responsive site templates

AI-CT-COVID-19

A collaborative online AI engine for precise CT-based COVID-19 diagnosis


We deliver an AI-based CT diagnostic tool based on the concept of federated learning to provide people worldwide an effective AI model for precise CT-COVID diagnosis.

  • Federated learning - enables machine learning engineers and medical data scientists to work collectively with decentralized CT data with privacy by default and therefore everyone can contribute to a continuously-evolved and improved central AI model and help to provide people worldwide an effective AI model for precise CT-COVID diagnosis.
  • Initial central model - utilizing deep convolutional neural networks (CNNs), capable of classifying CT cases into COVID-19, other viral pneumonia, bacterial pneumonia, or healthy tissue, furthermore, assessing the severity for putative COVID-19 patients. 
  • Online diagnostic engine- providing interfaces for clinician to use and for biomedical data scientists to training new model starting from the central model with their own decentralized CT studies.

Federated Learning Framework

The federated learning framework is a decentralized architecture where the AI model is distributed to and executed at each host institution with the data sources or client ends for training and inferencing. The local copies of the AI model on the host institution eliminate network latencies and costs incurred due to sharing large size of data with the central server.

APIs

APIs for the implementation of federated learning.

Download Initial Model

Download model structure and weight infomation from the server.

Train Locally

Modify configuration and start training with local data.

Upload Parameters

Contribute to the updating of the model by uploading parameters to the server.

Mobirise

Online Diagnostic Engine 

Online diagnostic interface and AI development interface.

1

Upload CT Images

Upload your CT image files to the online diagnostic engine. (.DICOM format)

2

Start Diagnosis

Hit the "Start Diagnosis" button to begin.

3

Get Results

The classification and confidence results will be shown and able to be downloaded.

The initial model or offline APP running on your PC or server with local CT data is publicly available upon request at

tianxia@hust.edu or xbai@hust.edu.cn

Team

Principal Investigators

Xiang Bai, Tian Xia, Yongchao Xu

School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China.

Zhen Li, Yongchao Xu, Liya Ma, Chuou Xu

Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430030, China.

Chuangsheng Zheng, Fan Yang

Department of Radiology, Union Hospital of Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China.

Daniel L. Rubin

Department of Radiation Oncology, Stanford University School of Medicine

Pattanasak Mongkolwat

Faculty of Information and Communication Technology, Mahidol University, Thailand.

Guoping, Wang, Yaobing Chen

Institute of Pathology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430030, China

Jianjun Zhang

Thoracic/Head and Neck Medical Oncology, and Translational Molecular Pathology, The University of Texas MD Anderson Cancer Center

Ihab Roushdy Kamel

Russell H Morgan Department of Radiology & Radiologic Science, Johns Hopkins hospital, Johns Hopkins Medicine Institute

Nagaraj Holalkere, Neil J. Halin

CardioVascular and Interventional Radiology, Radiology for Quality and Operations, The CardioVascular Center at Tufts Medical Center, Radiology, Tufts University School of Medicine.

Jia Wu

Department of Radiation Oncology, Stanford University School of Medicine, 1070 Arastradero Rd, Palo Alto, CA94304.

Ming-wei Wang, Dehua Yang

The National Center for Drug Screening, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, Shanghai 201203, China.

Jianbo Shao, Xuehua Peng

Department of Radiology, Wuhan Children’s Hospital, Wuhan, China.

Xiang Wang

Department of Radiology, Wuhan Central Hospital, Wuhan, China.

Development

Jiehua Yang, Xian Yang, Ke Ma, Ziwei Fan, Jiefeng Gan, Changzheng Zhang, Xinyu, Zou, Dandan Tu, Xiaowu Liu, Chang Shu, Renhao Huang, Changzheng Zhang

Mobirise



This website and the reported AI engine based on federated learning framework support UN Sustainability Development Goals (UN SDGs), especially #3 Good Health and Well-Being.

- The team

Creative Commons License
This engine is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported License
Copyright © Huazhong University of Science and Technology. All rights reserved.
Contact ai.ct.covid.19@gmail.com for the international collaboration of AI engine.