Benchmarking MRI Reconstruction Neural Networks on Large Public Datasets

• Published in: Applied sciences Vol. 10; no. 5; p. 1816
• Main Authors: Ramzi, Zaccharie, Ciuciu, Philippe, Starck, Jean-Luc
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.03.2020; Multidisciplinary digital publishing institute (MDPI)
• Subjects: Algorithms; Brain; Computer Science; Computer Vision and Pattern Recognition; Datasets; Deep learning; Dictionaries; fastmri; Fourier transforms; image reconstruction; Inverse problems; Machine Learning; Magnetic resonance imaging; Medical Physics; mri; Neural networks; oasis; Optimization; Physics; Signal and Image Processing; Statistics; Wavelet transforms
• ISSN: 2076-3417; 2076-3417
• DOI: 10.3390/app10051816

Deep learning is starting to offer promising results for reconstruction in Magnetic Resonance Imaging (MRI). A lot of networks are being developed, but the comparisons remain hard because the frameworks used are not the same among studies, the networks are not properly re-trained, and the datasets used are not the same among comparisons. The recent release of a public dataset, fastMRI, consisting of raw k-space data, encouraged us to write a consistent benchmark of several deep neural networks for MR image reconstruction. This paper shows the results obtained for this benchmark, allowing to compare the networks, and links the open source implementation of all these networks in Keras. The main finding of this benchmark is that it is beneficial to perform more iterations between the image and the measurement spaces compared to having a deeper per-space network.