Medical image processing method and system based on deep learning

Abstract

The invention belongs to the technical field of medical image processing, and particularly relates to a medical image processing method and system based on deep learning, and the method comprises the steps: creating a key frame extraction model, training the key frame extraction model through the marked medical image data, obtaining the medical video stream data of the brain of a patient, and carrying out the data preprocessing, inputting into a key frame extraction model; creating an image processing model, and inputting the extracted key frame image containing the specified waveform data into the image processing model for key feature recognition; the image processing model carries out image cutting on a key feature region in the key frame image based on the identified key features; and the image processing model performs specified feature extraction on the target area separated from the image, outputs the specified feature, performs data formatting processing on the output specified feature data, converts the specified feature data into a specified data format, and exports the specified data format. According to the process, continuous blood flow data can be obtained based on the image processing process of the medical image data of the TCCD.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical image processing, and in particular relates to a medical image processing method and system based on deep learning. Background Art

[0002] In clinical diagnosis and treatment, with the continuous advancement of science and technology and the continuous development of the medical field, personalized medicine is moving towards a more efficient and accurate direction, and is expected to improve the quality and effectiveness of medical services in the future. With the development of medical imaging equipment, the quality of tissue imaging data obtained by medical imaging equipment is getting higher and higher, and it can image the finer structures of patient tissues and lesions. Organ anatomical imaging obtained through advanced medical imaging technology can objectively reflect tissue structure, pathological changes, etc., and provide important assistance to doctors in diagnosis and treatment from positioning evidence to guiding treatment.

[0003] As the quality of medical imaging improves, a matching medical image processing method is needed. The medical image processing and analysis process in the prior art is to directly extract lesion features from the lesions in the medical image data, and perform lesion analysis based on the extracted lesion feature data to obtain the corresponding disease data.

[0004] However, the accuracy of the analysis results of lesions and conditions of lesion feature data only by extracting features from medical image data is not enough, and it is also impossible to obtain dynamic changes in the patient's tissues through medical images. For example, in the process of clinical diagnosis and treatment, the methods of obtaining cerebral blood flow signals are mostly TCD (transcranial Doppler) and TCCD (transcranial color Doppler). TCD uses the Doppler effect to emit high-frequency sound waves through an ultrasonic probe. The sound waves change frequency when passing through the blood flow, and this change can be used to calculate the blood flow velocity. TCCD combines traditional Doppler ultrasound and color coding technology to detect blood flow by emitting high-frequency sound waves. Color coding indicates the direction and speed of blood flow, allowing medical staff to intuitively identify and evaluate the state of blood vessels. TCD and TCCD have their own advantages and disadvantages in obtaining cerebral blood flow. TCD only measures blood flow velocity and cannot provide detailed structural information of blood flow. It is limited to velocity data, while TCCD not only provides information on blood flow velocity, but also displays the anatomical structure of blood vessels (through color coding), which helps to make a more comprehensive evaluation, but cannot provide continuous and real-time cerebral blood flow signals.

[0005] In the process of clinical diagnosis and treatment, most departments, such as intensive care and clinical anesthesia, are only equipped with TCCD equipment but lack TCD equipment. Therefore, the ability to obtain continuous cerebral blood flow signal monitoring is very limited. How to perform image processing based on TCCD medical imaging data to obtain continuous blood flow data is a technical problem that needs to be solved urgently. Summary of the invention

[0006] The purpose of the present invention is to provide a medical image processing method and system based on deep learning, which is used to perform image processing on medical image data based on TCCD to obtain continuous blood flow data.

[0007] In order to solve the above technical problems, the technical solution adopted by the present invention is as follows: A medical image processing method based on deep learning comprises the following steps: S1: creating a key frame extraction model, and training the key frame extraction model using labeled medical image data, and verifying the key frame extraction model using a verification set to determine whether specified performance parameters meet specified requirements; S2: obtaining the medical video stream data of the patient's brain and performing data preprocessing, inputting the preprocessed medical video stream data into the trained key frame extraction model, wherein the key frame extraction model extracts the key frame image containing the specified waveform data in the medical video stream data of the patient's brain; S3: creating an image processing model, and inputting the extracted key frame image containing the specified waveform data into the image processing model, wherein the image processing model recognizes key features in the pre-processed key frame image; S4: the image processing model performs image segmentation on the key feature area in the key frame image based on the identified key features, that is, separates the target area in the key frame image from the image; S5: The image processing model extracts and outputs designated features from the target area separated from the image, formats the output designated feature data, converts it into a designated data format, and exports it according to the designated data format to obtain continuous tissue data.

[0008] Preferably, the key frame extraction model in step S1 is a convolutional neural network model, and the convolutional neural network model is provided with an input layer, a combination layer of a convolutional layer + a pooling layer, a fully connected layer and an output layer, wherein the combination layer of the convolutional layer + the pooling layer includes a convolutional layer with a convolution kernel size of 5×5 and a step size of 2, a pooling layer with a pooling kernel size of 3×3 and a step size of 1, and the input of the fully connected layer is 120 nodes, and the output is 84 nodes; The input layer inputs raw image data of a medical video stream; The convolution layer is provided with a plurality of convolution kernels in the combination layer of the convolution layer + the pooling layer to perform convolution operation on the input image data to obtain local features in the image, and each convolution kernel generates a feature map; There are multiple pooling layers, each of which downsamples the feature map output by the convolutional layer above it, thereby reducing the spatial dimension and number of parameters of the feature map while retaining the specified features; The fully connected layer globally integrates the features extracted by the combination of the convolution layer + the pooling layer, maps them to the sample label space, and transmits the global integration results to the output layer for output.

[0009] Preferably, the specific process of step S2 is as follows: S21: Obtaining medical video stream data of the patient's brain and performing image denoising processing, and inputting the denoised medical video stream data into the trained key frame extraction model; S22: The key frame extraction model extracts key frame images containing designated waveform data from the patient's brain medical video stream data, and performs image enhancement processing on the key frame images.

[0010] Preferably, the specific process of denoising the patient's brain medical video stream data in step S21 is: S211: decomposing the observation signal in the patient's brain medical video stream image data into wavelet coefficients of different scales by discrete wavelet transform, and selecting an appropriate wavelet basis and decomposition layer number; S212: Setting a specified threshold, and obtaining a denoising coefficient for the wavelet coefficient based on a soft threshold function; S213: reconstructing the denoising coefficient into a denoised signal using an inverse wavelet transform; S214: Perform denoising processing on the patient's brain medical video stream data based on the reconstructed denoising signal.

[0011] Preferably, the specific process of performing image enhancement processing on the key frame image in step S22 is as follows: S221: Select multiple different Gaussian function standard deviations for the key frame image at multiple scales, and perform Gaussian blurring on the key frame image to obtain multiple blurred images L 1 ( x , y ), L 2 ( x , y ),···, L n ( x , y ), n is the scale quantity; S222: For images at each scale L 1 ( x , y ), L 2 ( x , y ),···, L n (x , y ) is logarithmically operated to obtain the reflection component of each scale, and we get Log [ R 1 ( x , y )], Log [ R 2 ( x , y )],···, Log [ R n ( x , y )]; S223: Perform weighted averaging on the reflection components of each scale to obtain a weighted average reflection component Log [ R ( x , y )] = Σ Weight ( i )* Log [ Ri ( x , y )]; S224: The weighted average reflection component Log [ R ( x , y )] is quantized to pixel values ​​ranging from 0 to 255 as the final output key frame image.

[0012] Preferably, the specific process of identifying the key features in the preprocessed key frame image in step S3 is as follows: S31: Processing continuous key frame images by Gaussian function to construct a continuous Gaussian scale space; S32: Calculate the difference of two adjacent Gaussian scale spaces in the continuous Gaussian scale space in step S31, and construct a Gaussian difference pyramid; S33: In the constructed Gaussian difference pyramid, a specified pixel point in the key frame image is compared with a specified number of neighboring pixels around it and a specified number of pixels at two scales to determine whether the specified pixel point is an extreme point, and if so, mark it as a candidate key point; S34: positioning the candidate key points, removing low-contrast points and edge response points therein, and assigning multiple main directions to each candidate key point after removing the low-contrast points and edge response points therein; S35: construct a vector of a specified dimension around each candidate key point after removing low-contrast points and edge response points therein, and count the gradient direction histogram of the surrounding area of ​​the key point to describe the local image structure.

[0013] Preferably, the specific process of performing image segmentation on the key feature area in the key frame image in step S4 is as follows: S41: describing the result of the local image structure based on the gradient direction histogram of the surrounding area of ​​the key point in step S35, and generating an initial region or superpixel by using the similarity of the pixels of the image; S42: according to the similarity criterion, merging adjacent regions to obtain a cut region; S43: Perform image segmentation based on the acquired segmentation area, and perform thinning, denoising, and hole filling processing on the boundary of the segmented image.

[0014] In a second aspect, a medical image processing system based on deep learning is provided, which is used to implement any one of the medical image processing methods based on deep learning, and includes a model creation module, a data acquisition module, a data preprocessing module, a key frame extraction model, an image processing model and a data formatting module, wherein the data acquisition module is connected to the preprocessing module, the data preprocessing module is connected to the key frame extraction model, the key frame extraction model is connected to the image processing model, and the image processing model is connected to the data formatting module; The model creation module is used to create the key frame extraction model and the image processing model; The data acquisition module is used to obtain the medical video stream data of the patient's brain; The data preprocessing module is used to perform data preprocessing on the patient's brain medical video stream data; The key frame extraction model is used to extract key frame images containing specified waveform data from the patient's brain medical video stream data; The image processing model identifies key features in the preprocessed key frame image and performs image segmentation on the key feature region in the key frame image, that is, separates the target region in the key frame image from the image; The data formatting module is used to perform data formatting processing on the output specified characteristic data, convert it into a specified data format, and export it according to the specified data format.

[0015] Preferably, the data acquisition module is a transcranial color Doppler ultrasound TCCD, which acquires the vascular structure image data of the patient's brain.

[0016] The beneficial effects of the present invention include: The medical image processing method and system based on deep learning provided by the present invention create a key frame extraction model, and use the labeled medical image data to train the key frame extraction model, obtain the patient's brain medical video stream data and perform data preprocessing, and input it into the key frame extraction model; create an image processing model, and input the extracted key frame image containing specified waveform data into the image processing model for key feature recognition; the image processing model performs image cutting on the key feature area in the key frame image based on the recognized key features; the image processing model extracts and outputs the specified features of the target area separated from the image, performs data formatting on the output specified feature data, converts it into a specified data format and exports it. The above process can obtain continuous blood flow data based on the image processing process of TCCD medical image data.

[0017] Firstly, the constructed key frame extraction model sets the input layer, the combination layer of convolution layer + pooling layer, the fully connected layer and the output layer. The combination layer of convolution layer + pooling layer includes a convolution layer with a convolution kernel size of 5×5 and a step size of 2, a pooling layer with a pooling kernel size of 3×3 and a step size of 1, the input of the fully connected layer is 120 nodes, and the output is 84 nodes. Through this key frame extraction model, the key frame images of the patient's brain medical video stream data can be accurately extracted, which provides a data basis for the image processing of the subsequent image processing model and ensures the effectiveness of the subsequent image processing process.

[0018] Secondly, the observation signal in the patient's brain medical video stream image data is decomposed into wavelet coefficients of different scales through discrete wavelet transform, and the appropriate wavelet basis and decomposition level are selected; the specified threshold is set, and the denoising coefficient is obtained for the wavelet coefficient based on the soft threshold function, and the denoising coefficient is reconstructed into a denoised signal using an inverse wavelet transform. The patient's brain medical video stream data is denoised based on the reconstructed denoised signal. This process achieves effective removal of noise data in the medical video stream image data and improves the accuracy of the results of subsequent image processing processes.

[0019] Thirdly, by selecting multiple different Gaussian function standard deviations for the key frame image at multiple scales, and performing Gaussian blur on the key frame image to obtain multiple blurred images, logarithmic operation is performed on the image at each scale to obtain the reflection component of each scale, and weighted averaging is performed on the reflection component of each scale to obtain the weighted average reflection component, and the weighted average reflection component is quantized into a pixel value ranging from 0 to 255, thereby achieving enhancement of the local features of the image and further improving the accuracy of the results of the subsequent image processing process.

[0020] Thirdly, the continuous key frame images are processed by Gaussian function to construct a continuous Gaussian scale space to construct a Gaussian difference pyramid; the specified pixel point in the key frame image is compared with the specified number of neighboring pixels around it and the specified number of pixels on two scales, the extreme points are marked as candidate key points, the low contrast points and edge response points are removed, and multiple main directions are assigned to each candidate key point; a vector of specified dimension is constructed around each candidate key point, and the gradient direction histogram of the surrounding area of ​​the key point is statistically analyzed to describe the local image structure, thereby realizing the accurate identification of key features in the key frame image and improving the accuracy of subsequent image segmentation.

[0021] Finally, the initial region or superpixel is generated based on the similarity of the image pixels; the adjacent regions are merged to obtain the cut region according to the similarity criterion; the image is cut based on the obtained cut region, and the boundaries of the cut image are refined, denoised, and the holes are filled, thereby achieving accurate segmentation of medical imaging data, and the specified features of the target area separated from the image are extracted and continuously output to obtain continuous data. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 Schematic diagram of the process of medical image processing based on deep learning of the present invention.

[0023] Figure 2 It is a schematic diagram of the process of identifying key features of the present invention.

[0024] Figure 3 Schematic diagram of the architecture of the deep learning-based medical image processing system of the present invention. DETAILED DESCRIPTION

[0025] The following is combined with Figure 1~Figure 3 The present invention is further described in detail: Example 1 See attached Figure 1 As shown, a medical image processing method based on deep learning comprises the following steps: S1: creating a key frame extraction model, training the key frame extraction model using labeled medical image data, and verifying the key frame extraction model using a verification set to determine whether specified performance parameters meet specified requirements; S2: obtaining the medical video stream data of the patient's brain and performing data preprocessing, inputting the preprocessed medical video stream data into the trained key frame extraction model, and the key frame extraction model extracting the key frame image containing the specified waveform data in the medical video stream data of the patient's brain; S3: creating an image processing model, and inputting the extracted key frame image containing the specified waveform data into the image processing model, so that the image processing model recognizes key features in the preprocessed key frame image; S4: The image processing model performs image segmentation on the key feature area in the key frame image based on the identified key features, that is, separating the target area in the key frame image from the image; S5: The image processing model extracts and outputs the specified features of the target area separated from the image, formats the output specified feature data, converts it into a specified data format, and exports it according to the specified data format to obtain continuous tissue data.

[0026] By creating a key frame extraction model and training the key frame extraction model with labeled medical image data, the patient's brain medical video stream data is obtained and preprocessed, and then input into the key frame extraction model; an image processing model is created, and the extracted key frame image containing the specified waveform data is input into the image processing model for key feature recognition; the image processing model performs image segmentation on the key feature area in the key frame image based on the recognized key features; the image processing model extracts and outputs the specified features of the target area separated from the image, formats the output specified feature data, converts it into a specified data format, and exports it. The above process can obtain continuous blood flow data based on the image processing process of medical imaging data such as TCD and TCCD. In this embodiment, the key frame extraction model in step S1 is a convolutional neural network model, which is provided with an input layer, a combination layer of convolutional layer + pooling layer, a fully connected layer and an output layer. The combination layer of convolutional layer + pooling layer includes a convolution layer with a convolution kernel size of 5×5 and a step size of 2, a pooling layer with a pooling kernel size of 3×3 and a step size of 1, and the input of the fully connected layer is 120 nodes and the output is 84 nodes.

[0027] The input layer inputs the original image data of the medical video stream. The convolution layer is provided with multiple layers. A series of convolution kernels in the combination layer of the convolution layer + the pooling layer are used to perform convolution operations on the input image data to obtain local features in the image. Each convolution kernel generates a feature map. The pooling layer is provided with multiple layers. Each pooling layer downsamples the feature map output by the convolution layer above it, and reduces the spatial dimension and number of parameters of the feature map while retaining the specified features. The fully connected layer globally integrates the features extracted by the combination layer of the convolution layer + the pooling layer, maps them to the sample label space, and transmits the global integration results to the output layer for output. The key frame extraction model realizes the accurate extraction of the key frame images of the patient's brain medical video stream data, provides a data basis for the image processing of the subsequent image processing model, and ensures the effectiveness of the subsequent image processing process.

[0028] Example 2 Based on Example 1, the specific process of step S2 is as follows: S21: Obtaining medical video stream data of the patient's brain and performing image denoising processing, and inputting the denoised medical video stream data into the trained key frame extraction model; S22: The key frame extraction model extracts key frame images containing designated waveform data from the patient's brain medical video stream data, and performs image enhancement processing on the key frame images.

[0029] In this embodiment, the specific process of denoising the patient's brain medical video stream data in step S21 is as follows: S211: decomposing the observation signal in the patient's brain medical video stream image data into wavelet coefficients of different scales by discrete wavelet transform, and selecting an appropriate wavelet basis and decomposition layer number; S212: Setting a specified threshold, and obtaining a denoising coefficient for the wavelet coefficient based on a soft threshold function; S213: reconstructing the denoising coefficient into a denoised signal using an inverse wavelet transform; S214: Perform denoising processing on the patient's brain medical video stream data based on the reconstructed denoising signal.

[0030] The above-mentioned discrete wavelet transform is used to decompose the observed signal in the patient's brain medical video stream image data into wavelet coefficients of different scales, and an appropriate wavelet basis and decomposition layer number are selected; a specified threshold is set, and a denoising coefficient is obtained for the wavelet coefficient based on a soft threshold function, and the denoising coefficient is reconstructed into a denoised signal using an inverse wavelet transform. The patient's brain medical video stream data is denoised based on the reconstructed denoised signal, thereby achieving effective removal of noise data in the medical video stream image data and improving the accuracy of the results of subsequent image processing processes.

[0031] In this embodiment, the specific process of performing image enhancement processing on the key frame image in step S22 is as follows: S221: Select multiple different Gaussian function standard deviations for the key frame image at multiple scales, and perform Gaussian blurring on the key frame image to obtain multiple blurred images L 1 ( x , y ), L 2 ( x , y ),···, L n ( x , y ), n is the scale quantity; S222: For images at each scale L 1 ( x , y ), L 2 ( x , y ),···, L n ( x , y ) is logarithmically operated to obtain the reflection component of each scale, and we get Log [ R 1 ( x , y )], Log [ R 2 ( x , y )],···, Log [ R n ( x , y )]; S223: Perform weighted averaging on the reflection components of each scale to obtain a weighted average reflection component Log [ R ( x , y )] = Σ Weight ( i )* Log [ Ri ( x , y )]; S224: The weighted average reflection component Log [ R ( x ,y )] is quantized to pixel values ​​ranging from 0 to 255 as the final output key frame image.

[0032] Example 3 Based on Example 1 or Example 2, see Figure 2 As shown, the specific process of identifying the key features in the preprocessed key frame image in step S3 is as follows: S31: Processing continuous key frame images by Gaussian function to construct a continuous Gaussian scale space; S32: Calculate the difference of two adjacent Gaussian scale spaces in the continuous Gaussian scale space in step S31, and construct a Gaussian difference pyramid; S33: In the constructed Gaussian difference pyramid, a specified pixel point in the key frame image is compared with a specified number of neighboring pixels around it and a specified number of pixels at two scales to determine whether the specified pixel point is an extreme point, and if so, mark it as a candidate key point; S34: positioning the candidate key points, removing low-contrast points and edge response points therein, and assigning multiple main directions to each candidate key point after removing the low-contrast points and edge response points therein; S35: construct a vector of a specified dimension around each candidate key point after removing low-contrast points and edge response points therein, and count the gradient direction histogram of the surrounding area of ​​the key point to describe the local image structure.

[0033] In this embodiment, the specific process of performing image segmentation on the key feature area in the key frame image in step S4 is as follows: S41: describing the result of the local image structure based on the gradient direction histogram of the surrounding area of ​​the key point in step S35, and generating an initial region or superpixel by using the similarity of the pixels of the image; S42: according to the similarity criterion, merging adjacent regions to obtain a cut region; S43: Perform image segmentation based on the acquired segmentation area, and perform thinning, denoising, and hole filling processing on the boundary of the segmented image.

[0034] In another implementation of this embodiment, the key information area is automatically cut out by extracting the imported video stream data frame by frame, thereby ensuring the speed of key frame image extraction and the accuracy of cropping, and providing high-quality image data for the subsequent text recognition module.

[0035] A medical image processing system based on deep learning, used to implement any one of the medical image processing methods based on deep learning, see Figure 3As shown, it includes a model creation module, a data acquisition module, a data preprocessing module, a key frame extraction model, an image processing model and a data formatting module. The data acquisition module is connected to the preprocessing module, the data preprocessing module is connected to the key frame extraction model, the key frame extraction model is connected to the image processing model, and the image processing model is connected to the data formatting module.

[0036] The model creation module is used to create the key frame extraction model and the image processing model, the data acquisition module is used to obtain the patient's brain medical video stream data, and the data preprocessing module is used to preprocess the patient's brain medical video stream data. The key frame extraction model is used to extract the key frame image containing the specified waveform data in the patient's brain medical video stream data. The image processing model identifies the key features in the preprocessed key frame image and performs image cutting on the key feature area in the key frame image, that is, separates the target area in the key frame image from the image. The data formatting module is used to format the output specified feature data, convert it into a specified data format, and export it according to the specified data format. The data acquisition module is a transcranial color Doppler ultrasound TCCD, which obtains the vascular structure image data of the patient's brain.

[0037] There is also an optical character recognition module, which is based on a deep learning model and achieves high-precision character recognition. It can extract text content and its location information, which provides a data basis for the subsequent generation of structured data. After obtaining the text content and coordinate position, it is split according to certain rules and organized into a table format to facilitate later statistics and analysis. After the statistical analysis is completed, the system automatically generates a structured table based on the extracted text and location information, and supports export in xlsx format, which is convenient for further analysis and storage of data.

[0038] In summary, the medical image processing method and system based on deep learning provided by the present invention, the constructed key frame extraction model sets the input layer, the combination layer of the convolution layer + pooling layer, the fully connected layer and the output layer, and the key frame extraction model realizes the accurate extraction of the key frame image of the patient's brain medical video stream data, which provides the data basis for the image processing of the subsequent image processing model, and ensures the effectiveness of the subsequent image processing process. The observation signal in the patient's brain medical video stream image data is decomposed into wavelet coefficients of different scales by discrete wavelet transform; the specified threshold is set, the denoising coefficient is obtained based on the soft threshold function for the wavelet coefficient, the denoising coefficient is reconstructed into a denoising signal using the inverse wavelet transform, and the process of denoising the patient's brain medical video stream data based on the reconstructed denoising signal realizes the effective removal of noise data in the medical video stream image data, and improves the accuracy of the results of the subsequent image processing process.

[0039] By selecting multiple different Gaussian function standard deviations for the key frame image at multiple scales, and performing Gaussian blur on the key frame image to obtain multiple blurred images, logarithmic operations are performed on the image at each scale to obtain the reflection component of each scale and perform weighted averaging, and the weighted average reflection component is obtained and quantized into a specified range of pixel values, thereby realizing the enhancement of the local features of the image and further improving the accuracy of the results of the subsequent image processing process. The continuous key frame images are processed by Gaussian functions to construct a Gaussian difference pyramid in a continuous Gaussian scale space. The specified pixel point in the key frame image is compared with the specified number of neighboring pixels around it and the specified number of pixels at two scales, and the extreme point is marked as a candidate key point, and the low contrast points and edge response points are removed, and multiple main directions are assigned to each candidate key point. A vector of a specified dimension is constructed around each candidate key point, and the gradient direction histogram of the surrounding area of ​​the key point is statistically analyzed to describe the local image structure, thereby realizing the accurate recognition of the key features in the key frame image and improving the accuracy of subsequent image segmentation. The initial region or superpixel is generated based on the similarity of the pixel points of the image; the adjacent regions are merged to obtain the cut region according to the similarity criterion; the image is cut based on the obtained cut region, and the boundary of the cut image is refined, denoised and the holes are filled, thereby achieving accurate segmentation of medical image data, and the specified features of the target area separated from the image are extracted and continuously output to obtain continuous data.

Claims

1. A medical image processing method based on deep learning, characterized in that: The following steps are involved: S1: creating a key frame extraction model, and training the key frame extraction model using labeled medical image data, and verifying the key frame extraction model using a verification set to determine whether specified performance parameters meet specified requirements; S2: obtaining the medical video stream data of the patient's brain and performing data preprocessing, inputting the preprocessed medical video stream data into the trained key frame extraction model, wherein the key frame extraction model extracts the key frame image containing the specified waveform data in the medical video stream data of the patient's brain; S3: creating an image processing model, and inputting the extracted key frame image containing the specified waveform data into the image processing model, wherein the image processing model recognizes key features in the pre-processed key frame image; S4: the image processing model performs image segmentation on the key feature area in the key frame image based on the identified key features, that is, separates the target area in the key frame image from the image; S5: The image processing model extracts and continuously outputs designated features from the target area separated from the image, formats the output designated feature data, converts it into a designated data format, and exports it according to the designated data format to obtain continuous tissue data.

2. The medical image processing method based on deep learning according to claim 1, characterized in that: The key frame extraction model in step S1 is a convolutional neural network model, which is provided with an input layer, a combination layer of a convolutional layer + a pooling layer, a fully connected layer and an output layer, wherein the combination layer of the convolutional layer + the pooling layer includes a convolutional layer with a convolution kernel size of 5×5 and a step size of 2, a pooling layer with a pooling kernel size of 3×3 and a step size of 1, and the input of the fully connected layer is 120 nodes and the output is 84 nodes; The input layer inputs raw image data of a medical video stream; The convolution layer is provided with a plurality of convolution kernels in the combination layer of the convolution layer + the pooling layer to perform convolution operation on the input image data to obtain local features in the image, and each convolution kernel generates a feature map; There are multiple pooling layers, each of which downsamples the feature map output by the convolutional layer above it, thereby reducing the spatial dimension and number of parameters of the feature map while retaining the specified features; The fully connected layer globally integrates the features extracted by the combination of the convolution layer + the pooling layer, maps them to the sample label space, and transmits the global integration results to the output layer for output.

3. The medical image processing method based on deep learning according to claim 1, characterized in that: The specific process of step S2 is as follows: S21: Obtaining medical video stream data of the patient's brain and performing image denoising processing, and inputting the denoised medical video stream data into the trained key frame extraction model; S22: The key frame extraction model extracts key frame images containing designated waveform data from the patient's brain medical video stream data, and performs image enhancement processing on the key frame images.

4. The medical image processing method based on deep learning according to claim 3, characterized in that: The specific process of denoising the patient's brain medical video stream data in step S21 is as follows: S211: decomposing the observation signal in the patient's brain medical video stream image data into wavelet coefficients of different scales by discrete wavelet transform, and selecting an appropriate wavelet basis and decomposition layer number; S212: Setting a specified threshold, and obtaining a denoising coefficient for the wavelet coefficient based on a soft threshold function; S213: reconstructing the denoising coefficient into a denoised signal using an inverse wavelet transform; S214: Perform denoising processing on the patient's brain medical video stream data based on the reconstructed denoising signal.

5. The medical image processing method based on deep learning according to claim 3, characterized in that: The specific process of performing image enhancement processing on the key frame image in step S22 is as follows: S221: Select multiple different Gaussian function standard deviations for the key frame image at multiple scales, and perform Gaussian blurring on the key frame image to obtain multiple blurred images L 1( x , y ), L 2( x , y ), ···, L n ( x , y ), n is the scale quantity; S222: For images at each scale L 1( x , y ), L 2( x , y ), ···, L n ( x , y ) is logarithmically operated to obtain the reflection component of each scale, and we get Log [ R 1( x , y )], Log [ R 2( x , y )],···, Log [ R n ( x , y )]; S223: Perform weighted averaging on the reflection components of each scale to obtain a weighted average reflection component Log [ R ( x , y )] =Σ Weight ( i )* Log [ Ri ( x , y )]; S224: The weighted average reflection component Log [ R ( x , y )] is quantized to pixel values ​​ranging from 0 to 255 as the final output key frame image.

6. The medical image processing method based on deep learning according to claim 5, characterized in that: The specific process of identifying the key features in the preprocessed key frame image in step S3 is as follows: S31: Processing continuous key frame images by Gaussian function to construct a continuous Gaussian scale space; S32: Calculate the difference of two adjacent Gaussian scale spaces in the continuous Gaussian scale space in step S31, and construct a Gaussian difference pyramid; S33: In the constructed Gaussian difference pyramid, a specified pixel point in the key frame image is compared with a specified number of neighboring pixels around it and a specified number of pixels at two scales to determine whether the specified pixel point is an extreme point, and if so, mark it as a candidate key point; S34: positioning the candidate key points, removing low-contrast points and edge response points therein, and assigning multiple main directions to each candidate key point after removing the low-contrast points and edge response points therein; S35: construct a vector of a specified dimension around each candidate key point after removing low-contrast points and edge response points therein, and count the gradient direction histogram of the surrounding area of ​​the key point to describe the local image structure.

7. The medical image processing method based on deep learning according to claim 6, characterized in that: The specific process of performing image segmentation on the key feature area in the key frame image in step S4 is as follows: S41: describing the result of the local image structure based on the gradient direction histogram of the surrounding area of ​​the key point in step S35, and generating an initial region or superpixel by using the similarity of the pixels of the image; S42: according to the similarity criterion, merging adjacent regions to obtain a cut region; S43: Perform image segmentation based on the acquired segmentation area, and perform thinning, denoising, and hole filling processing on the boundary of the segmented image.

8. A medical image processing system based on deep learning, used to implement a medical image processing method based on deep learning according to any one of claims 1 to 7, characterized in that: It includes a model creation module, a data acquisition module, a data preprocessing module, a key frame extraction model, an image processing model and a data formatting module, wherein the data acquisition module is connected to the preprocessing module, the data preprocessing module is connected to the key frame extraction model, the key frame extraction model is connected to the image processing model, and the image processing model is connected to the data formatting module; The model creation module is used to create the key frame extraction model and the image processing model; The data acquisition module is used to obtain the medical video stream data of the patient's brain; The data preprocessing module is used to perform data preprocessing on the patient's brain medical video stream data; The key frame extraction model is used to extract key frame images containing specified waveform data from the patient's brain medical video stream data; The image processing model identifies key features in the preprocessed key frame image and performs image segmentation on the key feature region in the key frame image, that is, separates the target region in the key frame image from the image; The data formatting module is used to perform data formatting processing on the output specified characteristic data, convert it into a specified data format, and export it according to the specified data format.

9. A medical image processing system based on deep learning according to claim 8, characterized in that: The data acquisition module is a transcranial color Doppler ultrasound TCCD, which acquires the vascular structure image data of the patient's brain.

Images