Aug 27, 2020Health Sciences0 likes Auto-indexed

Multi-Centre Optimization and Validation of an Open Deep Learning Model for Covid-19 Detection on Chest Radiographs

Keywords:Multi-CentreOptimizationValidationOpen Deep Learning ModelCOVID-19CoronavirusDetectionChestRadiographsDeep LearningChest Radiographs
Poster thumbnail

Description

Introduction The radiographic appearance of Covid-19 infection is fairly unique – characterized by bilateral symmetrical ground-glass consolidation without pleural effusion – and has been reported on both chest CT and chest radiographs (CXRs). Based on the hypothesis that this uniqueness can be used to reliably diagnose Covid-19 on CXRs, we performed a study to assess and optimize the ability of COVID-Net, an open-source deep learning model published by the University of Waterloo, to detect Covid-19 on local CXRs. Objective To optimize and validate COVID-Net for the prediction of Covid-19 in CXRs of Malaysian patients Methods [Refer to Poster]. Results [Refer to Poster]. Conclusion The published (unoptimized) COVID-Net model has mediocre performance which improved tremendously after optimization. This suggests the model is robust but requires optimization with local CXRs before consideration for clinical use. Class activation maps do not reflect disease distribution. Further work is required for model explainability.

Conference Information

NMRR-20-949-54941

Year:2020

Identifiers

Authors

Kim-Ann Git

Hospital Selayang

ORCID: https://orcid.org/0000-0002-4398-0040

Aida binti Abdul Aziz

Hospital Sungai Buloh

Law Kiew Siong

Sarawak General Hospital

Lau Song Lung

Sarawak General Hospital

Preetvinder a/l Dheer Singh

Hospital Raja Permaisuri Bainun

Tan Ying Sern

Taiping Hospital

Eric Chung

University Malaya Medical Centre

Kiew Siong Lau

Sarawak General Hospital

Additional Information

LanguageEnglish
Formatapplication/pdf
Version1
License
Creative Commons Attribution 4.0 International
Indexed fromZenodo