average error.

[0139] Module 2 is the segmentation process of skeletal muscle, subcutaneous fat and visceral fat. First, the slice corresponding to L1 located by module 1 is segmented and preprocessed, that is, the window level of all DICOM files is set to the range of [-190HU, 150HU], and data enhancement operations are performed, including random XY flip, 90-degree rotation, ±10-degree rotation around the XY axis, and random cropping. Then the image is input into the segmentation model trained with the dataset of 248 healthy subjects for physical examination, and the segmentation results of skeletal muscle, subcutaneous fat and visceral fat are obtained.

[0140] Table 1 and Table 2 show the test results of the data of 248 healthy subjects undergoing physical examinations on the positioning model and the segmentation model. In the positioning model, the slice corresponding to L1 is used as the gold standard for training. The higher the accuracy obtained in Table 1, the better the positioning effect. In the segmentation model, skeletal muscle, subcutaneous fat and visceral fat are used as the gold standard for training. The higher the segmentation indicators Iou, Precision, Recall and Dice, the better, and the smaller the SD, the better. Table 2 calculates the segmentation indicators of skeletal muscle, subcutaneous fat and visceral fat respectively. Here, Iou is an indicator to measure the degree of overlap between the predicted result and the true label in the image segmentation task, Precision indicates accuracy, Recall is an indicator to measure the model's ability to recognize four types of labeled samples, Dice is a commonly used indicator to evaluate image segmentation accuracy, and SD is the standard deviation;

[0141] Table 2 Test results of the segmentation model on 248 healthy people undergoing physical examinations

[0142]

[0143]

[0144] Based on the same inventive concept, the present invention also provides a computer device, which includes: one or more processors, and a memory for storing one or more computer programs; the program includes program instructions, and the processor is used to execute the program instructions stored in the memory. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is used to implement one or more instructions, specifically for loading and executing one or more instructions in a computer storage medium to implement the above method.

[0145] It needs to be further explained that, based on the same inventive concept, the present invention also provides a computer storage medium, on which a computer program is stored, and the computer program is executed by a processor to execute the above method. The storage medium can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electrical, magnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0146] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0147] The above shows and describes the basic principles, main features and advantages of the present disclosure. Those skilled in the art should understand that the present disclosure is not limited by the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present disclosure. Without departing from the spirit and scope of the present disclosure, the present disclosure may have various changes and improvements, and these changes and improvements fall within the scope of the present disclosure to be protected.

Claims

1. A fully automatic system for analyzing chest CT body tissue composition, characterized in that: include: Positioning module, segmentation module and automatic measurement module; The positioning module is used to collect chest CT scan images, identify and sort the anatomical features of all vertebrae in the chest CT, obtain CT sequence images predicted to be L1, obtain the sequence with the longest transverse process spacing in the sequence as the L1 sequence CT image, input the L1 sequence CT image into a pre-established ResNet-50 model, train to obtain an L1 positioning model, locate and determine the L1 sequence CT image based on the L1 positioning model, obtain the CT image of the best L1 slice, send the CT image of the best L1 slice to the segmentation module, and send the L1 positioning model to the automatic measurement module; The segmentation module is used to divide the CT image of the best L1 slice into skeletal muscle and fat tissue to obtain the divided L1 slice, input the divided L1 slice into a pre-established 3D U-Net+ model, output the optimal segmentation model, and send the optimal segmentation model to the automatic measurement module; The automatic measurement module is used to collect chest CT images to be processed, input the chest CT images to be processed into the L1 positioning model to obtain a single optimal LI slice, input the single optimal LI slice into the optimal segmentation model to obtain skeletal muscle, subcutaneous fat and visceral fat, use skeletal muscle, subcutaneous fat and visceral fat to calculate the quantity and average muscle attenuation, and obtain body tissue composition measurement results.

2. The fully automatic system for analyzing chest CT body tissue composition according to claim 1, characterized in that: The process of the positioning module collecting chest CT scan images: The chest CT slices that have been randomly flipped vertically and affine transformed are input into the positioning model. The model automatically identifies all the anatomical features of the cervical, thoracic, and lumbar vertebrae, and selects the sequence that may be L1 based on the unique anatomical features of the L1 vertebra. Then, the CT sequence with the longest inter-transverse process spacing is selected from the L1 sequence as the optimal L1 sequence, which is then further processed by the positioning model.

3. The fully automatic system for analyzing chest CT body tissue composition according to claim 2, characterized in that: The process of the positioning module processing the CT image of the best L1 slice: The data was processed on the Verse20 dataset, and the CT image of the best L1 slice and the slices connected above and below were used as positive samples. The remaining slices were randomly sampled as negative samples, so that the ratio of positive samples to negative samples was 1:

5.

4. The fully automatic system for analyzing chest CT body tissue composition according to claim 1, characterized in that: The pre-built ResNet-50 model of the positioning module is as follows: [H(x)=F(x,{W_i})+x] in: (H(x)) is the output of the network; (x) is the input to the network. (F(x,{W_i})) is the residual function, which represents the result of the input (x) after being transformed through a series of layers, and ({W_i}) represents the set of weights in the network; (+x) is a skip connection that adds the input (x) directly to the output of the residual function (F(x,{W_i})).

5. The fully automatic system for analyzing chest CT body tissue composition according to claim 1, characterized in that: The segmentation module divides the CT image of the best L1 slice into skeletal muscle and fat tissue, including background, skeletal muscle, subcutaneous fat and visceral fat, and the division is based on the spatial distribution of skeletal muscle and fat tissue and tissue radiation attenuation characteristics.

6. The fully automatic system for analyzing chest CT body tissue composition according to claim 1, characterized in that: The pre-built 3D U-Net+ model of the segmentation module includes a 3D encoder, a 3D decoder, and an output layer.

7. The fully automatic system for analyzing chest CT body tissue composition according to claim 6, characterized in that: The 3D encoder is composed of convolution blocks, each of which contains two 3D convolution layers and a 3D maximum pooling layer. After the convolution layer, each convolution block is downsampled by a 2×2×2 maximum pooling layer, and the output of each convolution block is passed to the corresponding 3D decoder part through a skip connection; The 3D decoder consists of convolution blocks, each of which includes a 3D upsampling layer and two 3D convolution layers. After upsampling, each convolution block uses two convolution kernels and is also equipped with BN and ReLU activation functions. The upsampled feature map is concatenated with the skip connection from the corresponding convolution block of the encoder. The output layer adopts a 3D convolutional layer to map the output of the last convolutional block of the 3D decoder to the number of target categories.

8. The fully automatic system for analyzing chest CT body tissue composition according to claim 7, characterized in that: The loss function of the pre-built 3D U-Net+ model is as follows: For a chest CT image I of size H×W, a multi-class cross entropy loss function is combined with a Dice loss function to segment the background, skeletal muscle, subcutaneous fat, and visceral fat, as shown in formula (1): Among them, C = 4 represents background, skeletal muscle, subcutaneous fat, and visceral fat; ω c represents the weight of the c-th type of organization; Indicates the gold standard value of pixel i belonging to the cth class label; Indicates the prediction result of pixel i being predicted as the cth class label; H and W represent the height and width of the 2D axial image, respectively.

9. The fully automatic system for analyzing chest CT body tissue composition according to claim 8, characterized in that: The pixel ratios of skeletal muscle, subcutaneous fat, visceral fat and background are counted, and then a small weight is set for skeletal muscle with a small ratio, and a large weight is set for subcutaneous and visceral fat with a large ratio, as shown in formula (2). Where H, W and D represent the height, width and depth of the two-dimensional image; N c Represents the pixel count statistics of the c-th label.

10. The fully automatic system for analyzing chest CT body tissue composition according to claim 1, characterized in that: The process of calculating the number and average muscle attenuation using skeletal muscle, subcutaneous fat and visceral fat is as follows: The calculation expression of skeletal muscle, subcutaneous fat and visceral fat area is: [A=sum_{i=1}^{N}p_i\times a_i] Where (p_i) is the classification probability that pixel (i) belongs to a specific tissue and (a_i) is the area of ​​pixel (i). Calculation of average muscle attenuation values ​​for skeletal muscle, subcutaneous fat and visceral fat: For each pixel, if it is classified as skeletal muscle, record the CT value, and then calculate the average CT value of all skeletal muscle pixels; expression: [mu = frac {sum_{i = 1}^{M}v_i}{M}] Where (v_i) is the CT value of pixel (i) and (M) is the total number of skeletal muscle pixels.

Images