Explainable weakly-supervised learning for optical biomarker discovery in multiphoton virtual histology

Jindou Shi; Haohua Tu; Jaena Park; Stephen A. Boppart

doi:10.1117/12.2608769

9 March 2022 Explainable weakly-supervised learning for optical biomarker discovery in multiphoton virtual histology

Jindou Shi, Haohua Tu, Jaena Park, Stephen A. Boppart

Proceedings Volume PC12019, AI and Optical Data Sciences III; PC1201905 (2022) https://doi.org/10.1117/12.2608769
Event: SPIE OPTO, 2022, San Francisco, California, United States

Abstract

We present a weakly-supervised deep learning framework for human breast cancer-related optical biomarker discovery based on label-free autofluorescence multiharmonic (SLAM) microscopy. This framework consists of three stages: self-supervised consistency training for image representation learning at multiple scales; cancer region identification by weakly-supervised Multiple Instance Learning (MIL); optical biomarker discovery based on channel-wise attribution maps. Currently, the model has achieved an average AUC of 0.86 on the breast cancer global detection task. The attribution maps on different scales highlight distinct structures in SLAM which facilitate new insights into tumor micro-environment and field cancerization.

Conference Presentation

Citation Download Citation

Jindou Shi, Haohua Tu, Jaena Park, and Stephen A. Boppart "Explainable weakly-supervised learning for optical biomarker discovery in multiphoton virtual histology", Proc. SPIE PC12019, AI and Optical Data Sciences III, PC1201905 (9 March 2022); https://doi.org/10.1117/12.2608769

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