Training method of classification deep neural network model and genetic disease detection method

Abstract

The invention discloses a training method and device of a classification deep neural network model and a genetic disease detection method and device. The training method comprises the following steps:constructing a genetic disease data set, wherein the genetic disease data set comprises a genetic disease face data set and a classification label; inputting a training set in the genetic disease data set into a pre-training model of a classification deep neural network to obtain a classification vector, and determining a classification loss cost function value based on the classification vectorand the classification label; and training a pre-training model of the classification deep neural network based on the classification loss cost function value and the training parameters, and stoppingtraining until the classification loss cost function value is smaller than a preset threshold to obtain a trained classification deep neural network model. According to the technical scheme, photos or videos of patients can be automatically detected, doctors are assisted in judging genetic diseases, a large amount of manpower and material resources can be saved, and meanwhile the problems of tension, imbalance and the like of medical resources can be relieved.

Description

technical field [0001] The invention relates to the technical field of deep learning, in particular to a training method and device for a classification deep neural network model, and a genetic disease detection method and device. Background technique [0002] At present, the detection of genetic diseases is mainly through the collection of the blood of the person being tested and then through genetic testing or biochemical, chromosome and other testing methods, combined with the analysis and judgment of clinical data by doctors to obtain the final diagnosis result. Since this method requires the participation of labor and advanced medical equipment throughout the process, there are deficiencies in the following aspects: [0003] 1. Existing technical methods of manual testing require the full participation of medical staff, and some advanced medical testing equipment require huge labor costs, equipment costs and time costs. [0004] 2Because of medical equipment, the teste...

AI Technical Summary

Problems solved by technology

[0006] The problem solved by the present invention is that the existing manual detection technology requires the participation of medical personnel throughout the process, and requires advanced medical detection equipment, and the cost is relatively high

Images