Model training method, device and equipment and medium

Abstract

The invention discloses a model training method which comprises the steps of obtaining a first sample data set, wherein each sample data in the first sample data set comprises a three-dimensional brain image, non-image information and a first labeling label of a tested person, and the first labeling labels are used for identifying whether the tested person suffers from a nervous system degeneration disease or is normal; using the first sample data set to train a neural network model, generating an end-to-end classification model, wherein the classification model takes a three-dimensional brainimage and non-image information of a first designated testee as input and takes a classification label of the first designated testee as output, and the classification label of the first designated testee is used for identifying that the first designated testee suffers from the nervous system degeneration disease or is normal. The method has higher accuracy and can provide reference suggestions for clinicians so as to improve the working efficiency of the clinicians. The invention further discloses a model training device and equipment and a computer storage medium.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular to a model training method, device, equipment and medium. Background technique [0002] Nervous system degenerative diseases are a kind of diseases with slow onset, progressive course and poor prognosis. So far, there is no effective cure method. The common clinical neurodegenerative diseases include Parkinson's disease (Parkinson's disease, PD), amyotrophic lateral Sclerosis (amyotrophic lateral sclerosis, ALS), Huntington's disease (Huntington's disease, HD) and Alzheimer's disease (Alzheimer's disease, AD), etc., although these diseases have different causes, they all have different parts of the central nervous system and Different degrees of neuronal loss and dysfunction. [0003] At present, in clinical practice, the method of artificial intelligence is often used to carry out computer-aided identification and prediction of neurodegenerative diseases thr...

AI Technical Summary

Problems solved by technology

[0004] At present, the widely used scheme is to preprocess the brain image to determine the local area, and then analyze the local area in the brain image based on the neural network model trained by traditional machine learning methods to obtain recognition or prediction. As a result, the effect of this scheme is not ideal in practical applications, and the reliability of the reference data it provides is not high

Images