Method, system and equipment for screening depression based on fundus color illumination and medium

Abstract

The invention discloses a method, a system, equipment and a medium for screening depression based on fundus color photograph, and the method comprises the following steps: collecting a fundus color photograph image data set containing healthy individuals and depression patients, carrying out the feature measurement of the image data set, building a model based on a random forest, and classifying the image data. And verifying and evaluating the model, and applying the model to a clinical working process. According to the method, model training and verification can be carried out on patients diagnosed with depression and healthy people of the same age and gender through fundus color images, depression diagnosis and clinical risk factors, and a trained random forest model is obtained and is used for distinguishing the healthy people from the depression patients; and a method and a tool are provided for early screening and identification of depression.

Description

Technical Field

[0001] The present invention relates to the field of medical disease screening, and more specifically, to a method, system, device and medium for screening depression based on fundus color photography. Background Art

[0002] Depressive disorder is a common mental disorder involving prolonged low mood or loss of happiness or interest in activities, which can affect all aspects of life. The number of people suffering from depression is large and the scope is wide. According to statistics, about 3.8% of the world's population suffers from depression, including 5% of adults (4% for men and 6% for women), and 5.7% of adults over 60 years old. The incidence of depression in women is about 50% higher than that in men. More than 10% of pregnant women and women who have just given birth suffer from depression. More than 700,000 people commit suicide each year, and suicide is the fourth leading cause of death among people aged 15-29. Therefore, it is crucial to prevent, diagnose and treat depression. The existing diagnosis of depression mainly relies on questionnaire assessment and doctors' judgment of patients' symptoms. These methods are often subjective, costly and not easy to popularize, which can easily lead to missed diagnosis and misdiagnosis of depression. Therefore, it is urgent to develop objective, efficient and convenient tools to assist in the assessment of depression.

[0003] Fundus color photography has the unique advantages of being non-invasive, objective, efficient and convenient, and is widely used in the diagnosis and monitoring of ophthalmology. The detection of eye diseases mainly relies on professional doctors to evaluate fundus color photography. This method is highly dependent on the rich experience and professional skills of doctors. With the rapid development of artificial intelligence (AI) technology, especially deep learning, AI models based on fundus color photography have shown good performance in the evaluation of common eye diseases such as diabetic retinopathy, age-related macular degeneration, and glaucoma, showing the great potential of fundus color photography AI. However, the current application of fundus color photography is limited to the diagnosis of eye diseases and is rarely used in systemic diseases. Systemic diseases can also have different ocular manifestations, such as depression, hypertension, kidney disease and diabetes. According to surveys, a large number of studies have confirmed that patients with depression have different degrees of fundus structural changes, such as changes in vascular fractal dimension, optic disc structure, retinal microcirculation and choroidal vascular density. In addition, as a non-invasive, low-cost and easy-to-operate evaluation method, fundus color photography can provide a new way for early screening of depression.

[0004] However, for diseases such as depression that are not directly reflected in fundus images, the current methods have the disadvantages of accuracy and stability that need to be improved. These problems may lead to unfavorable factors such as insufficient sensitivity and accuracy, limiting the widespread application of fundus color photography in depression screening. The existing methods are too limited in the scope of use of fundus feature parameters, mainly focusing on the diagnosis of eye diseases, and lack the classification of healthy people and depression. In addition, the lack of feature extraction makes it impossible to fully obtain the features related to depression in fundus images, resulting in difficulties in accurately distinguishing healthy people from depression. This proposal aims to establish a classification model for healthy people and depression based on fundus color photography, which can efficiently and accurately screen out patients with depression from the population. Summary of the invention

[0005] The present invention aims to overcome at least one defect in the prior art and provide a method, system, device and medium for screening depression based on fundus color photography, which is used to solve the problem of low accuracy and instability in distinguishing healthy people from depression patients through fundus images.

[0006] The technical solution adopted by the present invention is a method for screening depression based on fundus color photography, comprising the following steps: Step S100: collecting an image dataset containing healthy individuals and depression patients; Step S200: performing feature measurement on the image data set; Step S300: constructing a model based on random forest to classify image data; Step S400: verifying and evaluating the model; Step S500: Apply the model to the clinical workflow to provide real-time disease screening.

[0007] First, we collected a large number of fundus color images from UK Biobank, communities and hospitals, as well as the diagnosis of depression (mainly including whether it was diagnosed as depression, whether there was a preliminary diagnosis of eye diseases and other systemic diseases, such as cardiovascular and cerebrovascular diseases, neurodegenerative diseases and mental illnesses, as well as the specific diagnosis) and clinical risk factors (gender, age, body mass index). We trained and validated the model by using patients with confirmed depression and healthy controls of the same age and gender.

[0008] In order to increase the extraction of depression-related features, special measurement indicators are needed. Therefore, the feature measurements of the image dataset are designed to include the following indicators: Optic disc tilt angle: the angle between the major axis of the smallest outer ellipse and the horizontal line; Optic disc roundness:

[0009] Among them, C represents the roundness of the optic disc, F represents the optic disc area, that is, the number of pixels occupied by the optic disc area, and R represents the minimum circumference radius of the optic disc.

[0010] In order to enable early screening and identification of depression, the constructed model can distinguish healthy people from patients with depression based on fundus images. The random forest model is constructed based on the measured fundus image features and clinical risk factors, including the following steps: Step S310: randomly selecting samples, using a bootstrap sampling method with replacement to randomly extract samples from an original data set D containing fundus image features, depression diagnosis, and clinical risk factors; Step S320: randomly selecting features, the features including optic disc tilt angle, optic disc roundness, gender, age, and body mass index, and randomly selecting features for splitting at each node of each decision tree; Step S330: construct a decision tree, using the CART (Classification and Regression Trees) algorithm to construct the decision tree, and using the Gini Index as one of the criteria for selecting features and dividing nodes; Step S340: training the random forest model by using the preprocessed and feature selected data.

[0011] During the training process, the model learns how to distinguish between healthy people and patients with depression based on the input fundus color photo features and clinical risk factors. The required data is simplified, and only fundus color photos, gender, age, and body mass index are used to identify depression, making it more suitable for use in areas with scarce medical resources and improving the popularity of depression screening.

[0012] When building a decision tree, the Gini index is used as one of the criteria for selecting features and dividing nodes. The Gini index measures the probability that two samples randomly selected from a data set have inconsistent category labels. The smaller the Gini index, the higher the purity of the data set, that is, the greater the possibility that the samples belong to the same category; The calculation of the Gini index, for a dataset D containing K categories, where K is 2, including healthy people and patients with depression, its Gini index is defined as:

[0013] Among them, pk is the proportion of samples of the kth category in the data set D; Feature A includes: optic disc tilt angle, optic disc roundness, gender, age and body mass index. For a division D1 and D2 under feature A, that is, the data set D is divided into two parts according to feature A, the Gini index after division is:

[0014] Among them, |D|, |D1| and |D2| represent the number of samples in datasets D, D1 and D2 respectively.

[0015] The specific process of building a decision tree based on the CART algorithm includes the following steps: Step S321: Calculate the Gini index of each feature in the data set, select the feature with the smallest Gini index as the optimal partitioning feature, and divide the data set into different subsets according to different values ​​of the feature; Step S322: Repeat step S321 for each of the subsets until a stop condition is met; Step S333: Pruning the decision tree.

[0016] The stopping conditions of step S322 include that the number of samples in the subset is less than the minimum number of samples of the algorithm parameters, all samples belong to the same category, there are no more features to be divided, etc. In step S333, in order to avoid overfitting, the decision tree is pruned to remove leaf nodes with low gain and simplify the model.

[0017] In order to ensure the robustness and generalization ability of the model, the random forest model used five-fold cross-validation for internal validation, and fundus image data and depression diagnosis for external validation. The fundus image data used relevant data from 300 subjects in hospitals and communities whose personal identity information was concealed to provide sufficient external validation samples for model training.

[0018] In order to more intuitively display the difference between the model prediction results and the actual results, the evaluation uses cross entropy to evaluate the difference between the probability distribution predicted by the model and the actual distribution:

[0019] Where x represents a possible value of the random variable (1 or 0, 1 represents depression and 0 represents a healthy control), n is the number of all possible values ​​of the random variable, p(x) and q(x) represent the probabilities of x in distribution p and q respectively; the formula specifically represents the average coding length when encoding using the predicted distribution Q under the true distribution P, that is, the average information entropy, in bits or nats. The smaller the value of the cross entropy, the closer the two probability distributions are. The cross entropy here is a small value such as 0.2231, the lower the better.

[0020] A depression screening system based on fundus color photography, comprising: An image collection module is used to: collect a fundus color image dataset containing healthy individuals and patients with depression; A measurement module, used to: perform feature measurement on the image data set; Generate a module to: build a random forest model to classify image data; Verification and evaluation module: verify and evaluate the random forest model; The system has the ability to process and analyze fundus color photographs in real time and provide risk assessments for the diseases, and the system also includes a user-friendly interface to improve the efficiency and accuracy of clinical workflow.

[0021] The present application also provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, any of the above methods for screening depression based on fundus color photography is implemented.

[0022] The present application also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, any of the above methods for screening depression based on fundus color photography is implemented.

[0023] Compared with the prior art, the present invention has the following advantages and technical achievements: (1) Provide early screening for depression: By measuring the features of fundus images, the extraction of features related to depression is increased. The random forest model is constructed based on the measured fundus image features and clinical risk factors. It can distinguish between healthy people and patients with depression, providing an objective and convenient tool for early screening and identification of depression.

[0024] (2) Improved popularity: By simplifying the data and using fundus color photographs and gender, age, and body mass index to identify depression, the system is more suitable for use in areas with scarce medical resources, significantly improving the popularity of depression screening.

[0025] (3) The model has strong robustness and generalization ability: The fundus image dataset was established using 400 healthy controls of the same age and gender (without personal identity information) with a clear diagnosis of depression in a public database for model training and verification, including a fundus photo dataset, a diagnosis of depression, and clinical risk factors (gender, age, and body mass index). In addition, relevant data from 300 subjects in hospitals and communities (without personal identity information) were collected to provide sufficient external verification samples for model training.

[0026] (4) Economic and social benefits: It is expected that the present invention will significantly reduce the medical costs caused by misdiagnosis and missed diagnosis, and may reduce the overall treatment costs of depression through early screening. In addition, objective, efficient and convenient classification tools will improve the accessibility of medical services and show the potential in improving the level of public medical care. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The drawings of the present invention are only used for illustrative purposes and should not be construed as limiting the present invention. In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for describing the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0028] Figure 1 The figure is a flow chart of the method of the present invention.

[0029] Figure 2 This is a diagram of the depression screening model based on fundus color photography of the present invention.

[0030] Figure 3 This is a diagram of the depression screening model based on fundus color photography and clinical risk factors of the present invention.

[0031] Figure 4 This is a flow chart of the random forest model of the present invention.

[0032] Figure 5 This is a color fundus photograph discrimination diagram of healthy and depressed individuals according to the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] Example 1 like Figure 1 As shown, the present invention provides a method for screening depression based on fundus color photography, comprising the following steps: Step S100: collecting an image dataset containing healthy individuals and depression patients; Step S200: performing feature measurement on the image data set; Step S300: constructing a model based on random forest to classify image data; Step S400: verify and evaluate the model.

[0035] Step S500: Apply the model to the clinical workflow to provide real-time disease screening.

[0036] The image dataset includes a large number of fundus color images collected from UK Biobank, communities and hospitals, the diagnosis of depression (mainly including whether it is diagnosed as depression, whether there is a preliminary diagnosis of eye diseases and other systemic diseases, such as cardiovascular and cerebrovascular diseases, neurodegenerative diseases and mental illnesses, as well as specific diagnosis) and clinical risk factors (gender, age, body mass index). The fundus images of healthy individuals and patients with depression are measured for features, and the extraction of features related to depression is increased. A model is built based on the random forest model, the image data is classified, and the model is verified and evaluated to improve the model, providing an objective and convenient tool for the early screening and identification of depression.

[0037] In this embodiment, if Figure 2 As shown in the figure, the input fundus image is subjected to feature measurements of the optic disc tilt angle and the optic disc roundness, and is input into the model with features such as gender, age and weight to distinguish between healthy people and people with depression.

[0038] Among them, the characteristic measurement of the optic disc tilt angle and the optic disc roundness is specifically: The angle of optic disc tilt is the angle between the major axis of the smallest outer ellipse and the horizontal line. Optic disc roundness:

[0039] Among them, C represents the roundness of the optic disc, F represents the optic disc area, that is, the number of pixels occupied by the optic disc area, and R represents the minimum circumference radius of the optic disc.

[0040] By measuring the features of the optic disc tilt angle and the optic disc roundness, the extraction of depression-related features is increased, thereby improving the accuracy of the model.

[0041] In this embodiment, combined with Figure 3 and Figure 4 As shown in the figure, the model used in this method is a random forest model. The model is constructed based on the measured fundus image features and clinical risk factors. It can distinguish between healthy people and patients with depression and is suitable for early screening and identification of depression. The features of the optic disc tilt angle and optic disc roundness, gender, weight and age of the fundus image are input into the random forest model. The random forest model randomly selects samples from the training sample set D, and uses the bootstrap method with replacement to randomly extract samples from the training sample set D into different sample sets D1, D2, D3, etc. Optic disc tilt angle, optic disc roundness, gender, age, and weight features are randomly selected for different sample sets and input into the decision tree. At each node of the decision tree, features are randomly selected for splitting. The Gini index is used as the standard for selecting features and dividing nodes. The random forest model is trained by preprocessing and feature selecting data.

[0042] The Gini index measures the probability that two samples randomly selected from a data set have inconsistent category labels. The smaller the Gini index, the higher the purity of the data set, that is, the greater the possibility that the samples belong to the same category. The calculation of the Gini index is as follows: for a data set D containing K categories, where K is 2, including healthy people and patients with depression, its Gini index is defined as:

[0043] Among them, pk is the proportion of samples of the kth category in the data set D; Feature A includes: optic disc tilt angle, optic disc roundness, gender, age and body mass index. For a division D1 and D2 under feature A, that is, the data set D is divided into two parts according to feature A, the Gini index after division is:

[0044] Among them, |D|, |D1| and |D2| represent the number of samples in datasets D, D1 and D2 respectively.

[0045] The decision tree in the above random forest model is constructed based on the CART algorithm, specifically: calculate the Gini index of each feature in the data set, select the feature with the smallest Gini index as the optimal partition feature, and divide the data set into different subsets according to different feature values; repeatedly calculate the Gini index of each feature in the data set for each subset, select the feature with the smallest Gini index as the optimal partition feature, and divide the data set into different subsets according to different feature values ​​until the stopping condition is met (the number of samples in the subset is less than the minimum number of samples of the algorithm's parameters, all samples belong to the same category, there are no more features to be divided, etc.); in order to avoid overfitting, the decision tree is pruned to remove leaf nodes with low gain and simplify the model. In order to ensure the robustness and generalization ability of the model, the random forest model uses five-fold cross-validation for internal validation and fundus image data and depression diagnosis for external validation. The fundus image data uses relevant data of 300 subjects in hospitals and communities whose personal identity information is concealed to provide sufficient external validation samples for model training.

[0046] In this embodiment, if Figure 5 As shown, it reflects the difference between the probability distribution predicted by the model and the true distribution. The cross entropy is used for evaluation, specifically:

[0047] Where x represents a possible value of the random variable (1 or 0, 1 represents depression and 0 represents a healthy control), n is the number of all possible values ​​of the random variable, p(x) and q(x) represent the probability of x in distribution p and q respectively; The formula specifically indicates the average coding length when encoding using the predicted distribution Q under the true distribution P, that is, the average information entropy, in bits or nats. The smaller the cross entropy value, the closer the two probability distributions are. The cross entropy here is a small value such as 0.2231. The lower the better.

[0048] In addition, the embodiment of the present application also provides a system for screening depression based on fundus color photography, including an image collection module for collecting fundus color photography image data sets of healthy individuals and patients with depression, a measurement module for measuring features of the image data sets, a generation model for building a random forest model and classifying image data, and a verification and evaluation module for verifying and evaluating the random forest model. Through fundus color photography images, the diagnosis of depression and clinical risk factors, model training and verification are performed on confirmed depression patients and healthy controls of the same age and gender to obtain a trained model for distinguishing healthy people from patients with depression, providing a convenient tool for early screening and identification of depression. The system also has the ability to process and analyze fundus color photography in real time, and provides risk assessment of the disease, and the system also includes a user-friendly interface to improve the efficiency and accuracy of clinical workflows.

[0049] In addition, an embodiment of the present application also provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the above-mentioned method for screening depression based on fundus color photography is implemented.

[0050] In addition, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, any of the above-mentioned methods for screening depression based on fundus color photography is implemented.

[0051] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the technical solution of the present invention, and are not intended to limit the specific implementation methods of the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the claims of the present invention shall be included in the protection scope of the claims of the present invention.

Claims

1. A method for screening depression based on fundus color photography, characterized in that: The following steps are involved: Step S100: collecting an image dataset containing healthy individuals and depression patients; Step S200: performing feature measurement on the image data set; Step S300: constructing a model based on random forest to classify image data; Step S400: verifying and evaluating the model; Step S500: Apply the model to the clinical workflow.

2. The method for screening depression based on fundus color photography according to claim 1, characterized in that: The feature measurements of the image dataset include the following indicators: Optic disc tilt angle: the angle between the major axis of the smallest outer ellipse and the horizontal line; Optic disc roundness: in, C represents the roundness of the optic disc, F Represents the optic disc area, that is, the number of pixels occupied by the optic disc area. R Represents the minimum circumferential radius of the optic disc.

3. The method for screening depression based on fundus color photography according to claim 2, characterized in that: The random forest model is constructed based on measured fundus image features and clinical risk factors, and includes the following steps: Step S310: Randomly select samples using the bootstrap method with replacement from the original data set containing fundus image features, depression diagnosis and clinical risk factors. D Randomly extract samples from the tree and build multiple decision trees; Step S320: randomly selecting features, the features including optic disc tilt angle, optic disc roundness, gender, age, and body mass index, and randomly selecting features for splitting at each node of each decision tree; Step S330: construct a decision tree, using the CART (Classification and Regression Trees) algorithm to construct the decision tree, and using the Gini Index as one of the criteria for selecting features and dividing nodes; Step S340: training the random forest model by using the preprocessed and feature selected data.

4. The method for screening depression based on fundus color photography according to claim 3, characterized in that: The smaller the Gini index is, the higher the purity of the data set is, that is, the greater the possibility that the samples belong to the same category; The calculation of the Gini index is K categories, here K 2, including data sets of healthy people and patients with depression D , and its Gini index is defined as: in, p k It is a dataset D Middle k The proportion of samples in the same class; feature A Including: optic disc tilt angle, optic disc roundness, gender, age and body mass index, for the characteristics A A division under D 1 and D 2. Dataset D According to the characteristics A Divided into two parts, the Gini index after division is: Among them, ∣ D ∣、∣ D 1| and| D 2∣ respectively represent data sets D , D 1 and D The sample size is 2.

5. The method for screening depression based on fundus color photography according to claim 4, characterized in that: The specific process of constructing a decision tree based on the CART algorithm includes the following steps: Step S321: Calculate the Gini index of each feature in the data set, select the feature with the smallest Gini index as the optimal partitioning feature, and divide the data set into different subsets according to different values ​​of the feature; Step S322: Repeat step S321 for each of the subsets until a stop condition is met; Step S333: pruning the decision tree.

6. The method for screening depression based on fundus color photography according to claim 5, characterized in that: The random forest model was internally validated using five-fold cross validation, and externally validated using fundus image data and the diagnosis of depression.

7. The method for screening depression based on fundus color photography according to claim 6, characterized in that: The evaluation uses cross entropy to evaluate the difference between the probability distribution predicted by the model and the true distribution: in, x represents a possible value of the random variable, which can be 1 or 0, 1 represents depression and 0 represents a healthy control), n is the number of all possible values ​​of the random variable, p ( x )and q ( x ) respectively represent x In distribution p and q The probability in the real distribution P Next, using the predictive distribution Q The average coding length during encoding, that is, the average information entropy, is expressed in bits or nats. The smaller the cross entropy value, the closer the two probability distributions are.

8. A system for screening depression based on fundus color photography constructed according to the method for screening depression based on fundus color photography according to any one of claims 1 to 7, characterized in that: include: An image collection module is used to: collect a fundus color image dataset containing healthy individuals and patients with depression; A measurement module, used to: perform feature measurement on the image data set; Generate a module to: build a random forest model to classify image data; Verification and evaluation module: verify and evaluate the random forest model; The depression screening system based on fundus color photography has the ability to process and analyze fundus color photography in real time and provide risk assessment of the disease.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for screening depression based on fundus color photography as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for screening depression based on fundus color photography as described in any one of claims 1 to 7 is implemented.

Images