About: Sample-Efficient Deep Learning for COVID-19 Diagnosis Based on CT Scans

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

About: Sample-Efficient Deep Learning for COVID-19 Diagnosis Based on CT Scans Goto Sponge NotDistinct Permalink

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

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
title	Sample-Efficient Deep Learning for COVID-19 Diagnosis Based on CT Scans
Creator	He, Xuehai Xie, Pengtao Xing, Eric Yang, Xingyi Zhang, Shanghang Zhang, Yichen Zhao, Jinyu
source	MedRxiv
abstract	Coronavirus disease 2019 (COVID-19) has infected more than 1.3 million individuals all over the world and caused more than 106,000 deaths. One major hurdle in controlling the spreading of this disease is the inefficiency and shortage of medical tests. There have been increasing efforts on developing deep learning methods to diagnose COVID-19 based on CT scans. However, these works are difficult to reproduce and adopt since the CT data used in their studies are not publicly available. Besides, these works require a large number of CTs to train accurate diagnosis models, which are difficult to obtain. In this paper, we aim to address these two problems. We build a publicly-available dataset containing hundreds of CT scans positive for COVID-19 and develop sample-efficient deep learning methods that can achieve high diagnosis accuracy of COVID-19 from CT scans even when the number of training CT images are limited. Specifically, we propose an Self-Trans approach, which synergistically integrates contrastive self-supervised learning with transfer learning to learn powerful and unbiased feature representations for reducing the risk of overfitting. Extensive experiments demonstrate the superior performance of our proposed Self-Trans approach compared with several state-of-the-art baselines. Our approach achieves an F1 of 0.85 and an AUC of 0.94 in diagnosing COVID-19 from CT scans, even though the number of training CTs is just a few hundred.
has issue date	2020-04-17(xsd:dateTime)
bibo:doi	10.1101/2020.04.13.20063941
has license	medrxiv
sha1sum (hex)	bc1edd72df527404508d48292ecfa6e0137ae333
schema:url	https://doi.org/10.1101/2020.04.13.20063941
resource representing a document's title	Sample-Efficient Deep Learning for COVID-19 Diagnosis Based on CT Scans
resource representing a document's body	covid:bc1edd72df527404508d48292ecfa6e0137ae333#body_text
is schema:about of	named entity 'SUPERIOR' named entity 'CONTROLLING' named entity 'OUR APPROACH' named entity 'TESTS' named entity 'OUR' named entity 'USED' named entity 'TRANSFER LEARNING' named entity 'ADDRESS' named entity 'EFFICIENT' named entity 'COVID19' named entity 'ResNet' named entity 'CT scans' named entity 'medRxiv' named entity 'multi-layer perceptron' named entity 'chest X-rays' named entity 'medical imaging' named entity 'CT scans' named entity 'self-supervised learning' named entity 'COVID-19' named entity 'CT scans' named entity 'medical tests' named entity 'deep learning' named entity 'COVID-19' named entity 'Coronavirus disease 2019' named entity 'overfitting' named entity 'Deep Learning' named entity 'COVID-19' named entity 'transfer learning' named entity 'SSL' named entity 'neural network' named entity 'image classification' named entity 'deep learning' named entity 'ImageNet' named entity 'data augmentation' named entity 'SSL' named entity 'COVID-19' named entity 'self-supervised learning' named entity 'COVID-19' named entity 'CC-BY-NC-ND 4.0' named entity 'COVID-19' named entity 'RT-PCR' named entity 'CT scans' named entity 'bioRxiv' named entity 'CT scan' named entity 'maximum and minimum' named entity 'SSL' named entity 'preprint' named entity 'multi-task learning' named entity 'open research' named entity 'clinical findings' named entity 'Random Forest' named entity 'COVID-19' named entity 'neural networks' named entity 'infection' named entity 'preprint' named entity 'LMN' named entity 'transfer learning' named entity 'medRxiv' named entity 'self-supervised learning' named entity 'COVID-19' named entity 'ImageNet' named entity 'COVID-19' named entity 'SSL' named entity 'CTs' named entity 'CTs' named entity 'overfitting' named entity 'pooling layer' named entity 'ImageNet' named entity 'COVID19' named entity 'COVID-19' named entity 'COVID-19' named entity 'COVID-19' named entity 'preprint' named entity 'extracted features' named entity 'Computed tomography' named entity 'large-scale' named entity 'self-supervised learning' named entity 'COVID-19' named entity 'Algorithm'

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