Distribution-based detection of radiographic changes in pneumonia patterns: A COVID-19 case study

Although the classification of chest radiographs has long been an extensively researched topic, interest increased significantly with the onset of the COVID-19 pandemic. Existing results are promising; however, the radiological similarities between COVID-19 and other types of respiratory diseases li...

Full description

Saved in:
Bibliographic Details
Published in:Heliyon Vol. 10; no. 16; p. e35677
Main Authors: C. Pereira, Sofia, Rocha, Joana, Campilho, Aurélio, Mendonça, Ana Maria
Format: Journal Article
Language:English
Published: England Elsevier Ltd 30.08.2024
Elsevier
Subjects:
Anomaly detection
Autoencoder
case studies
chest
Coronavirus
COVID-19 infection
Deep learning
Distribution shift
image analysis
pneumonia
public health
radiography
X-ray
Deep learning
Coronavirus
X-ray
Autoencoder
Distribution shift
Anomaly detection
ISSN:2405-8440, 2405-8440
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Although the classification of chest radiographs has long been an extensively researched topic, interest increased significantly with the onset of the COVID-19 pandemic. Existing results are promising; however, the radiological similarities between COVID-19 and other types of respiratory diseases limit the success of conventional image classification approaches that focus on single instances. This study proposes a novel perspective that conceptualizes COVID-19 pneumonia as a deviation from a normative distribution of typical pneumonia patterns. Using a population-based approach, our approach utilizes distributional anomaly detection. This method diverges from traditional instance-wise approaches by focusing on sets of scans instead of individual images. Using an autoencoder to extract feature representations, we present instance-based and distribution-based assessments of the separability between COVID-positive and COVID-negative pneumonia radiographs. The results demonstrate that the proposed distribution-based methodology outperforms conventional instance-based techniques in identifying radiographic changes associated with COVID-positive cases. This underscores its potential as an early warning system capable of detecting significant distributional shifts in radiographic data. By continuously monitoring these changes, this approach offers a mechanism for early identification of emerging health trends, potentially signaling the onset of new pandemics and enabling prompt public health responses.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2405-8440
2405-8440
DOI:10.1016/j.heliyon.2024.e35677