Rapid Implementation of COVID-19 AI Assisted Diagnosis System Based on Supercomputing Platform

Abstract

As a global pandemic, New Coronary Pneumonia (COVID-19) has infected more than 10 million people worldwide. In the initial stage of outbreaks that lacks detection capabilities of nucleic acid testing, it become important approach to achieve the initial screening of patients through the application of artificial intelligence and other technologies. We proposed a technical solution to quickly establish a COVID-19 AI assisted diagnosis system by using the Tianhe artificial intelligence innovation integrated platform deployed on the Tianhe-1A supercomputer. The AI supported platform mainly includes three main parts: (1) the large-scale model training development and implementation environment that ensures the rapid training of the new crown AI-assisted diagnostic model; (2) the integration of artificial intelligence basic algorithm library that provides a shortcut for the selection of various artificial intelligence models of COVID-19 CT image classification; (3) the design and implementation of the artificial intelligence R&D cloud platform that realizes the online full life cycle management on modeling, training and deployment. Firstly, the data preprocessing and interactive modeling design are provided during the model building phase. Secondly, in the training phase, it provides huge computing source pool supporting parallel and concurrent tasks. Finally, after the model training is completed, the online deployment framework support is provided for public service. Based on the Tianhe artificial intelligence integrated platform, the whole process of modeling-training-validation-deployment activities of COVID-19 AI model development is realized. As a public welfare platform, the COVID-19 AI assisted diagnosis system has been adopted by more than 100 hospitals and research institutes around the world, and has contributed to the fight against the epidemic, which provides a technical reference for the rapid response to an outbreak.

Ähnliche Arbeiten