Accelerated MRI with Deep Linear Convolutional Transform Learning
- Authors
- Gu, H.[Gu, H.]; Yaman, B.[Yaman, B.]; Moeller, S.[Moeller, S.]; Chun, I.Y.[Chun, I.Y.]; Akcakaya, M.[Akcakaya, M.]
- Issue Date
- 2022
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Keywords
- AI; deep learning; inverse problems; MRI reconstruction; transform learning
- Citation
- 2022 IEEE 13th Annual Information Technology, Electronics and Mobile Communication Conference, IEMCON 2022, pp.197 - 201
- Indexed
- SCOPUS
- Journal Title
- 2022 IEEE 13th Annual Information Technology, Electronics and Mobile Communication Conference, IEMCON 2022
- Start Page
- 197
- End Page
- 201
- URI
- https://scholarworks.bwise.kr/skku/handle/2021.sw.skku/105639
- DOI
- 10.1109/IEMCON56893.2022.9946548
- ISSN
- 0000-0000
- Abstract
- Recent studies show that deep learning (DL) based MRI reconstruction outperforms conventional methods, such as parallel imaging and compressed sensing (CS), in multiple applications. Unlike CS that is typically implemented with pre-determined linear representations for regularization, DL inherently uses a non-linear representation learned from a large database. Another line of work uses transform learning (TL) to bridge the gap between these two approaches by learning linear representations from data. In this work, we combine ideas from CS, TL and DL reconstructions to learn deep linear convolutional transforms as part of an algorithm unrolling approach. Using end-to-end training, our results show that the proposed technique can reconstruct MR images to a level comparable to DL methods, while supporting uniform undersampling patterns unlike conventional CS methods. Our proposed method relies on convex sparse image reconstruction with linear representation at inference time, which may be beneficial for characterizing robustness, stability and generalizability. © 2022 IEEE.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - Information and Communication Engineering > School of Electronic and Electrical Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.