About: Benchmarking Deep Learning Models and Automated Model Design for COVID-19 Detection with Chest CT Scans

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

About: Benchmarking Deep Learning Models and Automated Model Design for COVID-19 Detection with Chest CT Scans 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
has title	Benchmarking Deep Learning Models and Automated Model Design for COVID-19 Detection with Chest CT Scans
Creator	Liu, Xin He, Xin Wang, Shihao Chu, Xiaowen Ding, Guiguang Shi, Shaohuai Tang, Jiangping Yan, Chenggang Zhang, Jiyong
topic	covid:1ca354d24da3f91d6932a4558d946884a96929b5#this
Source	MedRxiv
abstract	COVID-19 pandemic has spread all over the world for months. As its transmissibility and high pathogenicity seriously threaten people's lives, the accurate and fast detection of the COVID-19 infection is crucial. Although many recent studies have shown that deep learning based solutions can help detect COVID-19 based on chest CT scans, there lacks a consistent and systematic comparison and evaluation on these techniques. In this paper, we first build a clean and segmented CT dataset called Clean-CC-CCII by fixing the errors and removing some noises in a large CT scan dataset CC-CCII with three classes: novel coronavirus pneumonia (NCP), common pneumonia (CP), and normal controls (Normal). After cleaning, our dataset consists of a total of 340,190 slices of 3,993 scans from 2,698 patients. Then we benchmark and compare the performance of a series of state-of-the-art (SOTA) 3D and 2D convolutional neural networks (CNNs). The results show that 3D CNNs outperform 2D CNNs in general. With extensive effort of hyperparameter tuning, we find that the 3D CNN model DenseNet3D121 achieves the highest accuracy of 88.63% (F1-score is 88.14% and AUC is 0.940), and another 3D CNN model ResNet3D34 achieves the best AUC of 0.959 (accuracy is 87.83% and F1-score is 86.04%). We further demonstrate that the mixup data augmentation technique can largely improve the model performance. At last, we design an automated deep learning methodology to generate a lightweight deep learning model MNas3DNet41 that achieves an accuracy of 87.14%, F1-score of 87.25%, and AUC of 0.957, which are on par with the best models made by AI experts. The automated deep learning design is a promising methodology that can help health-care professionals develop effective deep learning models using their private data sets. Our Clean-CC-CCII dataset and source code are available at: https://github.com/arthursdays/HKBU_HPML_COVID-19.
has issue date	2020-06-09(xsd:dateTime)
bibo:doi	10.1101/2020.06.08.20125963
has license	medrxiv
sha1sum (hex)	1ca354d24da3f91d6932a4558d946884a96929b5
schema:url	https://doi.org/10.1101/2020.06.08.20125963
resource representing a document's title	Benchmarking Deep Learning Models and Automated Model Design for COVID-19 Detection with Chest CT Scans
resource representing a document's body	covid:1ca354d24da3f91d6932a4558d946884a96929b5#body_text
is http://vocab.deri.ie/void#inDataset of	https://covidontheweb.inria.fr:4443/about/id/http/ns.inria.fr/covid19/1ca354d24da3f91d6932a4558d946884a96929b5
is schema:about of	named entity 'controls' named entity 'deep learning' named entity 'dataset' named entity 'based' named entity 'large' named entity 'normal' named entity 'automated' named entity 'models' named entity 'extensive' named entity 'deep learning' named entity 'Chest' named entity 'CT Scans' named entity 'IS A' named entity 'NOVEL CORONAVIRUS' named entity 'FAST' named entity 'BUILD' named entity 'MODEL' named entity 'THESE' named entity 'PATHOGENICITY' named entity 'REMOVING' named entity 'EFFORT' named entity 'DATA SETS' named entity 'LIVES' named entity 'RESULTS' named entity 'OUR' named entity 'CARE' named entity 'noises' named entity 'studies' named entity 'performance' named entity 'demonstrate' named entity 'score' named entity 'score' named entity 'CNNs' named entity 'effective' named entity 'private' named entity 'pneumonia' named entity 'model' named entity 'data augmentation' named entity 'After' named entity 'benchmark' named entity 'systematic' named entity 'CNN' named entity 'Normal' named entity 'deep learning' named entity 'health-care' named entity 'series' named entity 'deep learning' named entity 'hyperparameter' named entity 'pneumonia' named entity 'CNN' named entity 'github.com' named entity 'COVID' named entity 'pathogenicity' named entity 'convolutional neural networks' named entity 'Benchmarking' named entity 'open-source' named entity 'lung' named entity 'X-ray images' named entity 'greyscale' named entity 'pneumonia' named entity 'slice sampling' named entity 'chest X-rays' named entity 'CT images' named entity 'training set' named entity 'COVID' named entity 'embedded devices' named entity 'China' named entity 'COVID' named entity 'CNN' named entity 'viral pneumonia' named entity 'data augmentation' named entity 'medRxiv' named entity 'random sampling' named entity 'rRT-PCR' named entity 'deep learning'

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 © 2009-2024 OpenLink Software