Co-occurring diseases heavily influence the performance of weakly supervised learning models for classification of chest CT

Fakrul Islam Tushar; Vincent M. D'Anniballe; Geoffrey D. Rubin; Ehsan Samei; Joseph Y. Lo

doi:10.1117/12.2612700

4 April 2022 Co-occurring diseases heavily influence the performance of weakly supervised learning models for classification of chest CT

Fakrul Islam Tushar, Vincent M. D'Anniballe, Geoffrey D. Rubin, Ehsan Samei, Joseph Y. Lo

Author Affiliations +

Proceedings Volume 12033, Medical Imaging 2022: Computer-Aided Diagnosis; 120332J (2022) https://doi.org/10.1117/12.2612700
Event: SPIE Medical Imaging, 2022, San Diego, California, United States

Abstract

Despite the potential of weakly supervised learning to automatically annotate massive amounts of data, little is known about its limitations for use in computer-aided diagnosis (CAD). For CT specifically, interpreting the performance of CAD algorithms can be challenging given the large number of co-occurring diseases. This paper examines the effect of co-occurring diseases when training classification models by weakly supervised learning, specifically by comparing multi-label and multiple binary classifiers using the same training data. Our results demonstrated that the binary model outperformed the multi-label classification in every disease category in terms of AUC. However, this performance was heavily influenced by co-occurring diseases in the binary model, suggesting it did not always learn the correct appearance of the specific disease. For example, binary classification of lung nodules resulted in an AUC of < 0.65 when there were no other co-occurring diseases, but when lung nodules cooccurred with emphysema, the performance reached AUC < 0.80. We hope this paper revealed the complexity of interpreting disease classification performance in weakly supervised models and will encourage researchers to examine the effect of co-occurring diseases on classification performance in the future.

Citation Download Citation

Fakrul Islam Tushar, Vincent M. D'Anniballe, Geoffrey D. Rubin, Ehsan Samei, and Joseph Y. Lo "Co-occurring diseases heavily influence the performance of weakly supervised learning models for classification of chest CT", Proc. SPIE 12033, Medical Imaging 2022: Computer-Aided Diagnosis, 120332J (4 April 2022); https://doi.org/10.1117/12.2612700

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
5 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Binary data

Emphysema

Performance modeling

Computed tomography

Machine learning

Data modeling

Lung

Show All Keywords

Keywords/Phrases

Search In:

Publication Years