Deep Learning-based Volumetric Modulated Arc Therapy Dose Prediction with Uncertainty Quantification for Left- and Right-sided Breast Cancer: A Single-institution Feasibility Study
Abstract
Background: Volumetric-modulated arc therapy (VMAT) enables precise tumor targeting while minimizing dose to organs at risk but requires time-consuming planning with quality variability. Most deep learning (DL) dose prediction studies focus on left-sided breast cancer, with limited exploration of right-sided cases or integrated uncertainty quantification. This study investigates the feasibility of a DL model for VMAT dose prediction in both left-and right-sided breast cancer, incorporating Monte Carlo dropout (MCD)-based uncertainty quantification within a single-institution dataset. Methods: A total of 68 clinically accepted breast cancer VMAT treatment plans (41 left-sided, 27 right-sided) were collected. A three-dimensional U-Net architecture was implemented. Two models with dropout rates of 0.25 (M0.25) and 0.50 (M0.50) were developed. MCD was applied for uncertainty quantification. Performance was evaluated using mean absolute error (MAE), gamma passing rate (GPR), and isodose Dice similarity coefficients. Results: The overall body MAE was 1.7 ± 0.11 Gy (M0.25) and 1.93 ± 0.11 Gy (M0.50). For the planning target volume (PTV) of 42.56 Gy, MAE was 0.93 ± 0.17 Gy (M0.25) and 0.88 ± 0.15 Gy (M0.50). The heart showed the lowest errors (M0.25: 0.87 ± 0.34 Gy; M0.50: 1.06 ± 0.38 Gy), while contralateral lung exhibited higher uncertainties. GPR at 3%/3 mm reached 85.5% for both models, with no significant difference between left- and right-sided cases. Uncertainty maps correlated with prediction errors (Pearson correlation =0.59) and identified regions with atypical anatomies. Conclusions: The proposed model supports the feasibility of VMAT dose prediction for both left-and right-sided breast cancer, while the uncertainty maps provide additional confidence information to assist clinical interpretation and decision-making. Uncertainty maps correlated with prediction error and flagged atypical cases. External validation with a larger, multi-institutional dataset is required before clinical implementation can be considered.
Related
- Physics-based prediction, uncertainty quantification and decision-making for IN718 crystallographic texture intensity across LPBF defocus regimes
- Dosimetric Outcomes of Definitive Radiation Therapy to Anal Squamous Cell Carcinoma in a Single Institution Using Volumetric Modulated Arc Therapy Evaluated Against Australian and International Treatment Planning Guidelines
- Real-time volumetric MRI-guided MLC tracking: A feasibility study
- Rapid Uncertainty Quantification on a Latent Field using Fisher Information
- Reconstruction of Unobserved Core Electron Density in Tokamak Plasmas with a Neural Operator Transport Surrogate and Uncertainty Quantification
BibTeX
@article{sukha2026deep,
title = {{Deep Learning-based Volumetric Modulated Arc Therapy Dose Prediction with Uncertainty Quantification for Left- and Right-sided Breast Cancer: A Single-institution Feasibility Study}},
author = {Thanakorn Sukha and Chanon Puttanawarut and Nat Sirirutbunkajorn and Pimolpun Changkaew and Nauljun Stansook and Suphalak Khachonkham},
journal = {Journal of Medical Physics},
year = {2026},
month = jul,
doi = {10.4103/jmp.jmp_147_26},
url = {https://doi.org/10.4103/jmp.jmp_147_26},
note = {CC BY-NC-SA},
}
RIS
TY - JOUR
TI - Deep Learning-based Volumetric Modulated Arc Therapy Dose Prediction with Uncertainty Quantification for Left- and Right-sided Breast Cancer: A Single-institution Feasibility Study
AU - Thanakorn Sukha
AU - Chanon Puttanawarut
AU - Nat Sirirutbunkajorn
AU - Pimolpun Changkaew
AU - Nauljun Stansook
AU - Suphalak Khachonkham
PY - 2026
DA - 2026/07/01
JO - Journal of Medical Physics
DO - 10.4103/jmp.jmp_147_26
UR - https://doi.org/10.4103/jmp.jmp_147_26
AB - Background: Volumetric-modulated arc therapy (VMAT) enables precise tumor targeting while minimizing dose to organs at risk but requires time-consuming planning with quality variability. Most deep learning (DL) dose prediction studies focus on left-sided breast cancer, with limited exploration of right-sided cases or integrated uncertainty quantification. This study investigates the feasibility of a DL model for VMAT dose prediction in both left-and right-sided breast cancer, incorporating Monte Carlo dropout (MCD)-based uncertainty quantification within a single-institution dataset. Methods: A total of 68 clinically accepted breast cancer VMAT treatment plans (41 left-sided, 27 right-sided) were collected. A three-dimensional U-Net architecture was implemented. Two models with dropout rates of 0.25 (M0.25) and 0.50 (M0.50) were developed. MCD was applied for uncertainty quantification. Performance was evaluated using mean absolute error (MAE), gamma passing rate (GPR), and isodose Dice similarity coefficients. Results: The overall body MAE was 1.7 ± 0.11 Gy (M0.25) and 1.93 ± 0.11 Gy (M0.50). For the planning target volume (PTV) of 42.56 Gy, MAE was 0.93 ± 0.17 Gy (M0.25) and 0.88 ± 0.15 Gy (M0.50). The heart showed the lowest errors (M0.25: 0.87 ± 0.34 Gy; M0.50: 1.06 ± 0.38 Gy), while contralateral lung exhibited higher uncertainties. GPR at 3%/3 mm reached 85.5% for both models, with no significant difference between left- and right-sided cases. Uncertainty maps correlated with prediction errors (Pearson correlation =0.59) and identified regions with atypical anatomies. Conclusions: The proposed model supports the feasibility of VMAT dose prediction for both left-and right-sided breast cancer, while the uncertainty maps provide additional confidence information to assist clinical interpretation and decision-making. Uncertainty maps correlated with prediction error and flagged atypical cases. External validation with a larger, multi-institutional dataset is required before clinical implementation can be considered.
SN - 0971-6203
SN - 1998-3913
ER -