A Macro-Micro Weakly-supervised Framework for AS-OCT Tissue Segmentation

TL;DR

This paper introduces a macro-micro weakly-supervised framework for accurate AS-OCT tissue segmentation, effectively leveraging limited fully-annotated data and abundant weakly-annotated images to improve performance and reduce annotation effort.

Contribution

It proposes a novel dual-model framework with uncertainty-guided strategies that outperforms existing semi- and weakly-supervised methods in AS-OCT tissue segmentation.

Findings

Outperforms state-of-the-art semi-/weakly-supervised methods

Achieves comparable performance to fully-supervised methods

Reduces annotation workload significantly

Abstract

Primary angle closure glaucoma (PACG) is the leading cause of irreversible blindness among Asian people. Early detection of PACG is essential, so as to provide timely treatment and minimize the vision loss. In the clinical practice, PACG is diagnosed by analyzing the angle between the cornea and iris with anterior segment optical coherence tomography (AS-OCT). The rapid development of deep learning technologies provides the feasibility of building a computer-aided system for the fast and accurate segmentation of cornea and iris tissues. However, the application of deep learning methods in the medical imaging field is still restricted by the lack of enough fully-annotated samples. In this paper, we propose a novel framework to segment the target tissues accurately for the AS-OCT images, by using the combination of weakly-annotated images (majority) and fully-annotated images (minority). The proposed framework consists of two models which provide reliable guidance for each other. In addition, uncertainty guided strategies are adopted to increase the accuracy and stability of the guidance. Detailed experiments on the publicly available AGE dataset demonstrate that the proposed framework outperforms the state-of-the-art semi-/weakly-supervised methods and has a comparable performance as the fully-supervised method. Therefore, the proposed method is demonstrated to be effective in exploiting information contained in the weakly-annotated images and has the capability to substantively relieve the annotation workload.