Share Email Print

Proceedings Paper

Performance deterioration of deep neural networks for lesion classification in mammography due to distribution shift: an analysis based on artificially created distribution shift
Author(s): Alexej Gossmann; Kenny H. Cha; Xudong Sun
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Despite the prominent success of deep learning (DL) in medical imaging for tasks such as computer-aided detection and diagnosis, the field faces a number of challenging problems. An important issue is that of mismatch of data distributions between different data sources, also known as a distribution shift. Distribution shifts may also be present between different subpopulations or subgroups. Distribution shifts that are not easily detectable can prevent the successful deployment of DL models in medical imaging. We use variational inference to create subsets of a given dataset while enforcing artificial distribution shifts between these subsets, thus creating subsets with different characteristics that represent different pseudo “data sources”. By training and testing ROI-based malignant/benign lesion classification models over these pseudo data sources, we evaluate the extent to which distribution shift could deteriorate the performance of popular DL models. We show that distribution shift indeed poses a serious concern for malignant/benign lesion classification in mammography, and we show that the algorithmically created pseudo data sources may not correspond to any recorded clinical or image characteristics. This study shows a potential method for evaluating deep learning algorithms for robustness against distribution shifts. Furthermore, our technique can serve as a benchmark method for development of new models which aim to be robust to distribution shift.

Paper Details

Date Published: 16 March 2020
PDF: 11 pages
Proc. SPIE 11314, Medical Imaging 2020: Computer-Aided Diagnosis, 1131404 (16 March 2020);
Show Author Affiliations
Alexej Gossmann, U.S. Food and Drug Administration (United States)
Kenny H. Cha, U.S. Food and Drug Administration (United States)
Xudong Sun, Ludwig-Maximilians-Univ. München (Germany)

Published in SPIE Proceedings Vol. 11314:
Medical Imaging 2020: Computer-Aided Diagnosis
Horst K. Hahn; Maciej A. Mazurowski, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?