Upendra Roshan Reddy, Wentz Brian Jamison, Shontz Suzanne M, Linte Cristian A
Chester F Carlson Center for Imaging Science, Rochester Institute of Technology, Rochester, NY, USA.
Bioengineering Graduate Program, University of Kansas, Lawrence, KS, USA.
Comput Cardiol (2010). 2020 Sep;47. doi: 10.22489/CinC.2020.204. Epub 2021 Feb 10.
In this work, we describe an unsupervised deep learning framework featuring a Laplacian-based operator as smoothing loss for deformable registration of 3D cine cardiac magnetic resonance (CMR) images. Before registration, the input 3D images are corrected for slice misalignment by segmenting the left ventricle (LV) blood-pool, LV myocardium and right ventricle (RV) blood-pool using a U-Net model and aligning the 2D slices along the center of the LV blood-pool. We conducted experiments using the Automated Cardiac Diagnosis Challenge (ACDC) dataset. We used the registration deformation field to warp the manually segmented LV blood-pool, LV myocardium and RV blood-pool labels from end-diastole (ED) frame to the other frames in the cardiac cycle. We achieved a mean Dice score of 94.84%, 85.22% and 84.36%, and Hausdorff distance (HD) of 2.74 mm, 5.88 mm and 9.04 mm, for the LV blood-pool, LV myocardium and RV blood-pool, respectively. We also introduce a pipeline to estimate patient tractography using the proposed CNN-based cardiac motion estimation.
在这项工作中，我们描述了一种无监督深度学习框架，该框架具有基于拉普拉斯算子的算子，作为用于三维电影心脏磁共振（CMR）图像可变形配准的平滑损失。在配准之前，通过使用U-Net模型分割左心室（LV）血池、LV心肌和右心室（RV）血池，并沿LV血池中心对齐二维切片，对输入的三维图像进行切片错位校正。我们使用自动心脏诊断挑战赛（ACDC）数据集进行了实验。我们使用配准变形场将手动分割的LV血池、LV心肌和RV血池标签从舒张末期（ED）帧扭曲到心动周期中的其他帧。对于LV血池、LV心肌和RV血池，我们分别获得了94.84%、85.22%和84.36%的平均骰子系数，以及2.74毫米、5.88毫米和9.04毫米的豪斯多夫距离（HD）。我们还引入了一个管道，以使用所提出的基于卷积神经网络的心脏运动估计来估计患者纤维束成像。
