WO2021128230A1

WO2021128230A1 - Deep learning-based medical image processing method and system, and computer device

Info

Publication number: WO2021128230A1
Application number: PCT/CN2019/128924
Authority: WO
Inventors: 刘非
Original assignee: 上海昕健医疗技术有限公司
Priority date: 2019-12-27
Filing date: 2019-12-27
Publication date: 2021-07-01

Abstract

A deep learning-based medical image processing method and system, and a computer device. A deep learning model design method comprises the following steps: collecting image data (S11); annotating the image data (S12); dividing an initial annotated data set (S13); selecting and designing a deep learning model (S14); adjusting a deep learning initial model hyperparameter and training a deep learning initial model (S15); testing a deep learning trained model (S16); and determining whether a test coefficient reaches a fixed parameter value or more (S17). According to the method, a complex part image can be segmented in a quick and high-precision manner, thereby improving working efficiency and diagnosis accuracy of doctors.

Description

Medical image processing method, system and computer equipment based on deep learning

Technical field

The present invention relates to the field of medical image processing, in particular to a medical image processing method, system and computer equipment based on deep learning.

Background technique

Accurate medical image segmentation is a solid foundation for subsequent doctors to diagnose and formulate surgical plans. If the results of image segmentation are biased, it will affect the safety and effectiveness of the operation. Therefore, efficient and high-precision image segmentation methods are essential. However, the current image segmentation for complex parts is still unable to obtain good results.

For example, the ankle includes 26 bones such as the calcaneus, talus, navicular, internal cuneiform, intermediate cuneiform, external cuneiform, cuboid, five metatarsals, and phalanges (including 14 bones in the phalanges). Among these parts, the bones are closely connected, the space between the bones at the bone joints is small, and the gray scale of the bone joint is similar to the gray scale of the surrounding tissues, which makes the segmentation of the bone and joint difficult. Using traditional methods to segment these 26 bones is difficult to achieve satisfactory results. It is easy to cause incomplete segmentation at the bone joints, leakage of segmentation boundaries, etc., which requires cumbersome subsequent editing and processing; manual calibration usually requires a lot of cost. The manpower, material resources and time required, and the calibration results of different people have certain differences, which will affect the accuracy of bone and joint segmentation.

Currently commonly used methods based on the idea of maximum flow and minimum segmentation, watershed methods, etc., for the segmentation of ankle multi-targets, a large number of foreground and background markers need to be manually added; methods based on template matching or registration not only take a long time to calculate, but also the segmentation effect is difficult. Guarantee.

Therefore, it is indeed necessary to provide a medical image processing method, system and computer equipment based on deep learning to overcome the defects in the prior art.

Summary of the invention

The purpose of the present invention is to provide a medical image processing method, system and computer equipment based on deep learning that can quickly and accurately segment images of complex parts.

In order to achieve the above objective, the present invention provides a deep learning model design method, including the following steps: S11, collecting two-dimensional medical image data containing the part to be segmented; S12, labeling the image data of the region of interest to obtain the initial label Data set; S13, divide the initial labeled data set into a training set and a test set; S14, select and design a deep learning model to obtain an initial deep learning model; the specific steps are as follows: select a deep learning model; according to the selected deep learning Model, add an adaptive layer to the first layer of the network to obtain a deep learning design model; according to the deep learning design model, add a custom loss function loss to the tail layer of the network to obtain the initial deep learning model; S15. Adjust Deep learning initial model hyperparameters, training the deep learning initial model according to the obtained training set data to obtain a deep learning training model; S16, testing the deep learning training model according to the obtained test set data , Calculate the test coefficient; S17, determine whether the test coefficient reaches a fixed parameter value or more, the judgment result is yes, then the model parameters after the deep learning training meet the requirements, the training ends, and the final deep learning model is obtained; otherwise, deep learning training After the model parameters do not meet the requirements, return to step S15.

Further, the activation function of the adaptive layer is

Where x is the input of the adaptive layer, and τ is the adaptive threshold of x; the loss function

Where ω is a constant, which is a custom hyperparameter; m represents the segmentation category; Vol(A_perd _i ) represents the predicted volume of the i-th category of bone; Vol(A_true _i ) represents the i-th category of bone artificial The marked volume; Vol(A_pred_true _i ) represents the correct volume predicted by the i-th category; Vol(A_pred _i ∪A_true _i ) represents the volume obtained after the merging of the bone predicted by the i-th category with the artificially labeled bone.

Further, the method for selecting a deep learning model includes the following steps: S31. Divide the training set data into N pieces, where N-1 pieces are used as training data and 1 piece is used as verification data, where N is an integer greater than 1; S32 Select a deep learning training model as the preliminary selected deep learning model; S33. According to the obtained training data, train the preliminary selected deep learning model, and verify the preliminary selected deep learning model according to the obtained verification data. Record the error at the same time; S34, non-repetitively select another piece of the N training set data in step S31 as the verification data, and the remaining N-1 pieces as the training data, repeat the operation of step S33; S35, steps S33 and S34 repeat After N times, record the average of the errors recorded for N times to obtain the average error of the selected deep learning model; S36, select other deep learning models as the preliminary selected deep learning models, and repeat steps S33 to S35 to obtain other deep learning The average error of the model; S37. Select the deep learning model with the smallest average error as the final selected deep learning model.

Further, the calculation steps of the adaptive threshold τ are as follows: S41, traverse the input data of the first layer of the network, and calculate the average value μ; S42, use the average value μ as the threshold to divide the input data of the first layer of the network into the foreground and the background. Part, calculate the mean values t_fore and t_back of the foreground part and the background part respectively; S43, calculate a new threshold μ_new according to the obtained mean value of the foreground part and the mean value of the background part, the threshold μ_new=(t_fore+t_back)/2 S44, calculate the diff according to the obtained new threshold μ_new, the diff=μ_new-μ, and assign the value of μ_new to μ; S45, repeat steps S42 to S44 until the diff is less than the set threshold and the iteration stops, Obtain an adaptive threshold τ.

A medical image processing method based on deep learning, which is a deep learning model designed based on the deep learning model design method of claim 1, comprising the following steps: reading two-dimensional medical image data; Preprocess the three-dimensional medical image data to obtain the initial data; extract the data of the region of interest according to the obtained initial data; scale the data of the region of interest to a fixed size through the interpolation method to obtain the scaled region of interest data; The scaled region of interest data is standardized to obtain input data of a deep learning model; the final deep learning model is run to obtain an initial segmentation result; the initial segmentation result is post-processed to obtain a final segmentation result.

Further, the preprocessing method is filtering processing.

Further, the method for standardizing the scaled region of interest data includes the following steps: obtaining the pixel value x _{i of the} scaled region of interest data according to the scaled region of interest data; and according to the obtained pixels Calculate the mean value μ and variance σ of the value x _i _{; calculate and obtain the normalized pixel value y i} according to the obtained mean value μ and variance σ, the

Assign the normalized pixel value _yi to the pixel value x _i as the normalized pixel value, that is, let x _i =y _i .

A medical image processing system based on deep learning, the system comprising: a reading module for reading two-dimensional medical image data; a preprocessing module for preprocessing the read two-dimensional medical image data, Obtain training data; an extraction module for extracting data of the region of interest according to the obtained training data; a scaling module for scaling the data of the region of interest to a fixed size through an interpolation method to obtain the scaled region of interest data ; Standardization module, used to standardize the scaled region of interest data to obtain input data of the deep learning model; Run module, used to run the final deep learning model to obtain the initial segmentation results; Post-processing module, used to The initial segmentation result is post-processed to obtain the final segmentation result.

A computer device includes a memory and a processor, and a computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented: reading two-dimensional medical image data; Perform preprocessing of the two-dimensional medical image data of the two-dimensional medical image to obtain training data; extract the region of interest data according to the obtained training data; scale the region of interest data to a fixed size through an interpolation method to obtain the scaled region of interest data Standardize the scaled region of interest data to obtain the input data of the deep learning model; run the final deep learning model to obtain the initial segmentation result; post-process the initial segmentation result to obtain the final segmentation result.

A computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented: reading two-dimensional medical image data; preprocessing the read two-dimensional medical image data, Obtain the training data; extract the region of interest data according to the obtained training data; scale the region of interest data to a fixed size by interpolation method to obtain the scaled region of interest data; convert the scaled region of interest Standardize data processing to obtain the input data of the deep learning model; run the final deep learning model to obtain the initial segmentation result;

Perform post-processing on the initial segmentation result to obtain the final segmentation result.

The medical image processing method, system and computer equipment based on deep learning of the present invention adopts a fully automatic segmentation algorithm, which can automatically and finely separate the calcaneus, talus, navicular bone, and internal cuneiform from the entire ankle within tens of seconds 26 bones, including the middle cuneiform, the external cuneiform, the cuboid, the first metatarsal, the second metatarsal, the third metatarsal, the fourth metatarsal, the fifth metatarsal and the phalanges, for the doctor’s reference. , Perform a specific analysis of the patient to obtain the diagnosis result, thereby reducing the workload of the doctor, improving the doctor's work efficiency and the accuracy of the diagnosis.

Description of the drawings

Fig. 1 is a schematic diagram of a method for designing a deep learning model for medical image processing according to the present invention.

Figure 2 is a schematic diagram of the process of selecting and designing the deep learning model in Figure 1 to obtain the initial deep learning model.

Fig. 3 is a schematic diagram of the process of selecting the deep learning model in Fig. 2.

Fig. 4 is a schematic flowchart of the calculation method of the adaptive threshold τ in Fig. 2.

Fig. 5 is a schematic flowchart of a medical image processing method based on deep learning of the present invention.

FIG. 6 is a schematic flowchart of the method for normalizing the zoomed region of interest data in FIG. 5.

Detailed ways

In order to make the above objectives, features and advantages of the present invention more obvious and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

Example one:

As shown in Figure 1, the first embodiment provides a deep learning model design method for medical image processing, including the following steps:

S11. Collect two-dimensional medical image data containing the part to be segmented;

S12. Annotate the image data of the region of interest to obtain an initial annotated data set;

S13. Divide the initial labeled data set into a training set and a test set;

S14. Select and design a deep learning model to obtain an initial deep learning model;

S15. Adjust the hyperparameters of the deep learning initial model, and train the deep learning initial model according to the obtained training set data to obtain the deep learning trained model;

S16. Test the model after the deep learning training according to the obtained test set data, and calculate a test coefficient;

S17. Determine whether the test coefficient reaches a fixed parameter value or more, and the judgment result is yes, then the model parameters after the deep learning training meet the requirements, and the training ends, and the final deep learning model is obtained; otherwise, the model parameters after the deep learning training do not meet the requirements , Return to step S15.

In the first embodiment, the part to be divided in step S11 is the ankle part, the number of the two-dimensional medical image data is more than 100 sets, and the size of each set of data may be 512*512 pixels*100 sheets.

The marking of the image data of the region of interest in step S12 is to organize some qualified physicians to manually outline the calcaneus, talus, navicular bone, internal cuneiform, and intermediate cuneiform in the image data of the region of interest. 26 bones including the external cuneiform, cuboid, first metatarsal, second metatarsal, third metatarsal, fourth metatarsal, fifth metatarsal, and phalanges, to obtain the initial labeled data set.

In step S13, the initial labeled data set is divided into a training set and a test set, and the division operation may be performed in a random allocation manner, and the allocation ratio of the training set and the test set may be 80% and 20%.

The test coefficient in step S16 is the index DICE coefficient of the test set data segmentation result; the fixed parameter value in step S17 is 90%.

As shown in Figure 2, the method of selecting and designing a deep learning model in step S14 to obtain an initial deep learning model includes the following steps:

S21. Select a deep learning model, the deep learning model includes but not limited to FCN, Res-VNet, U-Net, and V-Net models, and the method for selecting the deep learning model is to pass the training set data through N-fold cross-validation To evaluate the robustness of the selected deep learning model, choose a deep learning model with better robustness;

S22. According to the selected deep learning model, an adaptive layer is added to the first layer of the network to obtain a deep learning design model; the activation function of the adaptive layer is

Among them, x is the input of the adaptive layer, and τ is the adaptive threshold of x;

S23. Add a custom loss function loss to the tail layer of the network according to the deep learning design model to obtain an initial deep learning model; the loss function

Where ω is a constant, which is a custom hyperparameter; m represents the segmentation category, for example: define the calcaneus as category 1, talus as category 2, navicular bone as category 3, and so on; Vol(A_perd _i ) represents the first i categories predicted to bone volume; vol (A_true _i) represents the volume of the i-th category labeled artificial bone; vol (A_pred_true _i) denotes the i th class prediction correct volume; vol (a_pred _{_i} ∪A_true _i ) Represents the volume obtained after combining the predicted bone of the i-th category with the artificially labeled bone.

As shown in Fig. 3, the method for selecting a deep learning model in step S21 includes the following steps:

S31. Divide the training set data into N pieces, where N-1 pieces are used as training data, and 1 piece is used as verification data, where N is an integer greater than 1.

S32. Select a deep learning training model as the preliminary selected deep learning model;

S33. Train the preliminarily selected deep learning model according to the obtained training data, verify the preliminarily selected deep learning model according to the obtained verification data, and record the error at the same time;

S34. Non-repetitively select another piece of data in the N training set data in step S31 as verification data, and the remaining N-1 pieces as training data, and repeat the operation of step S33;

After S35, steps S33 and S34 are repeated N times, the average value of the errors recorded for N times is recorded to obtain the average error of the selected deep learning model;

S36. Select other deep learning models as the preliminary selected deep learning models, and repeat steps S33 to S35 to obtain the average error of other deep learning models;

S37. Select the deep learning model with the smallest average error as the final selected deep learning model.

Wherein, the value range of N is 3-10, preferably, the value range of N is 5-10, and more preferably, the value of N in the first embodiment is 10.

As shown in Fig. 4, the calculation steps of the adaptive threshold τ in step S22 are as follows:

S41. Traverse the input data of the first layer of the network and calculate the average value μ;

S42. Use the average value μ as a threshold value to divide the first layer input data of the network into two parts, a foreground part and a background part, and calculate the mean values t_fore and t_back of the foreground part and the background part respectively;

S43. Calculate a new threshold μ_new according to the obtained average value of the foreground part and the average value of the background part, the threshold μ_new=(t_fore+t_back)/2;

S44. Calculate diff according to the obtained new threshold μ_new, the diff=μ_new-μ, and assign the value of μ_new to μ, that is, let μ=μ_new;

S45. Repeat steps S42 to S44 until the diff is less than the set threshold and the iteration stops, and the adaptive threshold τ in the activation function is obtained, and the adaptive threshold τ is the obtained final μ value.

Wherein, the threshold value set in step S45 has a value range of 0.01-10. Preferably, the threshold value set in the first embodiment is 0.1.

Embodiment two:

As shown in Figure 5, the second embodiment provides a medical image processing method based on the deep learning model designed in the first embodiment, including the following steps:

S51. Reading two-dimensional medical image data, where the two-dimensional medical image data is CT image data conforming to the DICOM3.0 standard;

S52. Preprocess the read two-dimensional medical image data to obtain initial data;

S53. Extract the region of interest data according to the obtained initial data;

S54. Scale the data of the region of interest to a fixed size by an interpolation method to obtain the data of the region of interest after scaling, and the fixed size may be 512*512 pixels;

S55: Standardize the scaled region of interest data to obtain input data of the deep learning model;

S56: Run the final deep learning model obtained in the first embodiment to obtain an initial segmentation result;

S57. Perform post-processing on the initial segmentation result to obtain a final segmentation result.

The preprocessing method in step S52 is filtering processing, such as median filtering, mean filtering, Gaussian filtering, bilateral filtering or other filtering methods.

The method of extracting the region of interest data in step S53 includes: automatically searching all connected regions of the image according to the obtained initial data and according to a set threshold, and growing all connected regions into a separate container; according to the size of each connected region Judge the area of the patient’s ankle with the direction, and extract the area of the ankle as the area of interest data.

The method of post-processing the initial segmentation result in step S57 is to modify part of the over-segmented and under-segmented regions, filter out small mis-segmented impurities, and process them through algorithms such as morphological expansion, erosion, and filling. Obtain the final segmentation result.

As shown in FIG. 6, the method for standardizing the zoomed region of interest data in step S55 includes the following steps:

_{S61. Obtain a pixel value x i of the} zoomed region of interest data according to the zoomed region of interest data;

_S62: Calculate the mean value μ and variance σ of the obtained pixel value x i;

_{S63. Calculate and obtain a standardized pixel value y i} according to the obtained mean value μ and variance σ, and

S64. Assign the normalized pixel value _yi to the pixel value x _i as the normalized pixel value, that is, set x _i =y _i .

Due to the individual differences of patients and the limitations of doctors' observation of two-dimensional image information, it is inevitable that judgment errors will occur. The present invention adopts a medical image processing method based on deep learning and a fully automatic segmentation algorithm, which can automatically and finely separate the calcaneus, talus, navicular bone, internal cuneiform, and intermediate cuneiform from the entire ankle within tens of seconds. 26 bones, including the external cuneiform, cuboid, first metatarsal, second metatarsal, third metatarsal, fourth metatarsal, fifth metatarsal, and phalanges, for the doctor’s reference. The diagnosis results are analyzed, thereby reducing the workload of the doctors and improving the working efficiency of the doctors and the accuracy of the diagnosis.

Example three:

The third embodiment provides a medical image processing system based on deep learning, and the system includes:

A reading module for reading two-dimensional medical image data, the two-dimensional medical image data being CT image data complying with the DICOM3.0 standard;

The preprocessing module is used to preprocess the read two-dimensional medical image data to obtain training data;

The extraction module is used to extract the data of the region of interest according to the obtained training data;

A scaling module, configured to scale the region of interest data to a fixed size through an interpolation method to obtain scaled region of interest data, the fixed size may be 512*512 pixels;

The standardization module is used to standardize the scaled region of interest data to obtain input data of the deep learning model;

The running module is used to run the final deep learning model obtained in the first embodiment to obtain the initial segmentation result;

The post-processing module is used to perform post-processing on the initial segmentation result to obtain the final segmentation result.

The various modules in the medical image processing system based on deep learning can be implemented in whole or in part by software, hardware, and a combination thereof. The foregoing modules may be embedded in the form of hardware or independent of the processor in the computer device, or may be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the foregoing modules.

The implementation principles and technical effects of the medical image processing system based on deep learning provided in the third embodiment are similar to those in the second embodiment of the method, and will not be repeated here.

Embodiment four:

The fourth embodiment provides a computer device, the computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when the processor executes the computer program:

S71. Reading two-dimensional medical image data, where the two-dimensional medical image data is CT image data conforming to the DICOM3.0 standard;

S72. Preprocess the read two-dimensional medical image data to obtain training data;

S73. Extract the region of interest data according to the obtained training data;

S74. Scale the data of the region of interest to a fixed size by an interpolation method to obtain the data of the region of interest after scaling, and the fixed size may be 512*512 pixels;

S75. Standardize the scaled region of interest data to obtain input data of the deep learning model;

S76. Run the final deep learning model obtained in the first embodiment to obtain an initial segmentation result;

S77. Perform post-processing on the initial segmentation result to obtain a final segmentation result.

The implementation principles and technical effects of the computer device provided in the fourth embodiment are similar to those in the second embodiment of the method, and will not be repeated here.

Example five

The fifth embodiment provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

S81. Read two-dimensional medical image data, where the two-dimensional medical image data is CT image data that meets the DICOM3.0 standard;

S82. Preprocess the read two-dimensional medical image data to obtain training data;

S83. Extract the region of interest data according to the obtained training data;

S84. Scale the data of the region of interest to a fixed size by an interpolation method to obtain the data of the region of interest after scaling, and the fixed size may be 512*512 pixels;

S85. Standardize the scaled region of interest data to obtain input data of the deep learning model;

S86: Run the final deep learning model obtained in the first embodiment to obtain an initial segmentation result;

S87. Perform post-processing on the initial segmentation result to obtain a final segmentation result.

The implementation principle and technical effect of the computer-readable storage medium provided in the fifth embodiment are similar to those of the second method described above, and will not be repeated here.

In summary, the above are only preferred embodiments of the present invention, and should not be used to limit the scope of the present invention. That is, all simple equivalent changes and modifications made in accordance with the claims of the present invention and the contents of the description of the present invention are all It should still fall within the scope of the invention patent.

Claims

A method for designing a deep learning model is characterized in that it includes the following steps:

S11. Collect two-dimensional medical image data containing the part to be segmented;

S12. Annotate the image data of the region of interest to obtain an initial annotated data set;

S13. Divide the initial labeled data set into a training set and a test set;

S14. Select and design a deep learning model to obtain an initial deep learning model; the specific steps are as follows: select a deep learning model; add an adaptive layer to the first layer of the network according to the selected deep learning model to obtain a deep learning design model; In the deep learning design model, a custom loss function loss is added to the tail layer of the network to obtain an initial deep learning model;

S15. Adjust the hyperparameters of the deep learning initial model, and train the deep learning initial model according to the obtained training set data to obtain the deep learning trained model;

S16. Test the model after the deep learning training according to the obtained test set data, and calculate a test coefficient;

S17. Determine whether the test coefficient reaches a fixed parameter value or more, and the judgment result is yes, then the model parameters after the deep learning training meet the requirements, and the training ends, and the final deep learning model is obtained; otherwise, the model parameters after the deep learning training do not meet the requirements , Return to step S15.
The deep learning model design method of claim 1, wherein the activation function of the adaptive layer is

Among them, x is the input of the adaptive layer, and τ is the adaptive threshold of x;

The loss function
Where ω is a constant, which is a custom hyperparameter; m represents the segmentation category; Vol(A_perd i ) represents the predicted volume of the i-th category of bone; Vol(A_true i ) represents the i-th category of bone artificial The marked volume; Vol(A_pred_true i ) represents the correct volume predicted by the i-th category; Vol(A_pred i ∪A_true i ) represents the volume obtained after the merging of the bone predicted by the i-th category with the artificially labeled bone.
The method for designing a deep learning model according to claim 1, wherein the method for selecting a deep learning model comprises the following steps:

S31. Divide the training set data into N pieces, where N-1 pieces are used as training data, and 1 piece is used as verification data, where N is an integer greater than 1.

S32. Select a deep learning training model as the preliminary selected deep learning model;

S33. Train the preliminarily selected deep learning model according to the obtained training data, verify the preliminarily selected deep learning model according to the obtained verification data, and record the error at the same time;

S34. Non-repetitively select another piece of data in the N training set data in step S31 as verification data, and the remaining N-1 pieces as training data, and repeat the operation of step S33;

After S35, steps S33 and S34 are repeated N times, the average value of the errors recorded for N times is recorded to obtain the average error of the selected deep learning model;

S36. Select other deep learning models as the preliminary selected deep learning models, and repeat steps S33 to S35 to obtain the average error of other deep learning models;

S37. Select the deep learning model with the smallest average error as the final selected deep learning model.
The method for designing a deep learning model according to claim 2, wherein the steps of calculating the adaptive threshold τ are as follows:

S41. Traverse the input data of the first layer of the network and calculate the average value μ;

S42. Use the average value μ as a threshold value to divide the first layer input data of the network into two parts, a foreground part and a background part, and calculate the mean values t_fore and t_back of the foreground part and the background part respectively;

S43. Calculate a new threshold μ_new according to the obtained average value of the foreground part and the average value of the background part, the threshold μ_new=(t_fore+t_back)/2;

S44. According to the obtained new threshold μ_new, calculate to obtain diff, the diff=μ_new-μ, and assign the value of μ_new to μ;

S45. Repeat steps S42 to S44 until the diff is less than the set threshold and the iteration stops, and the adaptive threshold τ is obtained.
A medical image processing method based on deep learning, which is a deep learning model designed based on the deep learning model design method of claim 1, characterized in that it comprises the following steps:

Read two-dimensional medical image data;

Preprocess the read two-dimensional medical image data to obtain initial data;

According to the obtained initial data, extract the data of the region of interest;

Scaling the data of the region of interest to a fixed size by an interpolation method to obtain the data of the region of interest after scaling;

Standardize the scaled region of interest data to obtain input data of the deep learning model;

Run the final deep learning model to obtain an initial segmentation result;

Perform post-processing on the initial segmentation result to obtain the final segmentation result.
The medical image processing method based on deep learning according to claim 5, wherein the preprocessing method is filtering processing.
The medical image processing method based on deep learning according to claim 5, wherein the method for standardizing the scaled region of interest data comprises the following steps:

Obtaining the pixel value x i of the zoomed region of interest data according to the zoomed region of interest data;

Calculate the mean value μ and variance σ of the obtained pixel value x i;

According to the obtained mean value μ and variance σ, the normalized pixel value y i is calculated, the

Assign the normalized pixel value yi to the pixel value x i as the normalized pixel value, that is, let x i =y i .
A medical image processing system based on deep learning, characterized in that the system includes:

Reading module for reading two-dimensional medical image data;

The preprocessing module is used to preprocess the read two-dimensional medical image data to obtain training data;

The extraction module is used to extract the data of the region of interest according to the obtained training data;

A scaling module, configured to scale the data of the region of interest to a fixed size through an interpolation method, to obtain the data of the region of interest after scaling;

The standardization module is used to standardize the scaled region of interest data to obtain input data of the deep learning model;

The running module is used to run the final deep learning model to get the initial segmentation result;

The post-processing module is used to perform post-processing on the initial segmentation result to obtain the final segmentation result.
A computer device, the computer device includes a memory and a processor, and a computer program is stored in the memory, and is characterized in that the processor implements the following steps when the processor executes the computer program:

Read two-dimensional medical image data;

Preprocess the read two-dimensional medical image data to obtain training data;

According to the obtained training data, extract the data of the region of interest;

Scaling the data of the region of interest to a fixed size by an interpolation method to obtain the data of the region of interest after scaling;

Standardize the scaled region of interest data to obtain input data of the deep learning model;

Run the final deep learning model to get the initial segmentation result;

Perform post-processing on the initial segmentation result to obtain the final segmentation result.
A computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the following steps when being executed by a processor:

Read two-dimensional medical image data;

Preprocess the read two-dimensional medical image data to obtain training data;

According to the obtained training data, extract the data of the region of interest;

Scaling the data of the region of interest to a fixed size by an interpolation method to obtain the data of the region of interest after scaling;

Standardize the scaled region of interest data to obtain input data of the deep learning model;

Run the final deep learning model to get the initial segmentation result;

Perform post-processing on the initial segmentation result to obtain the final segmentation result.