A completely automated pipeline for 3D reconstruction of human heart from 2D cine magnetic resonance slices.
A completely automated pipeline for 3D reconstruction of human heart from 2D cine magnetic resonance slices.
复制标题
DOI：
10.1098/rsta.2020.0257
复制
发表时间：
2021-12-13
期刊：
影响因子：
--
通讯作者：
Grau V
中科院分区：
文献类型：
--
作者：
Banerjee A;Camps J;Zacur E;Andrews CM;Rudy Y;Choudhury RP;Rodriguez B;Grau V
心脏磁共振（CMR）成像是诊断和表征心血管疾病的一种有价值的方式，因为它可以无创地识别心肌结构和功能的异常，而不需要电离辐射。然而，在临床实践中，它通常被采集为分离和独立的2D图像平面的集合，这限制了其在3D分析中的准确性。本文提出了一种完全自动化的管道，用于从电影磁共振（MR）切片生成患者特定的3D双心室心脏模型。我们的流水线自动选择相关的电影MR图像，使用基于深度学习的方法对其进行分割以提取心脏轮廓，并在3D空间中对齐轮廓，首先使用电影数据中的强度和轮廓信息，然后在统计形状模型的帮助下，纠正由于呼吸或受试者运动而导致的可能的不对齐。最后，稀疏的三维表示的轮廓被用来生成一个光滑的三维双心室网格。在20名健康受试者的CMR数据集中应用和评估计算管道。我们的结果显示，在20名受试者中，就与最终重建网格的距离而言，未对准伪影的平均减少值从1.82 ± 1.60 mm降至0.72 ± 0.73 mm。使用我们的计算管道获得的高分辨率3D双心室网格用于模拟电激活模式，与非侵入性心电图成像一致。本文提出的基于患者特定MR成像的3D双心室表示的自动方法有助于有效实现精确医学，增强临床数据的可解释性，通过基于患者特定图像的建模和模拟实现数字孪生视觉，以及增强现实应用。这篇文章是“心血管生理学中的高级计算：新的挑战和机遇”主题的一部分。
Cardiac magnetic resonance (CMR) imaging is a valuable modality in the diagnosis and characterization of cardiovascular diseases, since it can identify abnormalities in structure and function of the myocardium non-invasively and without the need for ionizing radiation. However, in clinical practice, it is commonly acquired as a collection of separated and independent 2D image planes, which limits its accuracy in 3D analysis. This paper presents a completely automated pipeline for generating patient-specific 3D biventricular heart models from cine magnetic resonance (MR) slices. Our pipeline automatically selects the relevant cine MR images, segments them using a deep learning-based method to extract the heart contours, and aligns the contours in 3D space correcting possible misalignments due to breathing or subject motion first using the intensity and contours information from the cine data and next with the help of a statistical shape model. Finally, the sparse 3D representation of the contours is used to generate a smooth 3D biventricular mesh. The computational pipeline is applied and evaluated in a CMR dataset of 20 healthy subjects. Our results show an average reduction of misalignment artefacts from 1.82 ± 1.60 mm to 0.72 ± 0.73 mm over 20 subjects, in terms of distance from the final reconstructed mesh. The high-resolution 3D biventricular meshes obtained with our computational pipeline are used for simulations of electrical activation patterns, showing agreement with non-invasive electrocardiographic imaging. The automatic methodologies presented here for patient-specific MR imaging-based 3D biventricular representations contribute to the efficient realization of precision medicine, enabling the enhanced interpretability of clinical data, the digital twin vision through patient-specific image-based modelling and simulation, and augmented reality applications. This article is part of the theme issue ‘Advanced computation in cardiovascular physiology: new challenges and opportunities’.
登录
查看更多内容
影响因子：
37.8
作者：
DURRER, D;VANDAM, RT;ARZBAECHER, RC
通讯作者：
ARZBAECHER, RC
影响因子：
1.6
作者：
Khatamian, Alireza;Arabnia, Hamid R.
通讯作者：
Arabnia, Hamid R.
影响因子：
4
作者：
Minchole, Ana;Zacur, Ernesto;Rodriguez, Blanca
通讯作者：
Rodriguez, Blanca
影响因子：
6.4
作者：
de Marvao, Antonio;Dawes, Timothy J. W.;O'Regan, Declan P.
通讯作者：
O'Regan, Declan P.
影响因子：
3.3
作者：
Kustner, Thomas;Bustin, Aurelien;Prieto, Claudia
通讯作者：
Prieto, Claudia