2019/10/14 by Puneesh Deora, Bhavya Vasudeva, Deora, Puneesh +5 · 1 citation
Engineering · Medicine · #Advanced MRI Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Medical Imaging Techniques and Applications #Sparse and Compressive Sensing Techniques #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1910.06067
openalex publication_date 2019/10/14 · openalex created_date 2022/07/28 · openalex updated_date 2026/07/28
Compressive sensing magnetic resonance imaging (CS-MRI) accelerates the\nacquisition of MR images by breaking the Nyquist sampling limit. In this work,\na novel generative adversarial network (GAN) based framework for CS-MRI\nreconstruction is proposed. Leveraging a combination of patch-based\ndiscriminator and structural similarity index based loss, our model focuses on\npreserving high frequency content as well as fine textural details in the\nreconstructed image. Dense and residual connections have been incorporated in a\nU-net based generator architecture to allow easier transfer of information as\nwell as variable network length. We show that our algorithm outperforms\nstate-of-the-art methods in terms of quality of reconstruction and robustness\nto noise. Also, the reconstruction time, which is of the order of milliseconds,\nmakes it highly suitable for real-time clinical use.\n