Automated cardiac volume assessment and cardiac long- and short-axis imaging plane prediction from electrocardiogram-gated computed tomography volumes enabled by deep learning.
Automated cardiac volume assessment and cardiac long- and short-axis imaging plane prediction from electrocardiogram-gated computed tomography volumes enabled by deep learning.
复制标题
通过深度学习实现从心电门控计算机断层扫描容积进行自动心脏容积评估以及心脏长轴和短轴成像平面预测。
DOI：
10.1093/ehjdh/ztab033
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Contijoch F
中科院分区：
文献类型：
--
作者：
Chen Z;Rigolli M;Vigneault DM;Kligerman S;Hahn L;Narezkina A;Craine A;Lowe K;Contijoch F
旨在开发一种通过深度学习（DL）对心脏计算机断层扫描（CT）进行血池分割和成像平面重新切片的自动化方法，用于冠状动脉疾病（CAD）室壁运动评估和可再现纵向成像的临床应用。100名接受临床指示心脏CT扫描的患者，手动分割左心室（LV）和左心房（LA）腔室，用于培训。对于每例患者，由成像专家手动定义长轴（LAX）和短轴平面。训练DL模型以预测血池分割和成像平面。深度学习血池分割显示与手动LV [中位Dice：0.91，Hausdorff距离（HD）：6.18 mm]和LA（Dice：0.93，HD：7.35 mm）分割密切一致，与手动射血分数（Pearson r：0.95 LV，0.92 LA）具有强相关性。预测平面的中位位置（6.96 mm）和角度方向（7.96 mm）误差较低，与阅片员间差异相当（P > 0.71）。DL规定的LAX平面正确显示美国心脏协会节段的84-97%，与手动切片相当（P > 0.05）。在144例患者的测试队列中，我们评估了DL方法提供诊断成像平面的能力。两名盲态专家的视觉评分确定≥94%的DL预测平面具有诊断充分性。此外，DL使CAD引起的LV壁运动异常可视化，并在重复成像时提供可再现平面。容积、DL方法提供多个腔室分割，并且可以沿着标准化心脏成像平面重新切片成像容积沿着，用于可再现的室壁运动异常和功能评估。
To develop an automated method for bloodpool segmentation and imaging plane re-slicing of cardiac computed tomography (CT) via deep learning (DL) for clinical use in coronary artery disease (CAD) wall motion assessment and reproducible longitudinal imaging. One hundred patients who underwent clinically indicated cardiac CT scans with manually segmented left ventricle (LV) and left atrial (LA) chambers were used for training. For each patient, long-axis (LAX) and short-axis planes were manually defined by an imaging expert. A DL model was trained to predict bloodpool segmentations and imaging planes. Deep learning bloodpool segmentations showed close agreement with manual LV [median Dice: 0.91, Hausdorff distance (HD): 6.18 mm] and LA (Dice: 0.93, HD: 7.35 mm) segmentations and a strong correlation with manual ejection fraction (Pearson r: 0.95 LV, 0.92 LA). Predicted planes had low median location (6.96 mm) and angular orientation (7.96) errors which were comparable to inter-reader differences (P > 0.71). 84–97% of DL-prescribed LAX planes correctly intersected American Heart Association segments, which was comparable (P > 0.05) to manual slicing. In a test cohort of 144 patients, we evaluated the ability of the DL approach to provide diagnostic imaging planes. Visual scoring by two blinded experts determined ≥94% of DL-predicted planes to be diagnostically adequate. Further, DL-enabled visualization of LV wall motion abnormalities due to CAD and provided reproducible planes upon repeat imaging. A volumetric, DL approach provides multiple chamber segmentations and can re-slice the imaging volume along standardized cardiac imaging planes for reproducible wall motion abnormality and functional assessment.