Enhancing Cross-Modality Synthesis: Subvolume Merging for MRI-to-CT Conversion

TL;DR

This paper improves MRI-to-CT synthesis for radiation therapy planning by introducing a subvolume merging technique with optimal overlap and weighting, reducing errors and artifacts in the generated images.

Contribution

It presents a novel 3D subvolume merging method with optimal overlap and weighting to enhance MRI-to-CT synthesis accuracy using SwinUNETR.

Findings

Mean absolute error reduced from 52.65 HU to 47.75 HU

Optimal overlap between 50% and 70% balances quality and efficiency

Gamma-weighted merging further decreases MAE

Abstract

Providing more precise tissue attenuation information, synthetic computed tomography (sCT) generated from magnetic resonance imaging (MRI) contributes to improved radiation therapy treatment planning. In our study, we employ the advanced SwinUNETR framework for synthesizing CT from MRI images. Additionally, we introduce a three-dimensional subvolume merging technique in the prediction process. By selecting an optimal overlap percentage for adjacent subvolumes, stitching artifacts are effectively mitigated, leading to a decrease in the mean absolute error (MAE) between sCT and the labels from 52.65 HU to 47.75 HU. Furthermore, implementing a weight function with a gamma value of 0.9 results in the lowest MAE within the same overlap area. By setting the overlap percentage between 50% and 70%, we achieve a balance between image quality and computational efficiency.