Self-supervised equivariant regularization reconciles multiple-instance learning: joint referable diabetic retinopathy classification and lesion segmentation

Wenhui Zhu; Peijie Qiu; Natasha Lepore; Oana M. Dumitrascu; Yalin Wang

doi:10.1117/12.2669772

6 March 2023 Self-supervised equivariant regularization reconciles multiple-instance learning: joint referable diabetic retinopathy classification and lesion segmentation

Wenhui Zhu, Peijie Qiu, Natasha Lepore, Oana M. Dumitrascu, Yalin Wang

Author Affiliations +

Proceedings Volume 12567, 18th International Symposium on Medical Information Processing and Analysis; 125670D (2023) https://doi.org/10.1117/12.2669772
Event: 18th International Symposium on Medical Information Processing and Analysis, 2022, Valparaíso, Chile

Abstract

Lesion appearance is a crucial clue for medical providers to distinguish referable diabetic retinopathy (rDR) from non-referable DR. Most existing large-scale DR datasets contain only image-level labels rather than pixel-based annotations. This motivates us to develop algorithms to classify rDR and segment lesions via image-level labels. This paper leverages self-supervised equivariant learning and attention-based multi-instance learning (MIL) to tackle this problem. MIL is an effective strategy to differentiate positive and negative instances, helping us discard background regions (negative instances) while localizing lesion regions (positive ones). However, MIL only provides coarse lesion localization and cannot distinguish lesions located across adjacent patches. Conversely, a self-supervised equivariant attention mechanism (SEAM) generates a segmentation-level class activation map (CAM) that can guide patch extraction of lesions more accurately. Our work aims at integrating both methods to improve rDR classification accuracy. We conduct extensive validation experiments on the Eyepacs dataset, achieving an area under the receiver operating characteristic curve (AU ROC) of 0.958, outperforming current state-of-the-art algorithms.

Citation Download Citation

Wenhui Zhu, Peijie Qiu, Natasha Lepore, Oana M. Dumitrascu, and Yalin Wang "Self-supervised equivariant regularization reconciles multiple-instance learning: joint referable diabetic retinopathy classification and lesion segmentation", Proc. SPIE 12567, 18th International Symposium on Medical Information Processing and Analysis, 125670D (6 March 2023); https://doi.org/10.1117/12.2669772

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