Personalized brachytherapy dose reconstruction using deep learning. (September 2021)

• Record Type: Journal Article
• Authors: Akhavanallaf, Azadeh; Mohammadi, Reza; Shiri, Isaac; Salimi, Yazdan; Arabi, Hossein; Zaidi, Habib
• Is Part Of: Computers in biology and medicine. Volume 136(2021)
• Publication Date: 2021-09
• Subjects: Brachytherapy -- Dose reconstruction -- Heterogeneity correction -- Monte Carlo -- Deep learning; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2021.104755
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Background and purpose: Accurate calculation of the absorbed dose delivered to the tumor and normal tissues improves treatment gain factor, which is the major advantage of brachytherapy over external radiation therapy. To address the simplifications of TG-43 assumptions that ignore the dosimetric impact of medium heterogeneities, we proposed a deep learning (DL)-based approach, which improves the accuracy while requiring a reasonable computation time. Materials and methods: We developed a Monte Carlo (MC)-based personalized brachytherapy dosimetry simulator ( PBrDoseSim ), deployed to generate patient-specific dose distributions. A deep neural network (DNN) was trained to predict personalized dose distributions derived from MC simulations, serving as ground truth. The paired channel input used for the training is composed of dose distribution kernel in water medium along with the full-volumetric density maps obtained from CT images reflecting medium heterogeneity. Results: The predicted single-dwell dose kernels were in good agreement with MC-based kernels serving as reference, achieving a mean relative absolute error (MRAE) and mean absolute error (MAE) of 1.16 ± 0.42% and 4.2 ± 2.7 × 10 −4 (Gy.sec −1 /voxel), respectively. The MRAE of the dose volume histograms (DVHs) between the DNN and MC calculations in the clinical target volume were 1.8 ± 0.86%, 0.56 ± 0.56%, and 1.48 ± 0.72% for D90, V150, and V100, respectively. For bladder, sigmoid, and rectum, the MRAE of D5cc between the DNN and MC calculations were 2.7 ± 1.7%, 1.9 ± 1.3%, and 2.1 ± 1.7%, respectively. Conclusion: The proposed DNN-based personalized brachytherapy dosimetry approach exhibited comparable performance to the MC method while overcoming the computational burden of MC calculations and oversimplifications of TG-43. Graphical abstract: Image 1 Highlights: We developed a physics-informed deep learning-based framework through feeding full voxel density map into the neural network. We developed a Monte Carlo-based Brachytherapy Dosimetry Simulator (PBrDoseSim) to estimate patient-specific dose maps. The DNN outperformed other approaches by achieving the lowest bias and the smallest variance against MC calculations. Dose volume histogram-driven metrics demonstrated a lower bias and variance compared to AAPM TG-43 approach.