Abstract
BackgroundCS-MRI (compressed sensing for magnetic resonance imaging) exploits image sparsity properties to reconstruct MRI from very few Fourier k-space measurements. Due to imperfect modelings in the inverse imaging, state-of-the-art CS-MRI methods tend to leave structural reconstruction errors. Compensating such errors in the reconstruction could help further improve the reconstruction quality.ResultsIn this work, we propose a DECN (deep error correction network) for CS-MRI. The DECN model consists of three parts, which we refer to as modules: a guide, or template, module, an error correction module, and a data fidelity module. Existing CS-MRI algorithms can serve as the template module for guiding the reconstruction. Using this template as a guide, the error correction module learns a CNN (convolutional neural network) to map the k-space data in a way that adjusts for the reconstruction error of the template image. We propose a deep error correction network. Our experimental results show the proposed DECN CS-MRI reconstruction framework can considerably improve upon existing inversion algorithms by supplementing with an error-correcting CNN.ConclusionsIn the proposed a deep error correction framework, any off-the-shelf CS-MRI algorithm can be used as template generation. Then a deep neural network is used to compensate reconstruction errors. The promising experimental results validate the effectiveness and utility of the proposed framework.
Highlights
Compressed Sensing (CS)-MRI exploits image sparsity properties to reconstruct MRI from very few Fourier k-space measurements
We propose a deep learning framework called deep error correction network (DECN) in which an arbitrary CS-MRI inversion algorithm is combined with a deep learning error correction network
We observe that DECN improved all off-the-shelf CS-MRI inversion methods on all the under-sampling patterns
Summary
CS-MRI (compressed sensing for magnetic resonance imaging) exploits image sparsity properties to reconstruct MRI from very few Fourier k-space measurements. Due to imperfect modelings in the inverse imaging, state-of-the-art CS-MRI methods tend to leave structural reconstruction errors. Compensating such errors in the reconstruction could help further improve the reconstruction quality. MRI (Magnetic resonance imaging) is an important medi- agreement between the Fourier coefficients of the reconcal imaging technique with high resolution in soft tissues, structed image and the measured data, while the second low radiations, but the slow imaging speed is a major term regularizes the reconstruction to encourage certain drawback of MRI.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have