A deep learning approach for fully automated cardiac shape modeling in tetralogy of Fallot.
A deep learning approach for fully automated cardiac shape modeling in tetralogy of Fallot.
复制标题
DOI：
10.1186/s12968-023-00924-1
复制
发表时间：
2023-02-27
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
心脏形状建模是一种有用的计算工具，它为心脏病功能障碍的潜在机制提供了定量的见解。然而，制作心脏形状模型所需的手动输入和时间限制了其临床实用性。在这里，我们提出了一个端到端的管道，使用深度学习自动视图分类，切片选择，相位选择，解剖标志定位和心肌图像分割，自动生成三维，双心室形状模型。通过这种方法，我们的目标是使心脏形状建模成为一种更强大，更广泛适用的工具，其处理时间与临床工作流程一致。来自两个内部站点的123名法洛四联症（rTOF）修复患者的心血管磁共振（CMR）图像用于训练和验证自动化管道中的每个步骤。使用来自内部站点的12名rTOF患者和来自外部站点的18名rTOF患者的CMR图像对完整的自动化管道进行测试。使用欧几里德投影距离、全局心室测量和基于图谱的形状模式评分，对测试集中手动和自动生成的形状模型进行比较。测试集中手动和自动生成的形状模型之间的平均绝对误差（MAE）与舒张末期模型（MAE = 1.9 ± 0.5 mm）和收缩末期模型（MAE = 2.1 ± 0.7 mm）的原始CMR图像的体素分辨率相似。从自动模型计算的全球心室测量结果与手动模型计算的结果一致。对于参考统计形状图谱的前20个模式，手动和自动生成的模型之间的形状模式Z分数的平均绝对差为0.5标准差。使用深度学习，可以可靠地创建精确的三维双心室形状模型。这种完全自动化的端到端方法大大减少了创建形状模型所需的手动输入，从而能够快速分析大规模数据集，并有可能在护理点临床环境中部署基于统计图谱的分析。培训数据和网络可从cardiacatlas.org获得。
Cardiac shape modeling is a useful computational tool that has provided quantitative insights into the mechanisms underlying dysfunction in heart disease. The manual input and time required to make cardiac shape models, however, limits their clinical utility. Here we present an end-to-end pipeline that uses deep learning for automated view classification, slice selection, phase selection, anatomical landmark localization, and myocardial image segmentation for the automated generation of three-dimensional, biventricular shape models. With this approach, we aim to make cardiac shape modeling a more robust and broadly applicable tool that has processing times consistent with clinical workflows. Cardiovascular magnetic resonance (CMR) images from a cohort of 123 patients with repaired tetralogy of Fallot (rTOF) from two internal sites were used to train and validate each step in the automated pipeline. The complete automated pipeline was tested using CMR images from a cohort of 12 rTOF patients from an internal site and 18 rTOF patients from an external site. Manually and automatically generated shape models from the test set were compared using Euclidean projection distances, global ventricular measurements, and atlas-based shape mode scores. The mean absolute error (MAE) between manually and automatically generated shape models in the test set was similar to the voxel resolution of the original CMR images for end-diastolic models (MAE = 1.9 ± 0.5 mm) and end-systolic models (MAE = 2.1 ± 0.7 mm). Global ventricular measurements computed from automated models were in good agreement with those computed from manual models. The average mean absolute difference in shape mode Z-score between manually and automatically generated models was 0.5 standard deviations for the first 20 modes of a reference statistical shape atlas. Using deep learning, accurate three-dimensional, biventricular shape models can be reliably created. This fully automated end-to-end approach dramatically reduces the manual input required to create shape models, thereby enabling the rapid analysis of large-scale datasets and the potential to deploy statistical atlas-based analyses in point-of-care clinical settings. Training data and networks are available from cardiacatlas.org.
登录
查看更多内容
DOI：
10.1007/s10554-017-1236-6
发表时间：
2018-03
期刊：
The international journal of cardiovascular imaging
影响因子：
--
作者：
Gilbert K;Pontre B;Occleshaw CJ;Cowan BR;Suinesiaputra A;Young AA
通讯作者：
Young AA
DOI：
10.1098/rsta.2020.0257
发表时间：
2021-12-13
期刊：
Philosophical transactions. Series A, Mathematical, physical, and engineering sciences
影响因子：
--
作者：
Banerjee A;Camps J;Zacur E;Andrews CM;Rudy Y;Choudhury RP;Rodriguez B;Grau V
通讯作者：
Grau V
影响因子：
6.4
作者：
Mauger, Charlene;Gilbert, Kathleen;Young, Alistair A.
通讯作者：
Young, Alistair A.
影响因子：
3.6
作者：
Elsayed A;Mauger CA;Ferdian E;Gilbert K;Scadeng M;Occleshaw CJ;Lowe BS;McCulloch AD;Omens JH;Govil S;Pushparajah K;Young AA
通讯作者：
Young AA
影响因子：
3.4
作者：
Gilbert K;Forsch N;Hegde S;Mauger C;Omens JH;Perry JC;Pontré B;Suinesiaputra A;Young AA;McCulloch AD
通讯作者：
McCulloch AD