The effects of sparsity induction methods on attention-based multiple instance learning applied to Camelyon16

Thomas E. Tavolara; Metin N. Gurcan; M. Khalid Khan Niazi

doi:10.1117/12.2653885

6 April 2023 The effects of sparsity induction methods on attention-based multiple instance learning applied to Camelyon16

Thomas E. Tavolara, Metin N. Gurcan, M. Khalid Khan Niazi

Author Affiliations +

Proceedings Volume 12471, Medical Imaging 2023: Digital and Computational Pathology; 124710M (2023) https://doi.org/10.1117/12.2653885
Event: SPIE Medical Imaging, 2023, San Diego, California, United States

Abstract

Spectral decoupling, weight normalization, and L1 loss have been applied to varying degrees in studies concerning computational pathology. These methods induce sparsity and tend to improve overall model performance. However, no work has combined these methods to improve model performance. The work presented here combines and compares these three methods in an attention-based multiple instance learning model to classify whole slide histopathology images from Camelyon16. We observed that spectral decoupling improves accuracy and area under the curve (AUC), but that weight normalization and L1 loss do not. However, when either of the latter is combined with spectral decoupling, accuracy, and AUC further improve over just spectral decoupling. Finally, we demonstrate that varying the magnitude with which these three methods affect model training considerably affects the resulting testing accuracy and AUC.

Conference Presentation

Citation Download Citation

Thomas E. Tavolara, Metin N. Gurcan, and M. Khalid Khan Niazi "The effects of sparsity induction methods on attention-based multiple instance learning applied to Camelyon16", Proc. SPIE 12471, Medical Imaging 2023: Digital and Computational Pathology, 124710M (6 April 2023); https://doi.org/10.1117/12.2653885

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