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

Fan F, Qiu J, Huang Y, Maier A (2024)


Publication Language: English

Publication Type: Conference contribution

Publication year: 2024

Pages Range: 94-97

Event location: Bamberg, Germany

URI: https://arxiv.org/pdf/2409.05982

DOI: 10.48550/arXiv.2409.05982

Open Access Link: https://arxiv.org/pdf/2409.05982

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, \modified{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.

Authors with CRIS profile

How to cite

APA:

Fan, F., Qiu, J., Huang, Y., & Maier, A. (2024). Enhancing Cross-Modality Synthesis: Subvolume Merging for MRI-to-CT Conversion. In Proceedings of the The 8th International Conference on Image Formation in X-Ray Computed Tomography (pp. 94-97). Bamberg, Germany.

MLA:

Fan, Fuxin, et al. "Enhancing Cross-Modality Synthesis: Subvolume Merging for MRI-to-CT Conversion." Proceedings of the The 8th International Conference on Image Formation in X-Ray Computed Tomography, Bamberg, Germany 2024. 94-97.

BibTeX: Download