van der Pol Luuk H G, Blanck Oliver, Grehn Melanie, Blazek Tomáš, Knybel Lukáš, Balgobind Brian V, Verhoeff Joost J C, Miszczyk Marcin, Blamek Slawomir, Reichl Sabrina, Andratschke Nicolaus, Mehrhof Felix, Boda-Heggemann Judit, Tomasik Bartłomiej, Mandija Stefano, Fast Martin F
Department of Radiotherapy, University Medical Center Utrecht, Utrecht, the Netherlands.
Department of Radiation Oncology, University Medical Center Schleswig-Holstein, Kiel, Germany.
Radiother Oncol. 2025 Jan;202:110610. doi: 10.1016/j.radonc.2024.110610. Epub 2024 Nov 1.
BACKGROUND/PURPOSE: High doses to healthy cardiac substructures (CS) in stereotactic arrhythmia radioablation (STAR) raise concerns regarding potential treatment-induced cardio-toxicity. However, CS contours are not routinely created, hindering the understanding of the CS dose-effect relationships. To address this issue, the alignment of CS contouring was initiated within the STOPSTORM consortium. In this study, we developed and evaluated auto-contouring models trained to delineate CS and major vessels in ventricular tachycardia (VT) patients.
Eight centres provided standard treatment planning computed tomography (CT) and/or contrast-enhanced CT datasets of 55 VT patients, each including 16 CS. Auto-contouring models were trained to contour either large structures or small structures. Dice Similarity Coefficient (DSC), 95 % Hausdorff distance (HD95) and volume ratio (VR) were used to evaluate model performance versus inter-observer variation (IOV) on seven VT patient test cases. Significant differences were tested using the Mann-Whitney U test.
The performance on the four chambers and the major vessels (median DSC: 0.88; HD95: 5.8-19.4 mm; VR: 1.09) was similar to the IOV (median DSC: 0.89; HD95: 4.8-14.0 mm; VR: 1.20). For the valves, model performance (median DSC: 0.37; HD95: 11.6 mm; VR: 1.63) was similar to the IOV (median DSC: 0.41; HD95: 12.4 mm; VR: 3.42), but slightly worse for the coronary arteries (median DSC: 0.33 vs 0.42; HD95: 24.4 mm vs 16.9 mm; VR: 1.93 vs 3.30). The IOV for these small structures remains large despite using contouring guidelines.
CS auto-contouring models trained on VT patient data perform similarly to IOV. This allows for time-efficient evaluation of CS as possible organs-at-risk.
背景/目的：立体定向心律失常射频消融术（STAR）中对健康心脏亚结构（CS）的高剂量照射引发了对潜在治疗诱导心脏毒性的担忧。然而，CS轮廓并非常规生成，这阻碍了对CS剂量效应关系的理解。为解决这一问题，在STOPSTORM联盟内启动了CS轮廓对齐工作。在本研究中，我们开发并评估了经过训练以描绘室性心动过速（VT）患者CS和主要血管的自动轮廓模型。
八个中心提供了55例VT患者的标准治疗计划计算机断层扫描（CT）和/或增强CT数据集，每个数据集包含16个CS。自动轮廓模型经过训练以勾勒大结构或小结构。使用骰子相似系数（DSC）、95%豪斯多夫距离（HD95）和体积比（VR）来评估模型在七个VT患者测试病例上相对于观察者间差异（IOV）的性能。使用曼-惠特尼U检验来检验显著差异。
四个腔室和主要血管的模型性能（中位数DSC：0.88；HD95：5.8 - 19.4毫米；VR：1.09）与IOV相似（中位数DSC：0.89；HD95：4.8 - 14.0毫米；VR：1.20）。对于瓣膜，模型性能（中位数DSC：0.37；HD95：11.6毫米；VR：1.63）与IOV相似（中位数DSC：0.41；HD95：12.4毫米；VR：3.42），但对于冠状动脉稍差（中位数DSC：0.33对0.42；HD95：24.4毫米对16.9毫米；VR：1.93对3.30）。尽管使用了轮廓指南，这些小结构的IOV仍然很大。
基于VT患者数据训练的CS自动轮廓模型的性能与IOV相似。这使得能够高效地评估CS作为可能的危险器官。
