Self-training with improved regularization for sample-efficient chest x-ray classification

Deepta Rajan; Jayaraman J. Thiagarajan; Alexandros Karargyris; Satyananda Kashyap

doi:10.1117/12.2582290

15 February 2021 Self-training with improved regularization for sample-efficient chest x-ray classification

Deepta Rajan, Jayaraman J. Thiagarajan, Alexandros Karargyris, Satyananda Kashyap

Proceedings Volume 11597, Medical Imaging 2021: Computer-Aided Diagnosis; 115971S (2021) https://doi.org/10.1117/12.2582290
Event: SPIE Medical Imaging, 2021, Online Only

Abstract

Automated diagnostic assistants in healthcare necessitate accurate AI models that can be trained with limited labeled data, can cope with severe class imbalances and can support simultaneous prediction of multiple disease conditions. To this end, we present a deep learning framework that utilizes a number of key components to enable robust modeling in such challenging scenarios. Using an important use-case in chest X-ray classification, we provide several key insights on the effective use of data augmentation, self-training via distillation and confidence tempering for small data learning in medical imaging. Our results show that using 85% lesser labeled data, we can build predictive models that match the performance of classifiers trained in a large-scale data setting.

Conference Presentation

Citation Download Citation

Deepta Rajan, Jayaraman J. Thiagarajan, Alexandros Karargyris, and Satyananda Kashyap "Self-training with improved regularization for sample-efficient chest x-ray classification", Proc. SPIE 11597, Medical Imaging 2021: Computer-Aided Diagnosis, 115971S (15 February 2021); https://doi.org/10.1117/12.2582290

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