Premium
A Transfer‐Learning Approach for Accelerated MRI Using Deep Neural Networks
Author(s) -
Dar Salman Ul Hassan,
Özbey Muzaffer,
Çatlı Ahmet Burak,
Çukur Tolga
Publication year - 2020
Publication title -
magnetic resonance in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.696
H-Index - 225
eISSN - 1522-2594
pISSN - 0740-3194
DOI - 10.1002/mrm.28148
Subject(s) - computer science , transfer of learning , artificial neural network , artificial intelligence , domain (mathematical analysis) , deep neural networks , deep learning , pattern recognition (psychology) , machine learning , image (mathematics) , protocol (science) , transfer (computing) , computer vision , mathematics , medicine , mathematical analysis , alternative medicine , pathology , parallel computing
Purpose Neural networks have received recent interest for reconstruction of undersampled MR acquisitions. Ideally, network performance should be optimized by drawing the training and testing data from the same domain. In practice, however, large datasets comprising hundreds of subjects scanned under a common protocol are rare. The goal of this study is to introduce a transfer‐learning approach to address the problem of data scarcity in training deep networks for accelerated MRI. Methods Neural networks were trained on thousands (upto 4 thousand) of samples from public datasets of either natural images or brain MR images. The networks were then fine‐tuned using only tens of brain MR images in a distinct testing domain. Domain‐transferred networks were compared to networks trained directly in the testing domain. Network performance was evaluated for varying acceleration factors (4‐10), number of training samples (0.5‐4k), and number of fine‐tuning samples (0‐100). Results The proposed approach achieves successful domain transfer between MR images acquired with different contrasts (T 1 ‐ and T 2 ‐weighted images) and between natural and MR images (ImageNet and T 1 ‐ or T 2 ‐weighted images). Networks obtained via transfer learning using only tens of images in the testing domain achieve nearly identical performance to networks trained directly in the testing domain using thousands (upto 4 thousand) of images. Conclusion The proposed approach might facilitate the use of neural networks for MRI reconstruction without the need for collection of extensive imaging datasets.