PhD Student Tony Chi Wing Mok Awarded First Place in MICCAI Learn2Reg 2021 Challenge

CSE PhD student Tony Chi Wing Mok achieved First Place in the MICCAI Learn2Reg 2021 challenge with the method presented in his paper "Conditional Deformable Image Registration with Convolutional Neural Network", co-authored with Prof. Albert Chung, Professor of Computer Science and Engineering and Associate Dean of Engineering (Undergraduate Studies). Prior to receiving first place in this challenge, Tony has also received first place in the MICCAI Learn2Reg 2020 Challenge.

In their paper, they proposed a novel conditional deformable image registration framework and self-supervised learning paradigm for deep learning-based deformable image registration. By shifting the feature statistics, their method learns the conditional features that are correlated with the regularization hyperparameter. In addition, runtime advantage or registration accuracy of the original deep learning-based image registration (DLIR) method no longer need to be sacrificed as a more precise control of the smoothness regularization in the inference face has been demonstrated.

Learn2Reg challenge is a medical image registration challenge organized by The Medical Image Computing and Computer Assisted Intervention Society (MICCAI). It aims to standardise benchmark for the best conventional and learning based medical registration methods.

Congratulations again to Tony!

For more details, please refer to the event website and the paper.

Prof. Albert Chung (left) and Tony Chi Wing Mok

Prof. Albert Chung (left) and Tony Chi Wing Mok