Adversarial Robust Training of Deep Learning MRI Reconstruction Models

Francesco Calivá10000-0002-0425-7511, Kaiyang Cheng1,2, Rutwik Shah10000-0002-4290-1320, Valentina Pedoia1
1: Center for Intelligent Imaging (CI2), University of California, San Francisco, 2: Department of Electrical Engineering and Computer Sciences, University of California, Berkeley
Publication date: 2021/04/28
PDF · Code · Video · arXiv


Deep Learning (DL) has shown potential in accelerating Magnetic Resonance Image acquisition and reconstruction. Nevertheless, there is a dearth of tailored methods to guarantee that the reconstruction of small features is achieved with high fidelity. In this work, we employ adversarial attacks to generate small synthetic perturbations, which are difficult to reconstruct for a trained DL reconstruction network. Then, we use robust training to increase the network’s sensitivity to these small features and encourage their reconstruction. Next, we investigate the generalization of said approach to real world features. For this, a musculoskeletal radiologist annotated a set of cartilage and meniscal lesions from the knee Fast-MRI dataset, and a classification network was devised to assess the reconstruction of the features. Experimental results show that by introducing robust training to a reconstruction network, the rate of false negative features (4.8%) in image reconstruction can be reduced. These results are encouraging, and highlight the necessity for attention to this problem by the image reconstruction community, as a milestone for the introduction of DL reconstruction in clinical practice. To support further research, we make our annotations and code publicly available at


mri reconstruction · adversarial attack · robust training · abnormality detection · fast mri

Bibtex @article{melba:2021:007:calivá, title = "Adversarial Robust Training of Deep Learning MRI Reconstruction Models", author = "Calivá, Francesco and Cheng, Kaiyang and Shah, Rutwik and Pedoia, Valentina", journal = "Machine Learning for Biomedical Imaging", volume = "1", issue = "MIDL 2020 special issue", year = "2021", pages = "1--32", issn = "2766-905X", doi = "", url = "" }
RISTY - JOUR AU - Calivá, Francesco AU - Cheng, Kaiyang AU - Shah, Rutwik AU - Pedoia, Valentina PY - 2021 TI - Adversarial Robust Training of Deep Learning MRI Reconstruction Models T2 - Machine Learning for Biomedical Imaging VL - 1 IS - MIDL 2020 special issue SP - 1 EP - 32 SN - 2766-905X DO - UR - ER -

2021:007 cover