Feasibility study of using CNN‐GRU‐Dense model for real‐time liver tumor tracking during radiotherapy
The simulation results showed that the CNN-GRU-Dense model outperformed several existing methods, including the augmented linear model used in standard linear accelerators, the NG-RC model, and the constrained fourth-order polynomial equations used in the CyberKnife and Radixact systems. One key advantage of the CNN-GRU-Dense model is that it doesn't need to be updated during treatment, which reduces patients' radiation exposure.
Authors
- Payam Samadi Miandoab (ORCID: https://orcid.org/0000-0002-4337-1245)
- Gaolong Zhang (ORCID: https://orcid.org/0000-0003-4615-3187)
- Xuying Shang
- Shouping Xu (ORCID: https://orcid.org/0000-0003-3189-9680)
- Tie Lv (ORCID: https://orcid.org/0000-0002-1960-8687)
- Yaoying Liu (ORCID: https://orcid.org/0000-0002-6282-9936)
- Hui Xu (ORCID: https://orcid.org/0009-0003-2994-9834)
Institutions
- Chinese Academy of Medical Sciences & Peking Union Medical College (CN)
- National Cancer Center (US)
- Beihang University (CN)
- Tsinghua University (CN)
Publication Details
- Journal
- Medical Physics
- Published
- 2025-09-21
- DOI
- https://doi.org/10.1002/mp.70014
- Citations
- 1
- Primary Topic
- Brain Tumor Detection and Classification
- Type
- article
- Field-Weighted Citation Impact
- 0.84