Geometry-encoded deep learning (GeoDL) framework for real-time 3D dose verification for online adaptive radiotherapy
Machine Learning: Health · 2025
DOI: 10.1088/3049-477x/adcb4b ↗Kurz gefasst
Fachartikel in der Zeitschrift Machine Learning: Health, 2025. Verfasst von Shunyu Yan und 6 weiteren Autor:innen. Beteiligte Einrichtung: The Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology, University of Texas Southwestern Medical Cent…. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCI NIH HHS, Center for Cancer Research.
Abstract (Originalsprache)
Background
Accurate and efficient dose verification is vital for online adaptive radiotherapy (ART) while the patient is waiting on the treatment couch. Conventional methods are computationally intensive, limiting ART workflow efficiency and quality. A pilot study successfully illustrated the potential of geometry-encoded deep learning (GeoDL) algorithm for two-dimensional (2D) dose estimation on the central axial plane. This study investigates the feasibility of extending GeoDL for real-time dose verification for the entire three-dimensional (3D) volume of interest, fulfilling the unmet need in real clinical practice.
Methods
The proposed GeoDL unifies the representation of fluence maps (FMs) and CT images by resolving the treatment delivery geometry of a linear accelerator (LINAC) to ease the burden of learning the complex domain transformation between FMs and CT image. A carefully designed 3D U-Net was trained on the integrated CT-FM volume to estimate the 3D dose distribution for the entire volume of interest, utilizing a combined loss function focusing on prediction errors in both high and low dose regions. The model was trained and validated on 281 prostate cancer cases, with 24 additional cases employed for independent testing.
Results
The proposed GeoDL algorithm achieved highly accurate 3D dose estimation in almost real-time. The average γ passing rate ( 3 % / 2 m m , 10% threshold) for the estimated dose was 99.94% ± 0.15% on testing patients. The mean dose differences for the planning target volume (PTV) and organs at risk (OARs) were 0.93% ± 0.59% and 0.28% ± 0.32%, respectively. The average overall computational time for each testing case is ~35ms.
Conclusion
This study demonstrates the feasibility of GeoDL in ultra-fast dose verification for ART, with strong performance in relevant dosimetric metrics across the entire volume of interest, positioning it as a valuable tool for real clinical use.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- The Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.
Förderung
- NCI NIH HHS
- Center for Cancer Research
Zitieren
APA
Yan, S., Maniscalco, A., Wang, B., Zhao, H., Nguyen, D., Jiang, S., & Shen, C. (2025). Geometry-encoded deep learning (GeoDL) framework for real-time 3D dose verification for online adaptive radiotherapy. Machine Learning: Health. https://doi.org/10.1088/3049-477x/adcb4b
Vancouver
Yan S, Maniscalco A, Wang B, Zhao H, Nguyen D, Jiang S, et al. Geometry-encoded deep learning (GeoDL) framework for real-time 3D dose verification for online adaptive radiotherapy. Machine Learning: Health. 2025. doi:10.1088/3049-477x/adcb4b
BibTeX
@article{Yan2025,
author = {Yan, Shunyu and Maniscalco, Austen and Wang, Biling and Zhao, Hengrui and Nguyen, Dan and Jiang, Steve and Shen, Chenyang},
title = {Geometry-encoded deep learning (GeoDL) framework for real-time 3D dose verification for online adaptive radiotherapy},
journal = {Machine Learning: Health},
year = {2025},
doi = {10.1088/3049-477x/adcb4b}
}
EUVIMED