UNSUPERVISED DEFORMABLE MEDICAL IMAGE REGISTRATION WITH CONVOLUTIONAL NEURAL NETWORKS

PhD Thesis Proposal Defence


Title: "UNSUPERVISED DEFORMABLE MEDICAL IMAGE REGISTRATION WITH 
CONVOLUTIONAL NEURAL NETWORKS"

by

Mr. Chi Wing MOK


Abstract:

Image registration and the subsequent quantitative assessment in medical 
imaging studies provide valuable information that is important for 
clinical diagnosis, evolutionary evaluation and planning of treatment 
strategies. The treatment quality and diagnosis precision of these 
applications highly rely on an accurate registration result of automated 
image registration algorithms. Therefore, it is essential to improve the 
robustness, accuracy and runtime of image registration. Recently, there is 
a rapid adoption of deep learning-based medical image registration 
applications over the past few years. While existing deep learning-based 
image registration approaches significantly accelerate the image 
registration by circumventing the costly iterative optimization process in 
conventional methods, these methods often ignore the desirable 
diffeomorphic properties of the transformation and fail spectacularly in 
images with large displacement settings and in medical images with 
pathologies. The core of this thesis proposal is to develop a novel 
learning-based image registration framework for deformable medical image 
registration, which addresses the aforementioned issues. The contributions 
are linked under the common theme of learning-based image registration, 
but stand on their own as valuable components within the image 
registration framework.

In particular, a new unsupervised symmetric image registration method is 
proposed which maximizes the similarity between images within the space of 
diffeomorphic maps and estimates both forward and inverse transformations 
simultaneously. This original concept learns the image registration 
problem within the space of diffeomorphic maps, resulting in securing 
desirable diffeomorphic properties of the solution. Furthermore, we 
introduce a pioneering conditional deformable image registration 
architecture and learning paradigm for large deformation image 
registration and rapid hyperparameter tuning. By learning the conditional 
features that are correlated with the hyperparameters and utilizing the 
advantages of the multi-resolution architecture, our formulation achieves 
end-to-end fast image registration under large deformation settings and 
enables fast hyperparameter tuning in learning-based registration, where 
usual learning-based registration solutions do not succeed. Finally, we 
present a new deep learning-based deformable registration method that 
jointly estimates regions with absent correspondence and bidirectional 
deformation fields in pre-operative and follow-up brain tumour MRI scans. 
The experimental results demonstrated that our novel methods can achieve 
higher robustness and registration quality, as compared with 
state-of-the-art approaches, in deformable image registration under large 
deformation and images with missing correspondences.


Date:			Tuesday, 9 August 2022

Time:                  	2:00pm - 4:00pm

Zoom Meeting: 
https://hkust.zoom.us/j/96051474396?pwd=bFJGS1d0Qk9tajl4S1V6MmE4VnFTdz09

Committee Members:	Prof. Albert Chung (Supervisor)
 			Prof. Pedro Sander (Supervisor)
 			Dr. Minhao Cheng (Chairperson)
 			Prof. Siu-Wing Cheng


**** ALL are Welcome ****