Skip to main navigation Skip to search Skip to main content

Clinically Interpretable Geometric Constraints for Optic Cup and Disc Segmentation

  • Rui Qin
  • , Bailiang Zhao
  • , Kuo Yang
  • , Yue Wu
  • , Peng Gao
  • , Menghan Hu
  • East China Normal University
  • Shanghai Jiao Tong University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

We present GCN-CIS, a segmentation framework that embeds clinically interpretable geometric constraints into deep networks for optic cup and disc delineation in fundus images. A Prior Boundary Attention Module (PBAM) sharpens boundary predictions, while an ISNT-guided geometric loss enforces anatomically plausible regional ordering. Evaluated on an internal glaucoma screening set and three public benchmarks (REFUGE, ORIGA, Drishti-GS), GCN-CIS yields consistent gains in cup/disc Dice and reduces vCDR error compared to strong baselines. The method improves clinical reliability of segmentation outputs and facilitates efficient vCDR estimation for screening workflows. Code will be released.

Original languageEnglish
Title of host publicationProceedings - 2025 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2025
EditorsJuan Liu, Jingshan Huang, Xiaowo Wang, Fa Zhang, Xiufen Zou, Tian Tian, Xiaohua Hu, Bin Hu, Yi Xiong
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1805-1808
Number of pages4
ISBN (Electronic)9798331515577
DOIs
StatePublished - 2025
Event2025 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2025 - Wuhan, China
Duration: 15 Dec 2025 → 18 Dec 2025

Publication series

NameProceedings - 2025 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2025

Conference

Conference2025 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2025
Country/TerritoryChina
CityWuhan
Period15/12/25 → 18/12/25

Keywords

  • Boundary-Aware Attention
  • Clinically Oriented Segmentation
  • Geometrically Constrained Interpretable Model
  • ISNT-Guided Loss Function

Fingerprint

Dive into the research topics of 'Clinically Interpretable Geometric Constraints for Optic Cup and Disc Segmentation'. Together they form a unique fingerprint.

Cite this