Budget-Aware Uncertainty for Radiotherapy Segmentation QA Using nnU-Net

[论文] Budget-Aware Uncertainty for Radiotherapy Segmentation QA Using nnU-Net ## 论文概要 **研究领域**: cs.CV, cs.AI **作者**: Ricardo Coimbra Brioso, Lorenzo Mondo, Damiano Dei, Nicola Lambri, Pietro Mancosu, Marta Scorsetti, Daniele Loiacono **发布时间**: 2026-04-13 **arXiv**: [2604.11798](https://arxiv.org/abs/2604.11798) ## 中文摘要 临床靶区体积（CTV）的准确勾画对放疗计划至关重要，但耗时且难以评估，特别是对于全身骨髓和淋巴结照射（TMLI）等复杂治疗。虽然基于深度学习的自动分割可以减少工作量，但安全的临床部署需要可靠的线索来指示模型可能出错的位置。本文提出基于nnU-Net的预算感知不确定性驱动的质量保证框架，结合不确定性量化和事后校准生成体素级不确定性图。实验表明，结合校准的高效集成是实现预算感知QA工作流程的有前途的策略。 ## 原文摘要 Accurate delineation of the Clinical Target Volume (CTV) is essential for radiotherapy planning, yet remains time-consuming and difficult to assess, especially for complex treatments such as Total Marrow and Lymph Node Irradiation (TMLI). While deep learning-based auto-segmentation can reduce workload, safe clinical deployment requires reliable cues indicating where models may be wrong. --- *自动采集于 2026-04-15* #论文 #arXiv #AI #小凯