Meta-Learning Guided Pelvis MR to CT Translation: Addressing Cross-Modality Misalignments

Daniel Kim, Yoseob Han, Kanghyun Ryu, Dong-Hyun Kim

Abstract:

Motivation: In radiation therapy planning, both MR and CT are essential, but there is a potential risk of radiation exposure from CT. To address this problem, MR to CT translation could be an important solution.

Goal(s): In cross-modality translations like MR to CT, misalignment is significant challenge. The goal is to develop a method that can effectively learn to handle this misalignment.

Approach: We propose a method that utilizes meta-learning to focus on reliable regions and employs loss functions and network suited for misalignment.

Results: Our method surpassed existing GAN-based methods in quantitative evaluations, particularly in the reconstruction of bone structures.

Impact: It can be seen that meta-learning can be effectively applied to the problem of misalignment. This can aid in preserving fine details and bone structures in MR to CT translation. It is also broadly applicable to cross-modality translation.