Non-Rigid Respiratory Motion Estimation of Whole-Heart Coronary MR Images Using Unsupervised Deep Learning
| Autor: | Niccolo Fuin, Thomas Kuestner, Claudia Prieto, René M. Botnar, Aurelien Bustin, Haikun Qi, Gastao Cruz, Jiazhen Pan |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Image quality
Computer science Image registration Image processing Iterative reconstruction Coronary Angiography 030218 nuclear medicine & medical imaging Motion 03 medical and health sciences Deep Learning Imaging Three-Dimensional 0302 clinical medicine Motion estimation Image Processing Computer-Assisted Humans Computer vision Electrical and Electronic Engineering Image warping Radiological and Ultrasound Technology business.industry Heart Coronary Vessels Subpixel rendering Computer Science Applications Motion field Artificial intelligence business Magnetic Resonance Angiography Software |
| Zdroj: | IEEE Transactions on Medical Imaging. 40:444-454 |
| ISSN: | 1558-254X 0278-0062 |
| DOI: | 10.1109/tmi.2020.3029205 |
| Popis: | Non-rigid motion-corrected reconstruction has been proposed to account for the complex motion of the heart in free-breathing 3D coronary magnetic resonance angiography (CMRA). This reconstruction framework requires efficient and accurate estimation of non-rigid motion fields from undersampled images at different respiratory positions (or bins). However, state-of-the-art registration methods can be time-consuming. This article presents a novel unsupervised deep learning-based strategy for fast estimation of inter-bin 3D non-rigid respiratory motion fields for motion-corrected free-breathing CMRA. The proposed 3D respiratory motion estimation network (RespME-net) is trained as a deep encoder-decoder network, taking pairs of 3D image patches extracted from CMRA volumes as input and outputting the motion field between image patches. Using image warping by the estimated motion field, a loss function that imposes image similarity and motion smoothness is adopted to enable training without ground truth motion field. RespME-net is trained patch-wise to circumvent the challenges of training a 3D network volume-wise which requires large amounts of GPU memory and 3D datasets. We perform 5-fold cross-validation with 45 CMRA datasets and demonstrate that RespME-net can predict 3D non-rigid motion fields with subpixel accuracy (0.44 ± 0.38 mm) within ~10 seconds, being ~20 times faster than a GPU-implemented state-of-the-art non-rigid registration method. Moreover, we perform non-rigid motion-compensated CMRA reconstruction for 9 additional patients. The proposed RespME-net has achieved similar motion-corrected CMRA image quality to the conventional registration method regarding coronary artery length and sharpness. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|