解剖变化感知的双向选择性状态空间记忆用于临床部署的胸部放疗自动勾画

中文摘要 AI 辅助

我们开发了DAMM-Net++，一种用于胸部危及器官（OAR）和靶区体积分割的2.5D架构，解决了放疗自动勾画中三个持续存在的挑战：层间表面不连贯性、小尺寸低对比度靶区的系统性失败，以及缺乏逐病例可靠性信号。核心组件是一个解剖变化感知的双向选择性状态空间记忆，它建模贯穿平面的解剖变化，并沿轴向切片序列选择性地传播上下文。一个边界感知解码器锐化近表面预测，一个不确定性头提供校准的逐体素置信度，用于临床分诊。我们评估了来自四个中心的2,146名患者、一个包含112名患者的独立外部队列，以及一项涉及17名放射肿瘤学家对150个病例的多中心阅片研究。该模型实现了平均Dice为0.955，HD95为3.78毫米，在低对比度危及器官（OAR）和靶区体积上取得了最大增益，这些区域中贯穿平面上下文最为关键。不确定性头校准良好，并支持病例级分诊。在阅片研究中，AI辅助将不同经验水平的勾画时间减少了75-80%，并将初级阅片者的IoU从0.861提高到0.925，与未编辑的模型相当。外部验证显示内部到外部的性能下降幅度较小（小于5%），且校准的不确定性无需重新校准即可迁移。从DICOM导入到兼容TPS的RTSTRUCT导出的完整部署流程已集成到合作医院的临床工作流程中，用于辅助勾画。这些结果表明，解剖驱动的层间记忆，结合不确定性引导的审查，为胸部自动勾画提供了一条临床可行的路径。

英文摘要

We developed DAMM-Net++, a 2.5D architecture for thoracic OAR and target volume segmentation that addresses three persistent challenges in radiotherapy auto-contouring: inter-slice surface incoherence, systematic failure on small low-contrast targets, and the absence of per-case reliability signals. The central component is an anatomy-change-aware bidirectional selective state-space memory that models through-plane anatomical change and selectively propagates context along the axial slice sequence. A boundary-aware decoder sharpens near-surface predictions, and an uncertainty head provides calibrated per-voxel confidence for clinical triage. We evaluated 2,146 patients across four centers, an independent external cohort of 112 patients, and a multicenter reader study involving 17 radiation oncologists on 305 cases. The model achieves a mean Dice of 0.955 and HD95 of 3.78 mm, with the largest gains on low-contrast organs-at-risk (OARs) and target volumes where through-plane context is most critical. The uncertainty head is well-calibrated and supports case-level triage. In the reader study, AI assistance reduced contouring time by 75-80% across experience levels and raised junior-reader IoU from 0.861 to 0.925, matching the unedited model. External validation showed a modest internal-to-external drop (< 5%) with calibrated uncertainty transferring without recalibration. The complete deployment pipeline from DICOM ingestion to TPS-compatible RTSTRUCT export has been integrated into the clinical workflow at a partner hospital, where it is used to assist with contouring. These results suggest that anatomically motivated inter-slice memory, paired with uncertainty-guided review, offers a clinically viable path for thoracic auto-contouring.

发表机构

• North South University（北南大学）
• Friedrich-Alexander University（弗里德里希-亚历山大大学）
• Square Hospitals Limited（斯奎尔医院有限公司）

机构由 AI 辅助整理，请以论文原文为准。