Interpretable explanations of black box classifiers applied on medical images by meaningful perturbations using variational autoencoders

Hristina Uzunova; Jan Ehrhardt; Timo Kepp; Heinz Handels

doi:10.1117/12.2511964

15 March 2019 Interpretable explanations of black box classifiers applied on medical images by meaningful perturbations using variational autoencoders

Hristina Uzunova, Jan Ehrhardt, Timo Kepp, Heinz Handels

Author Affiliations +

Proceedings Volume 10949, Medical Imaging 2019: Image Processing; 1094911 (2019) https://doi.org/10.1117/12.2511964
Event: SPIE Medical Imaging, 2019, San Diego, California, United States

Abstract

The growing popularity of black box machine learning methods for medical image analysis makes their interpretability to a crucial task. To make a system, e.g. a trained neural network, trustworthy for a clinician, it needs to be able to explain its decisions and predictions. In this work, we tackle the problem of generating plausible explanations for the predictions of medical image classifiers, that are trained to differentiate between different types of pathologies and healthy tissues. An intuitive solution to determine which image regions influence the trained classifier is to find out whether the classification results change when those regions are deleted. This idea can be formulated as a minimization problem and thus efficiently implemented. However, the meaning of “deletion” of image regions, in our case pathologies in medical images, is not defined. We contribute by defining the deletion of pathologies, as the replacement by their healthy looking equivalent generated using variational autoencoders. The experiments with a classification neural network on OCT (Optical Coherence Tomography) images and brain lesion MRIs show that a meaningful replacement of “deleted” image regions has significant impact on the reliability of the generated explanations. The proposed deletion method is proven to be successful since our approach delivers the best results compared to four other established methods.

Conference Presentation

Citation Download Citation

Hristina Uzunova, Jan Ehrhardt, Timo Kepp, and Heinz Handels "Interpretable explanations of black box classifiers applied on medical images by meaningful perturbations using variational autoencoders", Proc. SPIE 10949, Medical Imaging 2019: Image Processing, 1094911 (15 March 2019); https://doi.org/10.1117/12.2511964

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