New coronal pneumonia disease patient risk screening deep learning system based on ocular surface characteristics

Abstract

The invention belongs to the crossing field of medical image and computer image recognition, and provides an ocular surface feature-based new coronal pneumonia disease patient risk screening deep learning system, which is used for carrying out new coronal pneumonia disease risk screening on a patient through an eye region in a shot face picture, and comprises a face image preprocessing part, a human face recognition part and a human face recognition part, the preprocessing module is used for preprocessing the face picture and obtaining an eye region picture; the eye image feature extraction part is used for extracting basic features of the eye region picture through the trained eye image feature extraction model; and the classification part is used for carrying out picture-level disease category prediction according to the basic features and obtaining a picture-level classification result, and is used for carrying out disease-level classification according to the picture-level classification result and obtaining a new coronal pneumonia disease-level prediction result.

Description

technical field [0001] The invention belongs to the cross field of medical imaging and computer image recognition, and specifically relates to a deep learning system for risk screening of patients with new coronary pneumonia disease based on ocular surface characteristics. Background technique [0002] Over the past few decades, deep learning (DL)-based artificial intelligence techniques have achieved remarkable progress in various computer vision tasks such as object detection, image classification, instance segmentation, and object recognition. [0003] In recent years, the advantages of deep learning have made it widely used in medical image analysis, for example, to classify different diseases, autism spectrum disorder or Alzheimer's disease in the brain, breast cancer, diabetic retina lesions and glaucoma, as well as common conditions such as lung cancer or pneumonia. [0004] In addition, some work has used deep learning technology to learn and extract CT image featur...

AI Technical Summary

Problems solved by technology

However, the existing disease patient screening technology has shortcomings such as poor timeliness, high equipment requirements, and reliance on professionals. The shooting of CT images requires professional CT equipment for shooting and requires professionals to operate. At the same time, due to the shooting and imaging It takes a long time, and it is impossible to quickly extract the features of CT images and complete the identification and screening of disease patients

In the prevention and control stage of the new coronary pneumonia (COVID-19), the risk screening of patients with new coronary pneumonia cannot be quickly completed based on CT images

Images