Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Boosting Sclera Segmentation through Semi-supervised Learning with Fewer Labels

Guanjun Wang, Lu Wang, Ning Niu, Qiaoyi Yao, Yixuan Wang, Sufen Ren, Shengchao Chen

TL;DR

This paper tackles the challenge of sclera segmentation under limited labeled data by introducing a semi-supervised framework that combines domain-specific augmentation and self-supervised learning with an enhanced U2Net backbone. A real-world eye-diagnosis dataset (≈800 images from 100+ patients) is introduced alongside evaluations on UBIRIS.v2 and SBVPI, showing strong performance with significantly fewer labels. The method demonstrates faster convergence and superior segmentation accuracy across multiple backbones and datasets, highlighting practical impact for eye CAD and biometrics while reducing labeling burdens. The approach promises robust scleral delineation in real-world, variable imaging conditions, enabling more reliable vessel-pattern extraction for downstream recognition and diagnosis.

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.

Boosting Sclera Segmentation through Semi-supervised Learning with Fewer Labels

TL;DR

This paper tackles the challenge of sclera segmentation under limited labeled data by introducing a semi-supervised framework that combines domain-specific augmentation and self-supervised learning with an enhanced U2Net backbone. A real-world eye-diagnosis dataset (≈800 images from 100+ patients) is introduced alongside evaluations on UBIRIS.v2 and SBVPI, showing strong performance with significantly fewer labels. The method demonstrates faster convergence and superior segmentation accuracy across multiple backbones and datasets, highlighting practical impact for eye CAD and biometrics while reducing labeling burdens. The approach promises robust scleral delineation in real-world, variable imaging conditions, enabling more reliable vessel-pattern extraction for downstream recognition and diagnosis.

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.
Paper Structure (20 sections, 12 equations, 9 figures, 4 tables)

This paper contains 20 sections, 12 equations, 9 figures, 4 tables.

Table of Contents

  1. Related Works
  2. Hand-crafted Features-based Scleral Segmentation
  3. Deep Learning-based Scleral Segmentation
  4. Preliminary
  5. Sclera Segmentation
  6. Semi-Supervised Learning
  7. Methodology
  8. Overview
  9. Data Augmentation
  10. Semi-supervised Segmentation Model
  11. SSL framework
  12. Segmentation Network
  13. Experiments and Results
  14. Dataset and Evaluation metrics
  15. Implementation Details
  16. ...and 5 more sections

Figures (9)

  • Figure 1: Overall structure of our method
  • Figure 2: Structure of the SSL framework
  • Figure 3: Improved U2Net architecture
  • Figure 4: Eye diagnostic instrument
  • Figure 5: Example images and corresponding sclera segmentation ground truths
  • ...and 4 more figures