Boosting Sclera Segmentation through Semi-supervised Learning with Fewer Labels

TL;DR

This paper presents a semi-supervised learning framework for sclera segmentation that performs well with limited labeled data, addressing the challenge of scarce high-quality datasets in medical imaging.

Contribution

It introduces a novel semi-supervised sclera segmentation method with domain-specific enhancements and spatial transformations, validated on a new real-world dataset and public datasets.

Findings

Effective with fewer labeled samples

Outperforms existing methods on multiple datasets

Demonstrates robustness in real-world scenarios

Abstract

Sclera segmentation is crucial for developing automatic eye-related medical computer-aided diagnostic systems, as well as for personal identification and verification, because the sclera contains distinct personal features. Deep learning-based sclera segmentation has achieved significant success compared to traditional methods that rely on hand-crafted features, primarily because it can autonomously extract critical output-related features without the need to consider potential physical constraints. However, achieving accurate sclera segmentation using these methods is challenging due to the scarcity of high-quality, fully labeled datasets, which depend on costly, labor-intensive medical acquisition and expertise. To address this challenge, this paper introduces a novel sclera segmentation framework that excels with limited labeled samples. Specifically, we employ a semi-supervised learning method that integrates domain-specific improvements and image-based spatial transformations to enhance segmentation performance. Additionally, we have developed a real-world eye diagnosis dataset to enrich the evaluation process. Extensive experiments on our dataset and two additional public datasets demonstrate the effectiveness and superiority of our proposed method, especially with significantly fewer labeled samples.