Fatty Liver Prediction Method Based on Tongue Image Characteristics and BMI Index

Abstract

The invention discloses a fatty liver prediction method based on tongue image characteristics and BMI index, relating to the technical field of artificial intelligence. The invention comprises the following steps of: collecting tongue image samples and corresponding BMI indexes, randomly dividing into training data sets and testing data sets; performing feature extraction on the tongue image samples in the training data set, based on tongue quality and tongue coating color feature vector [pxi, pyi], tongue coating thickness eigenvector [T, M], tongue moistening dryness characteristic L, tonguefat and thin index I and BMI index to construct training feature vector [pxi, pyi, T, M, L, I, BMI], using the training feature vector to train the preset Random Forest model, and using the network style parameter method to optimize the Random Forest model; testing the Random Forest model by using the test data set until the best trained Random Forest model is output; using the best Random Forestmodel to predict the tongue body image to be predicted to obtain a prediction result. The invention improves the prediction effect of fatty liver and the accuracy rate of the prediction result, has simple model structure and occupies less resources.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, and more specifically relates to a method for predicting fatty liver based on tongue image features and BMI index. Background technique [0002] BMI (Body Mass Index) is a body mass index, which is a tool commonly used in the world to measure the ratio of weight to height. It uses the ratio between height and weight to measure whether a person is too thin or fat. Usually, patients with fatty liver Often because the fat content is too high, people are obese, so the BMI index plays an auxiliary role in judging fatty liver. [0003] The traditional fatty liver diagnosis often relies on doctors to cooperate with auxiliary examinations to make a diagnosis. For example, doctors diagnose fatty liver based on the patient's medical history and auxiliary examination items such as liver function, blood lipids, B-ultrasound, and CT. However, the current diagnostic methods rely on a la...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is: in order to solve the current problem of directly using tongue body images to predict fatty liver, which relies on a large number of samples and has a complex network structure, the present invention provides a method for predicting fatty liver based on tongue image features and BMI index

Images