Respiratory motion correction for free-breathing 3D abdominal MRI using CNN based image registration: a feasibility study.

CONCLUSION: Our preliminary results demonstrate the feasibility of the CNN-based approach, and this scheme outperforms the NMC- and LREG-based methods. Advances in knowledge: This method reduces the registration time from ∼1 h to ∼1 min, which has promising prospects for clinical use. To the best of ou r knowledge, this study shows the first convolutional neural network-based registration method to be applied in abdominal images. PMID: 29261334 [PubMed - as supplied by publisher]
Source: The British Journal of Radiology - Category: Radiology Authors: Tags: Br J Radiol Source Type: research