Header

UZH-Logo

Maintenance Infos

Detection of tuberculosis patterns in digital photographs of chest X-ray images using Deep Learning: feasibility study


Becker, A S; Blüthgen, C; Phi van, V D; Sekaggya-Wiltshire, C; Castelnuovo, B; Kambugu, A; Fehr, J; Frauenfelder, T (2018). Detection of tuberculosis patterns in digital photographs of chest X-ray images using Deep Learning: feasibility study. The International Journal of Tuberculosis and Lung Disease, 22(3):328-335.

Abstract

OBJECTIVE To evaluate the feasibility of Deep Learning-based detection and classification of pathological patterns in a set of digital photographs of chest X-ray (CXR) images of tuberculosis (TB) patients. MATERIALS AND METHODS In this prospective, observational study, patients with previously diagnosed TB were enrolled. Photographs of their CXRs were taken using a consumer-grade digital still camera. The images were stratified by pathological patterns into classes: cavity, consolidation, effusion, interstitial changes, miliary pattern or normal examination. Image analysis was performed with commercially available Deep Learning software in two steps. Pathological areas were first localised; detected areas were then classified. Detection was assessed using receiver operating characteristics (ROC) analysis, and classification using a confusion matrix. RESULTS The study cohort was 138 patients with human immunodeficiency virus (HIV) and TB co-infection (median age 34 years, IQR 28-40); 54 patients were female. Localisation of pathological areas was excellent (area under the ROC curve 0.82). The software could perfectly distinguish pleural effusions from intraparenchymal changes. The most frequent misclassifications were consolidations as cavitations, and miliary patterns as interstitial patterns (and vice versa). CONCLUSION Deep Learning analysis of CXR photographs is a promising tool. Further efforts are needed to build larger, high-quality data sets to achieve better diagnostic performance.

Abstract

OBJECTIVE To evaluate the feasibility of Deep Learning-based detection and classification of pathological patterns in a set of digital photographs of chest X-ray (CXR) images of tuberculosis (TB) patients. MATERIALS AND METHODS In this prospective, observational study, patients with previously diagnosed TB were enrolled. Photographs of their CXRs were taken using a consumer-grade digital still camera. The images were stratified by pathological patterns into classes: cavity, consolidation, effusion, interstitial changes, miliary pattern or normal examination. Image analysis was performed with commercially available Deep Learning software in two steps. Pathological areas were first localised; detected areas were then classified. Detection was assessed using receiver operating characteristics (ROC) analysis, and classification using a confusion matrix. RESULTS The study cohort was 138 patients with human immunodeficiency virus (HIV) and TB co-infection (median age 34 years, IQR 28-40); 54 patients were female. Localisation of pathological areas was excellent (area under the ROC curve 0.82). The software could perfectly distinguish pleural effusions from intraparenchymal changes. The most frequent misclassifications were consolidations as cavitations, and miliary patterns as interstitial patterns (and vice versa). CONCLUSION Deep Learning analysis of CXR photographs is a promising tool. Further efforts are needed to build larger, high-quality data sets to achieve better diagnostic performance.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

0 downloads since deposited on 08 Mar 2018
0 downloads since 12 months

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:04 Faculty of Medicine > University Hospital Zurich > Clinic for Diagnostic and Interventional Radiology
04 Faculty of Medicine > University Hospital Zurich > Clinic for Infectious Diseases
Dewey Decimal Classification:610 Medicine & health
Language:English
Date:1 March 2018
Deposited On:08 Mar 2018 12:05
Last Modified:30 Jun 2018 05:59
Publisher:International Union Against Tuberculosis and Lung Disease
ISSN:1027-3719
OA Status:Closed
Free access at:Publisher DOI. An embargo period may apply.
Publisher DOI:https://doi.org/10.5588/ijtld.17.0520
PubMed ID:29471912

Download