Technical note: Minimizing CIED artifacts on a 0.35 T MRI-Linac using deep learning.
Technical note: Minimizing CIED artifacts on a 0.35 T MRI-Linac using deep learning.
复制标题
技术说明：使用深度学习最大限度地减少 0.35 T MRI-Linac 上的 CIED 伪影。
DOI：
10.1002/acm2.14304
复制
发表时间：
2024
影响因子：
2.1
通讯作者：
Gach,HMichael
中科院分区：
文献类型：
--
作者：
Curcuru,AustenN;Yang,Deshan;An,Hongyu;Cuculich,PhillipS;Robinson,CliffordG;Gach,HMichael
背景植入式心脏复律除颤器(ICD)伪影是磁共振成像(MRI)引导放射治疗(MRGRT)的一个挑战。目的本研究测试了一种无监督的生成性对抗网络，以减轻平衡稳态自由进动(BSSFP)电影MRI中ICD伪影，改善MRgRT的图像质量和跟踪性能。方法14名健康志愿者(A组)在0.35T磁共振直线加速器上进行扫描，模拟植入的ICD。12名志愿者的bSSFP MRI数据被用来训练CycleGAN模型，以减少ICD伪影。来自其余两名志愿者的数据用于测试。此外，使用遗漏一项计划对数据集进行了三次重组。跟踪指标[骰子相似系数(DSC)、目标配准误差(TRE)和95%Hausdorff距离(95%HD)]用于评估整个心脏轮廓。评价图像质量指标[归一化均方根误差(NRMSE)、峰值信噪比(PSNR)和多尺度结构相似性(MS-SSIM)评分]。这项技术还在另外三个ICD数据集(B组)上进行了定性测试，其中包括一名植入ICD的患者。结果对于CycleGAN重建的全心轮廓：1)平均DSC从0.910上升到0.935；2)平均TRE从4.488下降到2.877 mm；3)平均95%HD从10.236下降到7.700 mm。CycleGAN重建的全身切片：1)平均均方根误差从0.644降至0.420；2)平均MS-SSIM从0.779升至0.819；3)平均峰值信噪比从18.744升至22.368。定性评估的三个B组数据集显示心脏ICD伪影的减少。结论CycleGAN生成的重建在用于减少ICD伪影时显著改善了跟踪和图像质量指标。
BackgroundArtifacts from implantable cardioverter defibrillators (ICDs) are a challenge to magnetic resonance imaging (MRI)‐guided radiotherapy (MRgRT).PurposeThis study tested an unsupervised generative adversarial network to mitigate ICD artifacts in balanced steady‐state free precession (bSSFP) cine MRIs and improve image quality and tracking performance for MRgRT.MethodsFourteen healthy volunteers (Group A) were scanned on a 0.35 T MRI‐Linac with and without an MR conditional ICD taped to their left pectoral to simulate an implanted ICD. bSSFP MRI data from 12 of the volunteers were used to train a CycleGAN model to reduce ICD artifacts. The data from the remaining two volunteers were used for testing. In addition, the dataset was reorganized three times using a Leave‐One‐Out scheme. Tracking metrics [Dice similarity coefficient (DSC), target registration error (TRE), and 95 percentile Hausdorff distance (95% HD)] were evaluated for whole‐heart contours. Image quality metrics [normalized root mean square error (nRMSE), peak signal‐to‐noise ratio (PSNR), and multiscale structural similarity (MS‐SSIM) scores] were evaluated. The technique was also tested qualitatively on three additional ICD datasets (Group B) including a patient with an implanted ICD.ResultsFor the whole‐heart contour with CycleGAN reconstruction: 1) Mean DSC rose from 0.910 to 0.935; 2) Mean TRE dropped from 4.488 to 2.877 mm; and 3) Mean 95% HD dropped from 10.236 to 7.700 mm. For the whole‐body slice with CycleGAN reconstruction: 1) Mean nRMSE dropped from 0.644 to 0.420; 2) Mean MS‐SSIM rose from 0.779 to 0.819; and 3) Mean PSNR rose from 18.744 to 22.368. The three Group B datasets evaluated qualitatively displayed a reduction in ICD artifacts in the heart.ConclusionCycleGAN‐generated reconstructions significantly improved both tracking and image quality metrics when used to mitigate artifacts from ICDs.