用于可追溯视盘分割的贝叶斯优化超像素-GrabCut算法
Bayesian-Optimized Superpixel-GrabCut for Traceable Optic Disc Segmentation
浏览论文内容
中文总结 AI 辅助
该研究针对视盘分割中深度学习模型缺乏可追溯性的问题，提出贝叶斯优化的超像素-GrabCut可追溯分割流程，在Drishti-GS数据集上取得0.9536的戴斯系数，可作为黑箱模型的可追溯替代方案。
中文摘要 AI 辅助
视盘（OD）分割对于从视网膜眼底图像诊断眼科疾病至关重要。然而，主流深度学习方法如同不透明黑箱，缺乏推理阶段的数学可追溯性——这是临床工作流中算法审计与故障分析的关键要求。本文提出一种完全具备算法可追溯性和可训练性的分割流程，该流程联合结合了超像素分解、混合亮度-邻近度超像素评分、形态学正则化、迭代GrabCut优化以及椭圆形状拟合。超参数优化被构造成一个目标函数，并通过贝叶斯优化求解，以消除手动参数调整。在Drishti-GS数据集上的定量评估表明，我们的方法达到了0.9536的戴斯系数，匹配了最先进的性能。通过在所有处理阶段保持明确的数学透明度，我们的框架为医学审查和调试提供了一种确定性、可追溯的黑箱架构替代方案。
英文摘要
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 fitting. The hyperparameter optimization is formulated as an objective function and solved via Bayesian optimization to eliminate manual parameter tuning. A quantitative evaluation on the Drishti-GS dataset demonstrates that our method achieves a Dice coefficient of 0.9536, matching state-of-the-art performance. By maintaining explicit mathematical transparency across all processing stages, our framework offers a deterministic, traceable alternative to black-box architectures for medical review and debugging.
发表机构
- Indian Institute of Technology Delhi（印度德里理工学院）
- Gauhati University（古瓦哈提大学）
机构由 AI 辅助整理，请以论文原文为准。
