发表机构
University of Exeter; King Abdulaziz University; University College London（埃克塞特大学; 阿卜杜勒阿齐兹国王大学; 伦敦大学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对胶质瘤分割，提出混合结构-偶然不确定性人在回路框架，利用TTA不确定性与拓扑过滤定位高风险异常，在362例临床压力测试中提升WT Dice至0.914、降低HD95至4.76毫米，以11.3%交互工作量实现手术级精度。
AI 中文摘要
尽管最先进的医学图像分割自动化模型在平均性能上表现优异，但它们经常出现局部性、灾难性的失败，这阻碍了其在临床中的安全部署，尤其是在神经肿瘤学领域。交互式分割框架通过引入人工监督来缓解这一问题，但传统上要求临床医生手动搜索错误，从而带来过高的认知和时间负担。在本项目中，我们提出了一种高效的混合结构-偶然不确定性人在回路框架，用于胶质瘤分割，弥合了自动化基线性能与手术级精度之间的差距，在精选基准上实现了亚2.0毫米的HD95，同时为真实世界临床数据中的结构性失败提供了安全网路由。通过提取体素级测试时增强（TTA）不确定性并应用分层拓扑过滤，我们的方法主动隔离高风险的结构异常。我们在一个具有挑战性的分布外临床压力测试队列（N=362）上全面评估了我们的方法。在模拟人类神谕（Human Oracle）下，该框架将全肿瘤（WT）Dice分数从0.891提升至0.914，并将第95百分位豪斯多夫距离（HD95）从5.82毫米降至4.76毫米。对手术安全至关重要的一点是，该系统挽救了肿瘤核心区域的严重边界失败，将平均HD95从17.96毫米降至14.83毫米（绝对TC Dice提升至0.356）。这些空间挽救是在仅要求目标体积中位交互工作量11.3%的情况下实现的。尽管我们承认这是一个缺乏真实世界认知摩擦的模拟上限，但该框架仍然展示了一条高度帕累托高效的安全部署临床AI的路径。
英文摘要
While state-of-the-art automated models for medical image segmentation achieve high mean performance, they frequently suffer from localized, catastrophic failures that preclude safe clinical deployment, particularly in neuro-oncology. Interactive segmentation frameworks mitigate this by incorporating human oversight, but traditionally impose prohibitive cognitive and temporal workloads by requiring clinicians to manually search for errors. In this project, we present an efficient, Hybrid Structural-Aleatoric Human-in-the-Loop framework for glioma segmentation that bridges the gap between automated baseline performance and surgical-grade precision, achieving sub-2.0 mm HD95 on curated benchmarks while providing safety-net routing for structural failures across real-world clinical data. By extracting voxel-wise Test-Time Augmentation (TTA) uncertainty and applying hierarchical topological filtering, our method proactively isolates high-risk structural anomalies. We comprehensively evaluated our approach on a challenging out-of-distribution clinical stress-test cohort (N = 362). Operating under a simulated Human Oracle, the framework improved the Whole Tumor (WT) Dice score from 0.891 to 0.914 and reduced the 95th percentile Hausdorff Distance (HD95) from 5.82 mm to 4.76 mm. Critically for surgical safety, the system rescued severe boundary failures in the Tumor Core, reducing mean HD95 from 17.96 mm to 14.83 mm (improving absolute TC Dice to 0.356). These spatial rescues were achieved while demanding a median interactive workload of just 11.3% of the target volume. Acknowledging this as a simulated upper bound lacking real-world cognitive friction, the framework nevertheless demonstrates a highly Pareto-efficient pathway for safely deploying clinical AI.
Comments12 pages
