Pancreatic cancer artificial intelligence auxiliary pathological diagnosis system based on deep learning

Abstract

The invention provides a pancreatic cancer artificial intelligence auxiliary pathological diagnosis system based on deep learning, and relates to the technical field of medical diagnose.The pancreatic cancer artificial intelligence auxiliary pathological diagnosis system is characterized in that a corresponding target pancreatic cancer pathological image is generated by obtaining an original pancreatic cancer pathological image and performing preprocessing operation; classifying the target pancreatic cancer pathology image to generate a training pancreatic cancer pathology image and a verification pancreatic cancer pathology image; constructing and training a pancreatic cancer pathological diagnosis model based on the trained pancreatic cancer pathological image by adopting a deep learning algorithm, and adjusting model parameters of the pancreatic cancer pathological diagnosis model in real time; evaluating the diagnosis performance of the pancreatic cancer pathological diagnosis model based on the pancreatic cancer pathological image, and optimizing the pancreatic cancer pathological diagnosis model according to the evaluation result; according to the method, the current pancreatic cancer pathological image is obtained, the current pancreatic cancer pathological image is preprocessed and input into the pancreatic cancer pathological diagnosis model, and the current diagnosis result is output and displayed to a physician end, so that the pathological image can be automatically analyzed, accurate diagnosis of pancreatic cancer is realized, and the diagnosis efficiency and accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the field of medical diagnosis technology, and in particular to an artificial intelligence-assisted pathological diagnosis system for pancreatic cancer based on deep learning. Background Art

[0002] Pancreatic cancer is a highly malignant digestive system tumor with atypical early symptoms, strong invasiveness, and easy metastasis and recurrence after surgery. At present, the diagnosis of pancreatic cancer mainly relies on imaging examinations and pathological diagnosis, but the diagnostic accuracy of these methods is easily affected by many factors, such as the size, location and morphology of the tumor. In recent years, the application of artificial intelligence in the medical field has developed rapidly, especially machine learning and deep learning algorithms have been widely used in image recognition, risk prediction and diagnostic decision-making of pancreatic cancer.

[0003] Traditional pancreatic cancer pathological diagnosis methods are easily affected by factors such as image quality and physician experience, which may lead to limited diagnostic accuracy. For example, the specificity of ultrasound endoscopy in distinguishing malignant tumors from benign masses is not ideal, ranging from only 50% to 60%. In addition, existing diagnostic systems often lack multi-center databases and have small data sample sizes. At the same time, they are unable to automatically complete the analysis and diagnosis of pathological images, requiring a long diagnostic time, which may lead to insufficient model training, affecting the efficiency and accuracy of pancreatic cancer diagnosis, and failing to provide auxiliary decision support for doctors.

[0004] Therefore, it is necessary to provide a pancreatic cancer artificial intelligence-assisted pathological diagnosis system based on deep learning to solve the above technical problems. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a pancreatic cancer artificial intelligence-assisted pathological diagnosis system based on deep learning to solve the problem that traditional pancreatic cancer pathological diagnosis methods are easily affected by factors such as image quality and doctor experience, resulting in limited diagnostic accuracy. In addition, the existing diagnostic system lacks a multi-center database and has a small data sample size. At the same time, it is unable to automatically complete the analysis and diagnosis of pathological images, requires a long diagnosis time, and leads to insufficient model training, which affects the efficiency and accuracy of pancreatic cancer diagnosis and cannot provide auxiliary decision support for doctors.

[0006] The present invention provides a pancreatic cancer artificial intelligence-assisted pathological diagnosis system based on deep learning, and the system comprises: An acquisition module, used for acquiring an original pancreatic cancer pathology image, and performing a preprocessing operation on the original pancreatic cancer pathology image to generate a corresponding target pancreatic cancer pathology image; A classification module, used for classifying the target pancreatic cancer pathology image to generate a training pancreatic cancer pathology image and a verification pancreatic cancer pathology image; A construction module, used to adopt a deep learning algorithm to construct and train a pancreatic cancer pathology diagnosis model based on the training pancreatic cancer pathology images, and adjust model parameters of the pancreatic cancer pathology diagnosis model in real time; An evaluation module, used to evaluate the diagnostic performance of the pancreatic cancer pathology diagnosis model based on the verified pancreatic cancer pathology image, and optimize the pancreatic cancer pathology diagnosis model according to the evaluation result; The result module is used to obtain the current pancreatic cancer pathology image, input it into the pancreatic cancer pathology diagnosis model after preprocessing, output the current diagnosis result and display it to the physician through a visual interface.

[0007] Preferably, the original pancreatic cancer pathology images include images of benign and malignant pancreatic cancer pathology sections, and images of early, middle and late stage pancreatic cancer pathology sections.

[0008] Preferably, the pre-processing operation includes: Cleaning the acquired original pancreatic cancer pathology image, that is, removing blurred and repeated original pancreatic cancer pathology images, and generating a corresponding first pancreatic cancer pathology image; removing noise in the first pancreatic cancer pathology image based on a Gaussian filtering algorithm to generate a corresponding second pancreatic cancer pathology image; using a histogram equalization method to enhance the contrast of the second pancreatic cancer pathology image to generate a corresponding third pancreatic cancer pathology image; The third pancreatic cancer pathology image is normalized to generate the corresponding target pancreatic cancer pathology image.

[0009] Preferably, the construction module is used to adopt a deep learning algorithm to construct and train a pancreatic cancer pathology diagnosis model based on the training pancreatic cancer pathology images, and adjust the model parameters of the pancreatic cancer pathology diagnosis model in real time, specifically including: Using a deep learning algorithm, the training pancreatic cancer pathology image is input into the input layer of the pancreatic cancer pathology diagnosis model, and the size of the training pancreatic cancer pathology image is ,in, represents the height of the training pancreatic cancer pathology image; represents the width of the training pancreatic cancer pathology image; represents the number of channels of the training pancreatic cancer pathology image; The pancreatic cancer pathology diagnosis model includes multiple convolutional layers, each of which includes a preset number of convolutional kernels. By adjusting the size, number and step size of the convolutional kernels, introducing corresponding bias terms and activation functions, extracting local features of different scales and complexities in the training pancreatic cancer pathology image, and summing all the local features to obtain the corresponding first pancreatic cancer pathology feature. The mathematical formula of the first pancreatic cancer pathology feature is:

[0010] In the formula, Indicates the location of the first pancreatic cancer pathological feature The pixel value of Represents the training pancreatic cancer pathology image at position The pixel value of Represents the position in the convolution kernel The weight of represents the activation function of the convolutional layer; Represents the bias term of the convolutional layer.

[0011] Preferably, the dimension of the first pancreatic cancer pathological feature is reduced by the pooling layer of the pancreatic cancer pathological diagnosis model, and important feature information in the first pancreatic cancer pathological feature, that is, the second pancreatic cancer pathological feature, is retained. The mathematical formula of the second pancreatic cancer pathological feature is:

[0012] In the formula, Indicates the second pancreatic cancer pathological feature at the location The pixel value of Indicates the location of the first pancreatic cancer pathological feature The pixel value of represents the pooling window; Indicates taking the maximum value among all positions within the pooling window; The first pancreatic cancer pathological feature and second pancreatic cancer pathological features After flattening, the corresponding input pancreatic cancer pathological features are obtained .

[0013] Preferably, the input pancreatic cancer pathological features are subjected to feature fusion and dimensionality reduction processing through the fully connected layer of the pancreatic cancer pathological diagnosis model to generate corresponding output features, and the mathematical formula of the output features is:

[0014] In the formula, Represents the output features of the fully connected layer; represents the transpose of the weights of the fully connected layer; Indicates the input of pancreatic cancer pathological characteristics; represents the bias term of the fully connected layer; Based on the output layer of the pancreatic cancer pathological diagnosis model, a softmax classifier is used to map the output features to the probability distribution of the pancreatic cancer diagnosis results to obtain the corresponding pancreatic cancer diagnosis category and diagnosis probability:

[0015] In the formula, Indicates pancreatic cancer diagnosis category The probability of diagnosis; Indicates pancreatic cancer diagnosis category The corresponding output features; Represents the exponential sum of the output features corresponding to all pancreatic cancer diagnosis classes.

[0016] Preferably, a loss function corresponding to the pancreatic cancer pathological diagnosis model is determined to measure the difference between the pancreatic cancer diagnosis result and the actual pathological result. The mathematical formula of the loss function is:

[0017] In the formula, represents the loss function; Represents the number of input training pancreatic cancer pathology images; Represents the loss value corresponding to a single training pancreatic cancer pathology image; Indicates the actual pathological results corresponding to the training pancreatic cancer pathological images; Represents the pancreatic cancer diagnosis results corresponding to the training pancreatic cancer pathology images.

[0018] Preferably, the gradient of the loss function to the model parameters of the pancreatic cancer pathology diagnosis model is calculated based on the back propagation algorithm:

[0019] In the formula, represents the loss function; represents the weight of the fully connected layer; Indicates the pancreatic cancer diagnosis results corresponding to the training pancreatic cancer pathology images; Indicates the input of pancreatic cancer pathological characteristics; Represents the loss function Weights for the fully connected layers The gradient of Represents the loss function Diagnosis of pancreatic cancer The gradient of Indicates the input of pancreatic cancer pathological characteristics Weights for the fully connected layers gradient.

[0020] Preferably, the model parameters of the pancreatic cancer pathology diagnosis model are updated based on the gradient descent method to minimize the loss function:

[0021] In the formula, Indicates The weight of the fully connected layer after iterations; Indicates The weight of the fully connected layer after iterations; represents the learning rate, which is used to control the update step size of the model parameters of the pancreatic cancer pathology diagnosis model; represents the loss function; represents the weight of the fully connected layer; Represents the loss function Weights for the fully connected layers In the The gradient at iteration .

[0022] Preferably, the evaluation module is used to evaluate the diagnostic performance of the pancreatic cancer pathology diagnosis model based on the verified pancreatic cancer pathology image, and optimize the pancreatic cancer pathology diagnosis model according to the evaluation result, specifically including: Inputting the verified pancreatic cancer pathology image into the pancreatic cancer pathology diagnosis model, determining a confusion matrix corresponding to the verification result, wherein the elements of the confusion matrix include true positive examples, false positive examples, true negative examples and false negative examples, wherein the true positive examples are correctly diagnosed pancreatic cancer pathology results; the false positive examples are incorrectly diagnosed pancreatic cancer pathology results; the true negative examples are correctly diagnosed non-pancreatic cancer pathology results; and the false negative examples are incorrectly diagnosed non-pancreatic cancer pathology results; Based on the confusion matrix, the diagnostic indicators corresponding to the pancreatic cancer pathological diagnosis model are calculated, wherein the diagnostic indicators include accuracy, precision, recall, F1 score and false positive rate; The calculation formula of the accuracy is:

[0023] In the formula, Indicates the accuracy of the pancreatic cancer pathological diagnosis model; represents a true case, i.e., a correct diagnosis of pancreatic cancer pathology result; represents a true negative example, i.e., a correct diagnosis of non-pancreatic cancer pathology results; represents a false positive, i.e., an incorrect diagnosis of pancreatic cancer pathology result; represents a false negative example, i.e., an incorrect diagnosis of non-pancreatic cancer pathology results; The calculation formula of the accuracy is:

[0024] In the formula, Indicates the accuracy rate corresponding to the pancreatic cancer pathological diagnosis model; represents a true case, i.e., a correct diagnosis of pancreatic cancer pathology result; represents a false positive, i.e., an incorrect diagnosis of pancreatic cancer pathology result; The calculation formula of the recall rate is:

[0025] In the formula, Represents the recall rate corresponding to the pancreatic cancer pathological diagnosis model; represents a true case, i.e., a correct diagnosis of pancreatic cancer pathology result; represents a false negative example, i.e., an incorrect diagnosis of non-pancreatic cancer pathology results; The calculation formula of the F1 score is:

[0026] In the formula, Indicates the F1 score corresponding to the pancreatic cancer pathological diagnosis model; Indicates the accuracy rate corresponding to the pancreatic cancer pathological diagnosis model; Represents the recall rate corresponding to the pancreatic cancer pathological diagnosis model; The calculation formula of the false positive rate is:

[0027] In the formula, Represents the false positive rate corresponding to the pancreatic cancer pathological diagnosis model; represents a false positive, i.e., an incorrect diagnosis of pancreatic cancer pathology result; represents a true negative example, i.e., a correct diagnosis of non-pancreatic cancer pathology results; The diagnostic indicators are analyzed, and the precision and recall are weighed to evaluate the diagnostic performance of the pancreatic cancer pathology diagnosis model, and the pancreatic cancer pathology diagnosis model is optimized according to the evaluation results.

[0028] Compared with related technologies, the pancreatic cancer artificial intelligence-assisted pathological diagnosis system based on deep learning provided by the present invention has the following beneficial effects: The present invention can obtain original pancreatic cancer pathology images through an acquisition module, a classification module, a construction module, an evaluation module and a result module, and perform preprocessing operations on the original pancreatic cancer pathology images to generate corresponding target pancreatic cancer pathology images; classify the target pancreatic cancer pathology images to generate training pancreatic cancer pathology images and verification pancreatic cancer pathology images; use a deep learning algorithm to construct and train a pancreatic cancer pathology diagnosis model based on the training pancreatic cancer pathology images, and adjust the model parameters of the pancreatic cancer pathology diagnosis model in real time; evaluate the diagnostic performance of the pancreatic cancer pathology diagnosis model based on the verification pancreatic cancer pathology images, and optimize the pancreatic cancer pathology diagnosis model according to the evaluation results; obtain the current pancreatic cancer pathology image, input it into the pancreatic cancer pathology diagnosis model after preprocessing, output the current diagnosis result and display it to the physician through a visual interface. The present invention can automatically extract and analyze feature information in pathological images through deep learning algorithms, achieve accurate diagnosis of pancreatic cancer, and improve diagnostic accuracy; the system of the present invention can automatically complete the analysis and diagnosis of pathological images, greatly shorten the diagnosis time, and improve the diagnosis efficiency; at the same time, it can provide auxiliary decision support for doctors, help doctors to more accurately judge the condition and formulate reasonable treatment plans, thereby promoting the development of medical intelligence and improving the level and quality of medical services. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 This is a system block diagram of the pancreatic cancer artificial intelligence-assisted pathological diagnosis system based on deep learning of the present invention; Figure 2 A schematic diagram of preprocessing an original pancreatic cancer pathology image of the present invention; Figure 3 This is a schematic diagram showing the current diagnosis result of the present invention to the physician. DETAILED DESCRIPTION

[0030] The present invention will be further described below in conjunction with the accompanying drawings and implementation modes. Example

[0031] like Figure 1 As shown, a pancreatic cancer artificial intelligence-assisted pathological diagnosis system based on deep learning, the system includes: An acquisition module, used for acquiring an original pancreatic cancer pathology image, and performing a preprocessing operation on the original pancreatic cancer pathology image to generate a corresponding target pancreatic cancer pathology image; A classification module, used for classifying the target pancreatic cancer pathology image to generate a training pancreatic cancer pathology image and a verification pancreatic cancer pathology image; A construction module, used to adopt a deep learning algorithm to construct and train a pancreatic cancer pathology diagnosis model based on the training pancreatic cancer pathology images, and adjust model parameters of the pancreatic cancer pathology diagnosis model in real time; An evaluation module, used to evaluate the diagnostic performance of the pancreatic cancer pathology diagnosis model based on the verified pancreatic cancer pathology image, and optimize the pancreatic cancer pathology diagnosis model according to the evaluation result; The result module is used to obtain the current pancreatic cancer pathology image, input it into the pancreatic cancer pathology diagnosis model after preprocessing, output the current diagnosis result and display it to the physician through a visual interface.

[0032] The acquisition module uses high-precision image acquisition equipment, such as a high-resolution microscope with a digital imaging system, to ensure the high definition and detail integrity of the acquired images. Subsequently, the acquired original pancreatic cancer pathology images can be preprocessed to improve image quality, reduce interference factors, and ultimately generate the corresponding target pancreatic cancer pathology images.

[0033] The classification module can further divide the preprocessed target pancreatic cancer pathology images into training pancreatic cancer pathology images and verification pancreatic cancer pathology images. The classification process is based on factors such as the pathological characteristics, staging and grading of the image, thereby ensuring that the training pancreatic cancer pathology images and the verification pancreatic cancer pathology images are representative in terms of pathological type, complexity and other aspects. Specifically, the subsequent training pancreatic cancer pathology images are used to build a pancreatic cancer pathology diagnosis model, while the verification pancreatic cancer pathology images are used to evaluate the diagnostic performance of the pancreatic cancer pathology diagnosis model. The two are independent of each other, which helps to improve the generalization ability of the pancreatic cancer pathology diagnosis model.

[0034] The construction module uses a deep learning algorithm to build a pancreatic cancer pathology diagnosis model based on training pancreatic cancer pathology images. Through iterative training, the pancreatic cancer pathology diagnosis model can gradually learn and identify pathological features in images, such as cell morphology, nuclear division, etc. At the same time, the construction module can adjust model parameters in real time, such as learning rate, weight decay, etc., to optimize the performance of the pancreatic cancer pathology diagnosis model and ensure that it maintains high accuracy in complex and changeable pathology images.

[0035] The evaluation module can use the verified pancreatic cancer pathology images to evaluate the diagnostic performance of the trained pancreatic cancer pathology diagnosis model. The evaluation indicators include accuracy, recall rate, F1 score, etc., which can comprehensively measure the ability of the pancreatic cancer pathology diagnosis model in identifying pancreatic cancer pathological features. According to the evaluation results, the evaluation module can perform corresponding model optimization, such as adjusting the network structure, adding data enhancement strategies, etc., so as to further improve the diagnostic accuracy and robustness of the pancreatic cancer pathology diagnosis model.

[0036] The result module can obtain the pancreatic cancer pathology image to be diagnosed, and after the same preprocessing process, input it into the optimized pancreatic cancer pathology diagnosis model, and output the current diagnosis result, including pathology type, stage and grade information. This information is clearly displayed to the physician through a visual interface, which can assist the physician to make more accurate and rapid diagnostic decisions, improve the efficiency of pancreatic cancer diagnosis, and reduce the misdiagnosis rate caused by human factors.

[0037] In a specific implementation process, the original pancreatic cancer pathology images include images of benign and malignant pancreatic cancer pathology sections, and images of early, middle and late stage pancreatic cancer pathology sections.

[0038] It is understandable that the original pancreatic cancer pathology images include histopathological slice images of benign and malignant pancreatic cancer, as well as pathological slice images of different stages of disease development, namely, early pancreatic cancer, mid-stage pancreatic cancer and late pancreatic cancer. Specifically, early pancreatic cancer means that the tumor is confined to the pancreas and has not spread significantly; mid-stage pancreatic cancer means that the tumor has invaded surrounding tissues or local lymph node metastasis; late pancreatic cancer means that the tumor has distant metastasis, such as liver, lung and other organs.

[0039] The pre-processing operation includes: Cleaning the acquired original pancreatic cancer pathology image, that is, removing blurred and repeated original pancreatic cancer pathology images, and generating a corresponding first pancreatic cancer pathology image; removing noise in the first pancreatic cancer pathology image based on a Gaussian filtering algorithm to generate a corresponding second pancreatic cancer pathology image; using a histogram equalization method to enhance the contrast of the second pancreatic cancer pathology image to generate a corresponding third pancreatic cancer pathology image; The third pancreatic cancer pathology image is normalized to generate the corresponding target pancreatic cancer pathology image.

[0040] In practical applications, such as Figure 2 As shown, firstly, an image cleaning operation can be performed on the acquired original pancreatic cancer pathology images to remove blurred and repeated images caused by poor shooting conditions or technical factors, thereby ensuring the purity of the data set and generating a clear first pancreatic cancer pathology image set.

[0041] Subsequently, the Gaussian filtering algorithm can be used to remove noise from the first pancreatic cancer pathology image. As a linear smoothing filtering technology, Gaussian filtering can effectively reduce or eliminate random noise in the image, such as Gaussian noise, while retaining the edge details of the image as much as possible to generate a smoother second pancreatic cancer pathology image.

[0042] In order to further improve the visualization effect of the image, the histogram equalization method is used to enhance the contrast of the second pancreatic cancer pathology image. This method adjusts the grayscale histogram distribution of the image to make the grayscale value in the image more evenly distributed, thereby significantly improving the contrast of the image and generating a third pancreatic cancer pathology image with enhanced contrast.

[0043] Finally, the third pancreatic cancer pathology image can be normalized, that is, the pixel values ​​of the image are mapped into a standardized range to eliminate the brightness differences between different images caused by factors such as lighting and shooting equipment, and generate a standardized target pancreatic cancer pathology image, laying the foundation for subsequent image segmentation, feature extraction and pathology analysis.

[0044] The construction module is used to adopt a deep learning algorithm to construct and train a pancreatic cancer pathology diagnosis model based on the training pancreatic cancer pathology images, and adjust the model parameters of the pancreatic cancer pathology diagnosis model in real time, specifically including: Using a deep learning algorithm, the training pancreatic cancer pathology image is input into the input layer of the pancreatic cancer pathology diagnosis model, and the size of the training pancreatic cancer pathology image is ,in, represents the height of the training pancreatic cancer pathology image; represents the width of the training pancreatic cancer pathology image; represents the number of channels of the training pancreatic cancer pathology image; The pancreatic cancer pathology diagnosis model includes multiple convolutional layers, each of which includes a preset number of convolutional kernels. By adjusting the size, number and step size of the convolutional kernels, introducing corresponding bias terms and activation functions, extracting local features of different scales and complexities in the training pancreatic cancer pathology image, and summing all the local features to obtain the corresponding first pancreatic cancer pathology feature. The mathematical formula of the first pancreatic cancer pathology feature is:

[0045] In the formula, Indicates the location of the first pancreatic cancer pathological feature The pixel value of Represents the training pancreatic cancer pathology image at position The pixel value of Represents the position in the convolution kernel The weight of represents the activation function of the convolutional layer; Represents the bias term of the convolutional layer.

[0046] The dimension of the first pancreatic cancer pathological feature is reduced by the pooling layer of the pancreatic cancer pathological diagnosis model, and important feature information in the first pancreatic cancer pathological feature is retained, that is, the second pancreatic cancer pathological feature. The mathematical formula of the second pancreatic cancer pathological feature is:

[0047] In the formula, Indicates the second pancreatic cancer pathological feature at the location The pixel value of Indicates the location of the first pancreatic cancer pathological feature The pixel value of represents the pooling window; Indicates taking the maximum value among all positions within the pooling window; The first pancreatic cancer pathological feature and second pancreatic cancer pathological features After flattening, the corresponding input pancreatic cancer pathological features are obtained .

[0048] The input pancreatic cancer pathological features are subjected to feature fusion and dimensionality reduction processing through the fully connected layer of the pancreatic cancer pathological diagnosis model to generate corresponding output features. The mathematical formula of the output features is:

[0049] In the formula, Represents the output features of the fully connected layer; represents the transpose of the weights of the fully connected layer; Indicates the input of pancreatic cancer pathological characteristics; represents the bias term of the fully connected layer; Based on the output layer of the pancreatic cancer pathological diagnosis model, a softmax classifier is used to map the output features to the probability distribution of the pancreatic cancer diagnosis results to obtain the corresponding pancreatic cancer diagnosis category and diagnosis probability:

[0050] In the formula, Indicates pancreatic cancer diagnosis category The probability of diagnosis; Indicates pancreatic cancer diagnosis category The corresponding output features; Represents the exponential sum of the output features corresponding to all pancreatic cancer diagnosis classes.

[0051] It is understandable that the convolutional neural network (CNN) architecture is selected as the basis based on the deep learning framework and appropriately modified according to the characteristics of pancreatic cancer pathological images. Then, multiple convolutional layers can be designed, each of which contains a certain number of convolutional kernels. By adjusting the size, number and step size of the convolutional kernels, local features in the image can be extracted and features of different scales and complexities can be captured.

[0052] Furthermore, a pooling layer can be added after the convolution layer to reduce the dimension of the feature map and the amount of computation while retaining important feature information. After flattening the output of the convolution layer and the pooling layer, the output features can be fused and reduced in dimension through the fully connected layer and finally connected to the output layer. The output layer usually uses a softmax function to map the features to the probability distribution of the diagnosis results and output the diagnosis results of benign, malignant and different stages of pancreatic cancer.

[0053] The loss function corresponding to the pancreatic cancer pathological diagnosis model is determined to measure the difference between the pancreatic cancer diagnosis result and the actual pathological result. The mathematical formula of the loss function is:

[0054] In the formula, represents the loss function; Represents the number of input training pancreatic cancer pathology images; Represents the loss value corresponding to a single training pancreatic cancer pathology image; Indicates the actual pathological results corresponding to the training pancreatic cancer pathological images; Represents the pancreatic cancer diagnosis results corresponding to the training pancreatic cancer pathology images.

[0055] The gradient of the loss function to the model parameters of the pancreatic cancer pathology diagnosis model is calculated based on the back propagation algorithm:

[0056] In the formula, represents the loss function; represents the weight of the fully connected layer; Indicates the pancreatic cancer diagnosis results corresponding to the training pancreatic cancer pathology images; Indicates the input of pancreatic cancer pathological characteristics; Represents the loss function Weights for the fully connected layers The gradient of Represents the loss function Diagnosis of pancreatic cancer The gradient of Indicates the input of pancreatic cancer pathological characteristics Weights for the fully connected layers gradient.

[0057] The model parameters of the pancreatic cancer pathology diagnosis model are updated based on the gradient descent method to minimize the loss function:

[0058] In the formula, Indicates The weight of the fully connected layer after iterations; Indicates The weight of the fully connected layer after iterations; represents the learning rate, which is used to control the update step size of the model parameters of the pancreatic cancer pathology diagnosis model; represents the loss function; represents the weight of the fully connected layer; Represents the loss function Weights for the fully connected layers In the The gradient at iteration .

[0059] In practical applications, the model parameters of the pancreatic cancer pathology diagnosis model are continuously adjusted through the back-propagation algorithm to minimize the difference between the output of the pancreatic cancer pathology diagnosis model and the true label.

[0060] The evaluation module is used to evaluate the diagnostic performance of the pancreatic cancer pathology diagnosis model based on the verified pancreatic cancer pathology image, and optimize the pancreatic cancer pathology diagnosis model according to the evaluation result, and specifically includes: Inputting the verified pancreatic cancer pathology image into the pancreatic cancer pathology diagnosis model, determining a confusion matrix corresponding to the verification result, wherein the elements of the confusion matrix include true positive examples, false positive examples, true negative examples and false negative examples, wherein the true positive examples are correctly diagnosed pancreatic cancer pathology results; the false positive examples are incorrectly diagnosed pancreatic cancer pathology results; the true negative examples are correctly diagnosed non-pancreatic cancer pathology results; and the false negative examples are incorrectly diagnosed non-pancreatic cancer pathology results; Based on the confusion matrix, the diagnostic indicators corresponding to the pancreatic cancer pathological diagnosis model are calculated, wherein the diagnostic indicators include accuracy, precision, recall, F1 score and false positive rate; The calculation formula of the accuracy is:

[0061] In the formula, Indicates the accuracy of the pancreatic cancer pathological diagnosis model; represents a true case, i.e., a correct diagnosis of pancreatic cancer pathology result; represents a true negative example, i.e., a correct diagnosis of non-pancreatic cancer pathology results; represents a false positive, i.e., an incorrect diagnosis of pancreatic cancer pathology result; represents a false negative example, i.e., an incorrect diagnosis of non-pancreatic cancer pathology results; The calculation formula of the accuracy is:

[0062] In the formula, Indicates the accuracy rate corresponding to the pancreatic cancer pathological diagnosis model; represents a true case, i.e., a correct diagnosis of pancreatic cancer pathology result; represents a false positive, i.e., an incorrect diagnosis of pancreatic cancer pathology result; The calculation formula of the recall rate is:

[0063] In the formula, Represents the recall rate corresponding to the pancreatic cancer pathological diagnosis model; represents a true case, i.e., a correct diagnosis of pancreatic cancer pathology result; represents a false negative example, i.e., an incorrect diagnosis of non-pancreatic cancer pathology results; The calculation formula of the F1 score is:

[0064] In the formula, Indicates the F1 score corresponding to the pancreatic cancer pathological diagnosis model; Indicates the accuracy rate corresponding to the pancreatic cancer pathological diagnosis model; Represents the recall rate corresponding to the pancreatic cancer pathological diagnosis model; The calculation formula of the false positive rate is:

[0065] In the formula, Represents the false positive rate corresponding to the pancreatic cancer pathological diagnosis model; represents a false positive, i.e., an incorrect diagnosis of pancreatic cancer pathology result; represents a true negative example, i.e., a correct diagnosis of non-pancreatic cancer pathology results; The diagnostic indicators are analyzed, and the precision and recall are weighed to evaluate the diagnostic performance of the pancreatic cancer pathology diagnosis model, and the pancreatic cancer pathology diagnosis model is optimized according to the evaluation results.

[0066] Furthermore, the optimized pancreatic cancer pathology diagnosis model can be integrated into the pancreatic cancer pathology diagnosis system to ensure that the system can run stably and process actual pathology images. Figure 3 As shown, based on the terminal device, by designing a user visualization interface, the physician can input the pathological slices to be diagnosed and view the diagnosis results of the pancreatic cancer pathology diagnosis system in real time.

[0067] It should be noted that the physician terminal refers to the terminal corresponding to the doctor. The pancreatic cancer pathology diagnosis system can not only provide accurate diagnosis results, but also provide diagnosis basis and possible misdiagnosis analysis, providing comprehensive auxiliary decision support for the physician terminal.

[0068] Through the introduction of the above embodiments, the present invention can obtain the original pancreatic cancer pathology image through the acquisition module, classification module, construction module, evaluation module and result module, and perform preprocessing operations on the original pancreatic cancer pathology image to generate the corresponding target pancreatic cancer pathology image; classify the target pancreatic cancer pathology image to generate a training pancreatic cancer pathology image and a verification pancreatic cancer pathology image; use a deep learning algorithm to construct and train a pancreatic cancer pathology diagnosis model based on the training pancreatic cancer pathology image, and adjust the model parameters of the pancreatic cancer pathology diagnosis model in real time; evaluate the diagnostic performance of the pancreatic cancer pathology diagnosis model based on the verification pancreatic cancer pathology image, and optimize the pancreatic cancer pathology diagnosis model according to the evaluation results; obtain the current pancreatic cancer pathology image, input it into the pancreatic cancer pathology diagnosis model after preprocessing, output the current diagnosis result and display it to the physician through a visual interface. Through the deep learning algorithm, the present invention can automatically extract and analyze the characteristic information in the pathological images, realize the accurate diagnosis of pancreatic cancer, and improve the diagnostic accuracy; the system of the present invention can automatically complete the analysis and diagnosis of pathological images, greatly shorten the diagnosis time, and improve the diagnostic efficiency; at the same time, the present invention can provide auxiliary decision support for doctors, help doctors to more accurately judge the condition and formulate reasonable treatment plans, thereby promoting the development of medical intelligence and improving the level and quality of medical services.

[0069] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0070] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0071] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

Claims

1. The deep learning-based artificial intelligence-assisted pathological diagnosis system for pancreatic cancer is characterized by: The system comprises: An acquisition module, used for acquiring an original pancreatic cancer pathology image, and performing a preprocessing operation on the original pancreatic cancer pathology image to generate a corresponding target pancreatic cancer pathology image; A classification module, used for classifying the target pancreatic cancer pathology image to generate a training pancreatic cancer pathology image and a verification pancreatic cancer pathology image; A construction module, used to adopt a deep learning algorithm to construct and train a pancreatic cancer pathology diagnosis model based on the training pancreatic cancer pathology images, and adjust model parameters of the pancreatic cancer pathology diagnosis model in real time; An evaluation module, used to evaluate the diagnostic performance of the pancreatic cancer pathology diagnosis model based on the verified pancreatic cancer pathology image, and optimize the pancreatic cancer pathology diagnosis model according to the evaluation result; The result module is used to obtain the current pancreatic cancer pathology image, input it into the pancreatic cancer pathology diagnosis model after preprocessing, output the current diagnosis result and display it to the physician through a visual interface.

2. The pancreatic cancer artificial intelligence-assisted pathological diagnosis system based on deep learning according to claim 1 is characterized in that: The original pancreatic cancer pathology images include images of benign and malignant pancreatic cancer pathology sections, and images of early, middle and late stage pancreatic cancer pathology sections.

3. The pancreatic cancer artificial intelligence-assisted pathological diagnosis system based on deep learning according to claim 1 is characterized in that: The pre-processing operation includes: Cleaning the acquired original pancreatic cancer pathology image, that is, removing blurred and repeated original pancreatic cancer pathology images, and generating a corresponding first pancreatic cancer pathology image; removing noise in the first pancreatic cancer pathology image based on a Gaussian filtering algorithm to generate a corresponding second pancreatic cancer pathology image; using a histogram equalization method to enhance the contrast of the second pancreatic cancer pathology image to generate a corresponding third pancreatic cancer pathology image; The third pancreatic cancer pathology image is normalized to generate the corresponding target pancreatic cancer pathology image.

4. The pancreatic cancer artificial intelligence-assisted pathological diagnosis system based on deep learning according to claim 1 is characterized in that: The construction module is used to adopt a deep learning algorithm to construct and train a pancreatic cancer pathology diagnosis model based on the training pancreatic cancer pathology images, and adjust the model parameters of the pancreatic cancer pathology diagnosis model in real time, specifically including: Using a deep learning algorithm, the training pancreatic cancer pathology image is input into the input layer of the pancreatic cancer pathology diagnosis model, and the size of the training pancreatic cancer pathology image is ,in, represents the height of the training pancreatic cancer pathology image; represents the width of the training pancreatic cancer pathology image; represents the number of channels of the training pancreatic cancer pathology image; The pancreatic cancer pathology diagnosis model includes multiple convolutional layers, each of which includes a preset number of convolutional kernels. By adjusting the size, number and step size of the convolutional kernels, introducing corresponding bias terms and activation functions, extracting local features of different scales and complexities in the training pancreatic cancer pathology image, and summing all the local features to obtain the corresponding first pancreatic cancer pathology feature. The mathematical formula of the first pancreatic cancer pathology feature is: ； In the formula, Indicates the location of the first pancreatic cancer pathological feature The pixel value of Represents the training pancreatic cancer pathology image at position The pixel value of Represents the position in the convolution kernel The weight of represents the activation function of the convolutional layer; Represents the bias term of the convolutional layer.

5. The pancreatic cancer artificial intelligence-assisted pathological diagnosis system based on deep learning according to claim 4 is characterized in that: The dimension of the first pancreatic cancer pathological feature is reduced by the pooling layer of the pancreatic cancer pathological diagnosis model, and important feature information in the first pancreatic cancer pathological feature is retained, that is, the second pancreatic cancer pathological feature. The mathematical formula of the second pancreatic cancer pathological feature is: ； In the formula, Indicates the second pancreatic cancer pathological feature at the location The pixel value of Indicates the location of the first pancreatic cancer pathological feature The pixel value of represents the pooling window; Indicates taking the maximum value among all positions within the pooling window; The first pancreatic cancer pathological feature and second pancreatic cancer pathological features After flattening, the corresponding input pancreatic cancer pathological features are obtained .

6. The deep learning-based artificial intelligence-assisted pathological diagnosis system for pancreatic cancer according to claim 5 is characterized in that: The input pancreatic cancer pathological features are subjected to feature fusion and dimensionality reduction processing through the fully connected layer of the pancreatic cancer pathological diagnosis model to generate corresponding output features. The mathematical formula of the output features is: ； In the formula, Represents the output features of the fully connected layer; represents the transpose of the weights of the fully connected layer; Indicates the input of pancreatic cancer pathological characteristics; represents the bias term of the fully connected layer; Based on the output layer of the pancreatic cancer pathological diagnosis model, a softmax classifier is used to map the output features to the probability distribution of the pancreatic cancer diagnosis results to obtain the corresponding pancreatic cancer diagnosis category and diagnosis probability: ； In the formula, Indicates pancreatic cancer diagnosis category The probability of diagnosis; Indicates pancreatic cancer diagnosis category The corresponding output features; Represents the exponential sum of the output features corresponding to all pancreatic cancer diagnosis classes.

7. The deep learning-based artificial intelligence-assisted pathological diagnosis system for pancreatic cancer according to claim 6 is characterized in that: The loss function corresponding to the pancreatic cancer pathological diagnosis model is determined to measure the difference between the pancreatic cancer diagnosis result and the actual pathological result. The mathematical formula of the loss function is: ； In the formula, represents the loss function; Represents the number of input training pancreatic cancer pathology images; Represents the loss value corresponding to a single training pancreatic cancer pathology image; Indicates the actual pathological results corresponding to the training pancreatic cancer pathological images; Represents the pancreatic cancer diagnosis results corresponding to the training pancreatic cancer pathology images.

8. The deep learning-based artificial intelligence-assisted pathological diagnosis system for pancreatic cancer according to claim 7 is characterized in that: The gradient of the loss function to the model parameters of the pancreatic cancer pathology diagnosis model is calculated based on the back propagation algorithm: ； In the formula, represents the loss function; represents the weight of the fully connected layer; Indicates the pancreatic cancer diagnosis results corresponding to the training pancreatic cancer pathology images; Indicates the input of pancreatic cancer pathological characteristics; Represents the loss function Weights for the fully connected layers The gradient of Represents the loss function Diagnosis of pancreatic cancer The gradient of Indicates the input of pancreatic cancer pathological characteristics Weights for the fully connected layers gradient.

9. The deep learning-based artificial intelligence-assisted pathological diagnosis system for pancreatic cancer according to claim 8, characterized in that: The model parameters of the pancreatic cancer pathology diagnosis model are updated based on the gradient descent method to minimize the loss function: ； In the formula, Indicates The weight of the fully connected layer after iterations; Indicates The weight of the fully connected layer after iterations; represents the learning rate, which is used to control the update step size of the model parameters of the pancreatic cancer pathology diagnosis model; represents the loss function; represents the weight of the fully connected layer; Represents the loss function Weights for the fully connected layers In the The gradient at iteration .

10. The deep learning-based artificial intelligence-assisted pathological diagnosis system for pancreatic cancer according to claim 1, characterized in that: The evaluation module is used to evaluate the diagnostic performance of the pancreatic cancer pathology diagnosis model based on the verified pancreatic cancer pathology image, and optimize the pancreatic cancer pathology diagnosis model according to the evaluation result, and specifically includes: Inputting the verified pancreatic cancer pathology image into the pancreatic cancer pathology diagnosis model, determining a confusion matrix corresponding to the verification result, wherein the elements of the confusion matrix include true positive examples, false positive examples, true negative examples and false negative examples, wherein the true positive examples are correctly diagnosed pancreatic cancer pathology results; the false positive examples are incorrectly diagnosed pancreatic cancer pathology results; the true negative examples are correctly diagnosed non-pancreatic cancer pathology results; and the false negative examples are incorrectly diagnosed non-pancreatic cancer pathology results; Based on the confusion matrix, the diagnostic indicators corresponding to the pancreatic cancer pathological diagnosis model are calculated, wherein the diagnostic indicators include accuracy, precision, recall, F1 score and false positive rate; The calculation formula of the accuracy is: ； In the formula, Indicates the accuracy of the pancreatic cancer pathological diagnosis model; represents a true case, i.e., a correct diagnosis of pancreatic cancer pathology result; represents a true negative example, i.e., a correct diagnosis of non-pancreatic cancer pathology results; represents a false positive, i.e., an incorrect diagnosis of pancreatic cancer pathology result; represents a false negative example, i.e., an incorrect diagnosis of non-pancreatic cancer pathology results; The calculation formula of the accuracy is: ； In the formula, Indicates the accuracy rate corresponding to the pancreatic cancer pathological diagnosis model; represents a true case, i.e., a correct diagnosis of pancreatic cancer pathology result; represents a false positive, i.e., an incorrect diagnosis of pancreatic cancer pathology result; The calculation formula of the recall rate is: ； In the formula, Represents the recall rate corresponding to the pancreatic cancer pathological diagnosis model; represents a true case, i.e., a correct diagnosis of pancreatic cancer pathology result; represents a false negative example, i.e., an incorrect diagnosis of non-pancreatic cancer pathology results; The calculation formula of the F1 score is: ； In the formula, Indicates the F1 score corresponding to the pancreatic cancer pathological diagnosis model; Indicates the accuracy rate corresponding to the pancreatic cancer pathological diagnosis model; Represents the recall rate corresponding to the pancreatic cancer pathological diagnosis model; The calculation formula of the false positive rate is: ； In the formula, Represents the false positive rate corresponding to the pancreatic cancer pathological diagnosis model; represents a false positive, i.e., an incorrect diagnosis of pancreatic cancer pathology result; represents a true negative example, i.e., a correct diagnosis of non-pancreatic cancer pathology results; The diagnostic indicators are analyzed, and the precision and recall are weighed to evaluate the diagnostic performance of the pancreatic cancer pathology diagnosis model, and the pancreatic cancer pathology diagnosis model is optimized according to the evaluation results.

Images