Enhanced detection of neoplasia in esophageal biopsies via non-destructive 3D pathology with deep-learning triage

Lindsey A. Barner; Gan Gao; Deepti M. Reddi; Lydia Lan; Wynn Burke; William M. Grady; Jonathan T. C. Liu

doi:10.1117/12.2657485

17 March 2023 Enhanced detection of neoplasia in esophageal biopsies via non-destructive 3D pathology with deep-learning triage

Lindsey A. Barner, Gan Gao, Deepti M. Reddi, Lydia Lan, Wynn Burke, William M. Grady, Jonathan T. C. Liu

Author Affiliations +

Proceedings Volume PC12363, Multiscale Imaging and Spectroscopy IV; PC1236302 (2023) https://doi.org/10.1117/12.2657485
Event: SPIE BiOS, 2023, San Francisco, California, United States

Abstract

Esophageal adenocarcinoma (EAC), which can arise from Barrett’s esophagus (BE), has a 5-year survival rate of < 20%. Unfortunately, the severe sampling limitations associated with conventional histology may limit the sensitivity for detecting EAC and dysplasia (a precursor lesion to EAC) through regular endoscopic screening of BE patients. We have developed a non-destructive 3D pathology workflow to provide comprehensive evaluation of whole biopsies and a deep learning-based computational triage method that automatically segments potentially neoplastic regions (dysplasia or EAC) to guide pathologist review. A preliminary clinical validation study shows that our AI-assisted 3D workflow enables neoplasia to be identified with higher sensitivity on a per-biopsy level than conventional slide-based 2D histology.

Conference Presentation

Citation Download Citation

Lindsey A. Barner, Gan Gao, Deepti M. Reddi, Lydia Lan, Wynn Burke, William M. Grady, and Jonathan T. C. Liu "Enhanced detection of neoplasia in esophageal biopsies via non-destructive 3D pathology with deep-learning triage", Proc. SPIE PC12363, Multiscale Imaging and Spectroscopy IV, PC1236302 (17 March 2023); https://doi.org/10.1117/12.2657485

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