How can data augmentation improve attribution maps for disease subtype explainability

3 April 2023 How can data augmentation improve attribution maps for disease subtype explainability

Elina Thibeau Sutre, Jelmer M. Wolterink, Olivier Colliot, Ninon Burgos

Proceedings Volume 12464, Medical Imaging 2023: Image Processing; 1246424 (2023) https://doi.org/10.1117/12.2653809
Event: SPIE Medical Imaging, 2023, San Diego, California, United States

Conference Poster

Abstract

As deep learning has been widely used for computer aided-diagnosis, we wished to know whether attribution maps obtained using gradient back-propagation could correctly highlight the patterns of disease subtypes discovered by a deep learning classifier. As the correctness of attribution maps is difficult to evaluate directly on medical images, we used synthetic data mimicking the difference between brain MRI of controls and demented patients to design more reliable evaluation criteria of attribution maps. We demonstrated that attribution maps may mix the regions associated with different subtypes for small data sets while they could accurately characterize both subtypes using a large data set. We then proposed simple data augmentation techniques and showed that they could improve the coherence of the explanations for a small data set. .

Citation Download Citation

Elina Thibeau Sutre, Jelmer M. Wolterink, Olivier Colliot, and Ninon Burgos "How can data augmentation improve attribution maps for disease subtype explainability", Proc. SPIE 12464, Medical Imaging 2023: Image Processing, 1246424 (3 April 2023); https://doi.org/10.1117/12.2653809

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