用于带有心脏植入物的室性心动过速放射消融和放射治疗患者的心脏分割

中文摘要 AI 辅助

深度学习（DL）分割技术能够实现心脏亚结构（CS）的勾画，用于先进的心脏保护性放射治疗（RT）。接受RT的患者可能带有植入式设备（如心律转复除颤器（ICDs）），并产生金属伪影。立体定向体部放射治疗（SBRT）用于治疗室性心动过速（VT），该人群常携带ICDs。我们将一个DL模型应用于带有ICDs或接受VT-SBRT的RT患者，实现分割及CS级别的剂量分析。评估了19名带有ICDs并接受VT-SBRT患者的CT模拟（CT-SIM）数据。使用一个高度精选的CT-SIM队列重新训练了一个经过验证的分割模型，并补充了ICD图像用于训练和验证，同时设置了一个独立的ICD测试集（n=10），以预测20个CS。额外的CT-SIM数据集包括带有ICDs（n=9）和不带ICDs（n=10）的癌症RT患者，以评估泛化能力。将重新训练的ICD补充模型与一个非ICD模型进行了比较，使用Dice相似系数（DSC）、95% Hausdorff距离（HD95）和Wilcoxon符号秩检验（p<0.05）。对VT-SBRT的CS进行了剂量学评估。对于VT-SBRT，ICD补充模型实现了平均DSC/HD95分别为0.71(0.19)/10.7(22.5)mm，显著优于（p<0.05）非ICD模型。在带有ICDs的CT-SIM上，平均DSC/HD95分别为0.70(0.22)/7.9(5.1)mm，显著优于（p<0.05）非ICD模型。在不带ICDs的CT-SIM上，平均DSC为0.74(0.17)（非ICD模型DSC为0.75(0.16)，p<0.05），平均HD95为5.5(3.1)mm（非ICD模型HD95为5.3(2.8)mm）。对于VT-SBRT，CS剂量取决于靶区位置，心室、三尖瓣、房室结和左冠状动脉相对于其他CS接受了更高的相对剂量。ICD补充训练在存在金属伪影的情况下改善了CS分割，且未显著降低非ICD性能，支持在ICD人群中进行分割和CS级别剂量测定。

英文摘要

Deep-learning (DL) segmentation enables cardiac substructure (CS) delineation for advanced cardiac-sparing radiation therapy (RT). Patients presenting for RT may have implantable devices (cardioverter-defibrillators (ICDs)) and metal artifacts. Stereotactic body RT (SBRT) is used to treat ventricular tachycardia (VT), a population frequently with ICDs. We apply a DL model for RT patients with ICDs or undergoing VT-SBRT, enabling segmentation and CS-level dose analysis. CT simulation (CT-SIM) of 19 patients with ICDs and received VT-SBRT were evaluated. A validated segmentation model was retrained using a highly-curated CT-SIM cohort, supplemented with ICD images for training and validation, with a hold-out ICD test set (n=10), to predict 20 CS. Additional CT-SIM datasets included cancer-RT patients with (n=9) and without (n=10) ICDs to evaluate generalizability. The retrained ICD-supplemented model was compared against a non-ICD model using Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and Wilcoxon signed-rank test (p<0.05). Dosimetric evaluation was performed for VT-SBRT CS. For VT-SBRT, the ICD-supplemented model achieved average DSC/HD95 of 0.71(0.19)/10.7(22.5)mm respectively, outperforming (p<0.05) the non-ICD model. On CT-SIM with ICDs, average DSC/HD95 were 0.70(0.22)/7.9(5.1)mm respectively, outperforming (p<0.05) the non-ICD model. On CT-SIM without ICDs, the average DSC was 0.74(0.17) (Non-ICD, DSC, 0.75(0.16), p<0.05) and average HD95 was 5.5(3.1)mm (Non-ICD, HD95, 5.3(2.8mm)). For VT-SBRT, CS dose depended on target location, with higher relative dose delivered to the ventricles, tricuspid valve, atrioventricular node, and left coronary arteries than other CS. ICD-supplemented training improved CS segmentation despite metal artifacts without meaningfully degrading non-ICD performance, supporting segmentation and CS-level dosimetry in ICD populations.

发表机构

• University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
• Wayne State University（韦恩州立大学）

机构由 AI 辅助整理，请以论文原文为准。