Automating in vivo cardiac diffusion tensor postprocessing with deep learning-based segmentation

Abstract

Purpose: In this work we develop and validate a fully automated postprocessing framework for in vivo diffusion tensor cardiac magnetic resonance (DT-CMR) data powered by deep learning.

Methods: A U-Net based convolutional neural network was developed and trained to segment the heart in short-axis DT-CMR images. This was used as the basis to automate and enhance several stages of the DT-CMR tensor calculation workflow, including image registration and removal of data corrupted with artifacts, and to segment the left ventricle. Previously collected and analyzed scans (348 healthy scans and 144 cardiomyopathy patient scans) were used to train and validate the U-Net. All data were acquired at 3 T with a STEAM-EPI sequence. The DT-CMR postprocessing and U-Net training/testing were performed with MATLAB and Python TensorFlow, respectively.

Results: The U-Net achieved a median Dice coefficient of 0.93 [0.92, 0.94] for the segmentation of the left-ventricular myocardial region. The image registration of diffusion images improved with the U-Net segmentation (P < .0001), and the identification of corrupted images achieved an F1 score of 0.70 when compared with an experienced user. Finally, the resulting tensor measures showed good agreement between an experienced user and the fully automated method.

Conclusion: The trained U-Net successfully automated the DT-CMR postprocessing, supporting real-time results and reducing human workload. The automatic segmentation of the heart improved image registration, resulting in improvements of the calculated DT parameters.

Keywords: cardiac; deep learning; diffusion tensor imaging; image processing; machine learning.