Logo image
Model based image reconstruction using deep learned priors (MODL)
Conference proceeding

Model based image reconstruction using deep learned priors (MODL)

Hemant Kumar Aggarwal, Merry P Mani and Mathews Jacob
2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Vol.2018-, pp.671-674
04/2018
DOI: 10.1109/ISBI.2018.8363663
PMID: 33584973
url
https://www.ncbi.nlm.nih.gov/pmc/articles/7876898View
Open Access

Abstract

We introduce a model-based image reconstruction framework, where we use a deep convolution neural network (CNN) based regularization prior. We rely on a recursive algorithm, which alternates between a CNN based denoising step and enforcement of data consistency. Unrolling the recursive algorithm yields a deep network that is trained using backpropagation. The unique aspect of this method is the use of the same CNN weights at each iteration, which makes the resulting structure consistent with the model-based formulation. Also, this approach reduces the number of trainable parameters, which hence lower the amount of training data needed. The use of a forward model also reduces the size of the network and enables the exploitation additional prior information available from calibration data. The use of the framework for multichannel MRI reconstruction provides improved reconstructions, compared to other state-of-the-art methods.
Training Deep learning parallel imaging Sensitivity Magnetic resonance imaging Noise reduction convolutional neural network Computer architecture Data models Image reconstruction

Details

Metrics

Logo image