提出可追溯的视盘分割方法，解决深度学习黑箱问题
Bayesian-Optimized Superpixel-GrabCut for Traceable Optic Disc Segmentation
- 结合超像素与GrabCut迭代优化，全程数学可追溯
- 在Drishti-GS数据集上达0.9536的Dice系数
- 适合医疗算法审计与临床故障分析场景
视盘（OD）分割对从视网膜眼底图像诊断眼科疾病至关重要。然而，当前主流深度学习方法作为不可解释的黑箱，缺乏推理阶段的数学可追溯性——这在临床工作流中进行算法审计和故障分析时是关键需求。本文提出一种完全算法可追溯且可训练的分割流程，联合使用超像素分解、混合亮度-邻近度超像素评分、形态学正则化、迭代GrabCut精炼及椭圆形状拟合。超参数优化被建模为目标函数，通过贝叶斯优化求解，消除人工调参。在Drishti-GS数据集上的定量评估显示，该方法取得0.9536的Dice系数，达到当前最优水平。通过在所有处理阶段保持明确的数学透明性，本框架为医疗审查与调试提供了确定性的可追溯替代方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。