AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

Bayesian-Optimized Superpixel-GrabCut for Traceable Optic Disc Segmentation

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

Optic disc (OD) segmentation is essential for diagnosing ophthalmic pathologies from retinal fundus images. However, prevailing deep learning approaches operate as opaque black boxes, lacking the inference-stage mathematical traceability--a critical requirement for algorithmic auditing and failure analysis in clinical workflows. This paper presents a fully algorithmically traceable and trainable segmentation pipeline that jointly combines superpixel decomposition, hybrid brightness-proximity superpixel scoring, morphological regularization, iterative GrabCut refinement, and elliptical shape fi

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-21T07:51:58.603Z. This is not the publication date.