Timezone: »

 
On the Robustness of deep learning-based MRI Reconstruction to image transformations
jinghan jia · Mingyi Hong · Yimeng Zhang · Mehmet Akcakaya · Sijia Liu

@
in Trustworthy and Socially Responsible Machine Learning »
Event URL: https://openreview.net/forum?id=guu52Gtj1B »

Although deep learning (DL) has received much attention in accelerated magnetic resonance imaging (MRI), recent studies show that tiny input perturbations may lead to instabilities of DL-based MRI reconstruction models. However, the approaches of robustifying these models are underdeveloped. Compared to image classification, it could be much more challenging to achieve a robust MRI image reconstruction network considering its regression-based learning objective, limited amount of training data, and lack of efficient robustness metrics. To circumvent the above limitations, our work revisits the problem of DL-based image reconstruction through the lens of robust machine learning. We find a new instability source of MRI image reconstruction, i.e., the lack of reconstruction robustness against spatial transformations of an input, e.g., rotation and cutout. Inspired by this new robustness metric, we develop a robustness-aware image reconstruction method that can defend against both pixel-wise adversarial perturbations as well as spatial transformations. Extensive experiments are also conducted to demonstrate the effectiveness of our proposed approaches.

[ Poster]  [ OpenReview]  [ Topia] 

Author Information

jinghan jia (Michigan State University (MSU))
Mingyi Hong (University of Minnesota)
Yimeng Zhang (Michigan State University)
Mehmet Akcakaya (University of Minnesota)
Sijia Liu (Michigan State University)

More from the Same Authors