Boosting Sclera Segmentation through Semi-supervised Learning with Fewer Labels

2025-01-13

AI Summary

To address the scarcity and high acquisition cost of annotated data in sclera segmentation, this paper proposes a domain-prior-guided semi-supervised learning framework. Methodologically: (1) we design a sclera-aware spatial transformation augmentation strategy that explicitly encodes geometric and textural priors of the sclera; (2) we introduce the first real-world clinical ophthalmological dataset dedicated to sclera segmentation; and (3) we employ consistency-regularized semi-supervised training using a customized U-Net variant, jointly optimized across multiple datasets. Experiments demonstrate that our method achieves a Dice coefficient of 94.2% using only 10% labeled samples—significantly outperforming fully supervised baselines—and attains state-of-the-art performance on three public benchmarks. These results validate the effectiveness and generalizability of our approach for low-resource medical image segmentation.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Semi-Supervised Learning
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Security and Privacy: Data transparency and provenance
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

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.

Problem

• Limited Annotated Data
• Deep Learning
• Sclera Segmentation

Innovation

• Limited annotated data
• Sclera segmentation
• Data augmentation techniques