MoDL-MUSSELS: Model-Based Deep Learning for Multishot Sensitivity-Encoded Diffusion MRI
Autor: | Mathews Jacob, Merry Mani, Hemant Kumar Aggarwal |
---|---|
Rok vydání: | 2020 |
Předmět: |
FOS: Computer and information sciences
Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Image processing Iterative reconstruction Convolutional neural network Article 030218 nuclear medicine & medical imaging Convolution Reduction (complexity) 03 medical and health sciences Deep Learning 0302 clinical medicine Distortion Connectome Image Processing Computer-Assisted Humans Electrical and Electronic Engineering Radiological and Ultrasound Technology business.industry Deep learning Brain Filter bank Computer Science Applications Diffusion Magnetic Resonance Imaging Computer Science::Computer Vision and Pattern Recognition Artificial intelligence business Algorithm Algorithms Software Signal subspace |
Zdroj: | IEEE Trans Med Imaging |
ISSN: | 1558-254X 0278-0062 |
Popis: | We introduce a model-based deep learning architecture termed MoDL-MUSSELS for the correction of phase errors in multishot diffusion-weighted echo-planar MR images. The proposed algorithm is a generalization of the existing MUSSELS algorithm with similar performance but significantly reduced computational complexity. In this work, we show that an iterative re-weighted least-squares implementation of MUSSELS alternates between a multichannel filter bank and the enforcement of data consistency. The multichannel filter bank projects the data to the signal subspace, thus exploiting the annihilation relations between shots. Due to the high computational complexity of the self-learned filter bank, we propose replacing it with a convolutional neural network (CNN) whose parameters are learned from exemplary data. The proposed CNN is a hybrid model involving a multichannel CNN in the k-space and another CNN in the image space. The k-space CNN exploits the annihilation relations between the shot images, while the image domain network is used to project the data to an image manifold. The experiments show that the proposed scheme can yield reconstructions that are comparable to state-of-the-art methods while offering several orders of magnitude reduction in run-time. |
Databáze: | OpenAIRE |
Externí odkaz: |