Segmentation methods and dosimetric evaluation of 3D-printed immobilization devices in head and neck radiotherapy
This study highlights the potential of Mask2Former in 3D-printed headrest and MFIF segmentation automation, providing a novel approach to enhance personalized radiation therapy plan accuracy. The attenuation effects of 3D-printed headrests and MFIFs reduce V<sub>100%</sub> and D<sub>mean</sub> for PTVs in head and neck cancer patients, while the buildup effects of 3D-printed headrests increases the skin dose (31.3%). Challenges such as segmentation inaccuracies for small targets and artifacts from metal fasteners in MFIFs highlight the need for model optimization and validation on larger, more diverse datasets.
Authors
- Weisha Zhang (ORCID: https://orcid.org/0009-0000-1533-0959)
- Ming Wang (ORCID: https://orcid.org/0000-0002-0384-1767)
- Luxin Yu
- Yunpeng Yin (ORCID: https://orcid.org/0009-0006-2859-624X)
- Lian Zou
- Xiangxiang Liu (ORCID: https://orcid.org/0000-0002-4934-6227)
Institutions
- University of Electronic Science and Technology of China (CN)
- Chengdu University of Technology (CN)
Publication Details
- Journal
- BMC Cancer
- Published
- 2025-02-18
- DOI
- https://doi.org/10.1186/s12885-025-13669-0
- Citations
- 3
- Primary Topic
- Advanced Radiotherapy Techniques
- Type
- article
- Field-Weighted Citation Impact
- 5.65
Funders
- Natural Science Foundation of Sichuan Province