Unifying Structure Analysis and Surrogate-driven Function Regression for Glaucoma OCT Image Screening

TL;DR

This paper introduces a unified semi-supervised multi-task learning framework that combines structure analysis and function regression for improved glaucoma detection from OCT images, outperforming experts and baselines.

Contribution

It is the first to unify structure analysis and function regression in glaucoma OCT image screening, utilizing a large dataset and semi-supervised learning for enhanced accuracy.

Findings

Achieved 93.2% accuracy, F1 score, and 97.8% AUC.

Outperformed baseline methods and glaucoma experts.

Built the largest glaucoma OCT image dataset with 4877 volumes.

Abstract

Optical Coherence Tomography (OCT) imaging plays an important role in glaucoma diagnosis in clinical practice. Early detection and timely treatment can prevent glaucoma patients from permanent vision loss. However, only a dearth of automated methods has been developed based on OCT images for glaucoma study. In this paper, we present a novel framework to effectively classify glaucoma OCT images from normal ones. A semi-supervised learning strategy with smoothness assumption is applied for surrogate assignment of missing function regression labels. Besides, the proposed multi-task learning network is capable of exploring the structure and function relationship from the OCT image and visual field measurement simultaneously, which contributes to classification performance boosting. Essentially, we are the first to unify the structure analysis and function regression for glaucoma screening. It is also worth noting that we build the largest glaucoma OCT image dataset involving 4877 volumes to develop and evaluate the proposed method. Extensive experiments demonstrate that our framework outperforms the baseline methods and two glaucoma experts by a large margin, achieving 93.2%, 93.2% and 97.8% on accuracy, F1 score and AUC, respectively.