Enhancing Cross-Modality Synthesis: Subvolume Merging for MRI-to-CT Conversion
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913494387916800 |
|---|---|
| author | Fan, Fuxin Qiu, Jingna Huang, Yixing Maier, Andreas |
| author_facet | Fan, Fuxin Qiu, Jingna Huang, Yixing Maier, Andreas |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_05982 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Cross-Modality Synthesis: Subvolume Merging for MRI-to-CT Conversion Fan, Fuxin Qiu, Jingna Huang, Yixing Maier, Andreas Image and Video Processing Computer Vision and Pattern Recognition 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. |
| title | Enhancing Cross-Modality Synthesis: Subvolume Merging for MRI-to-CT Conversion |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.05982 |