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

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: A collaborative online AI engine for CT-based COVID-19 diagnosis Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : wasabi.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
title	A collaborative online AI engine for CT-based COVID-19 diagnosis
Creator	Li, Zhen Peng, Xuehua Shao, Jianbo Wang, Xi Zhang, Jianjun Xia, Tian Wang, Xiang Shu, Chang Zhang, Wenqing Wu, Jia Wang, Ming-Wei Kamel, Ihab Ma, Bai, Xiang Liu, Xiaowu Tu, Dandan Xu, Yongchao Zhang, Changzheng Yang, Dehua Wang, Guoping Fan, Ziwei Gan, Jiefeng Halin, Neil Holalkere, Nagaraj Huang, Renhao Leng, Hongxiang Liya, Ma Mongkolwat, Pattanasak Xie, Xiaoliang Xu, Chuou Yang, Jiehua Yang, Xian Zheng, Chuangsheng Zou, Xinyu
source	MedRxiv; Medline; PMC
abstract	Artificial intelligence can potentially provide a substantial role in streamlining chest computed tomography (CT) diagnosis of COVID-19 patients. However, several critical hurdles have impeded the development of robust AI model, which include deficiency, isolation, and heterogeneity of CT data generated from diverse institutions. These bring about lack of generalization of AI model and therefore prevent it from applications in clinical practices. To overcome this, we proposed a federated learning-based Unified CT-COVID AI Diagnostic Initiative (UCADI, http://www.ai-ct-covid.team/), 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 without sharing individual patient data. Specifically, we firstly developed an initial AI CT model based on data collected from three Tongji hospitals in Wuhan. After model evaluation, we found that the initial model can identify COVID from Tongji CT test data at near radiologist-level (97.5% sensitivity) but performed worse when it was tested on COVID cases from Wuhan Union Hospital (72% sensitivity), indicating a lack of model generalization. Next, we used the publicly available UCADI framework to build a federated model which integrated COVID CT cases from the Tongji hospitals and Wuhan Union hospital (WU) without transferring the WU data. The federated model not only performed similarly on Tongji test data but improved the detection sensitivity (98%) on WU test cases. The UCADI framework will allow participants worldwide to use and contribute to the model, to deliver a real-world, globally built and validated clinic CT-COVID AI tool. This effort directly supports the United Nations Sustainable Development Goals’ number 3, Good Health and Well-Being, and allows sharing and transferring of knowledge to fight this devastating disease around the world.
has issue date	2020-05-19(xsd:dateTime)
bibo:doi	10.1101/2020.05.10.20096073
bibo:pmid	32511484
has license	cc-by-nc
sha1sum (hex)	cb3b31a9689432915797aa26a1f3191eaec335b5
schema:url	https://doi.org/10.1101/2020.05.10.20096073
resource representing a document's title	A collaborative online AI engine for CT-based COVID-19 diagnosis
has PubMed Central identifier	PMC7273252
has PubMed identifier	32511484
schema:publication	medRxiv
resource representing a document's body	covid:cb3b31a9689432915797aa26a1f3191eaec335b5#body_text
is schema:about of	named entity 'provide' named entity 'robust' named entity 'CNN' named entity 'source code' named entity 'nucleotide' named entity 'pneumonia' named entity 'COVID-19' named entity 'false negative' named entity 'radiologists' named entity 'diagnostic tool' named entity 'CT image' named entity 'high-quality' named entity 'COVID-19' named entity 'viral pneumonia' named entity 'COVID-19' named entity 'CNN' named entity 'pneumonia' named entity 'CNN' named entity 'federated learning' named entity 'diagnostic accuracy' named entity 'CNN' named entity 'RT-PCR' named entity 'asymptomatic carriers' named entity 'COVID-19' named entity 'COVID 19' named entity 'lung' named entity 'LWE' named entity 'CT image' named entity 'COVID-19' named entity 'secret key' named entity 'medical data' named entity 'virus' named entity 'COVID-19' named entity 'federated learning' named entity 'virus' named entity 'validation set' named entity '68%' named entity 'viral pneumonia' named entity 'lung' named entity 'information leakage' named entity '95%' named entity 'ground glass opacity' named entity 'homomorphic encryption' named entity 'COVID-19' named entity 'CNN' named entity 'sensitivity and specificity' named entity 'COVID-19' named entity 'COVID-19'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2025 OpenLink Software