Efficient deep learning-driven workflows for accelerated single-fraction radiation therapy planning of a solitary tumour in the lung.
Authors
Affiliations (5)
Affiliations (5)
- Peter MacCallum Cancer Centre, Melbourne, Victoria 3000, Australia.
- Sir Peter MacCallum Department of Oncology, the University of Melbourne, Victoria 3000, Australia.
- Centre for Medical Radiation Physics, University of Wollongong, NSW 2522, Australia.
- Department of Medical Imaging and Radiation Sciences, Monash University, Clayton, Victoria 3800, Australia.
- School of Translational Medicine, Monash University, Melbourne, Victoria 3800, Australia.
Abstract
Same-day, single-fraction radiotherapy requires efficient planning. We introduce two deep learning (DL) dose prediction-driven workflows to generate clinically acceptable plans for treating metastases in the lung. Consecutive patients treated for a tumour in the lung (11/2018-11/2024) were considered. One workflow used the computed tomography density map and a synthetic dose built from the tumour segmentation as inputs for the DL model [<i>without-organs of interest (OOI)</i>]. The other workflow additionally used predicted OOI segmentations (<i>with-OOI</i>). Optimisation objectives were extracted from the predicted dose by the treatment planning system (TPS). Generated plans were compared with clinical plans with the number of achieved goals, conformity index CI<sub>100</sub>, and control point modulation complexity score (cpMCS). Plan complexity increases with decreasing cpMCS. Processing times were recorded. Training and testing datasets contained 200 and 56 treatments, respectively. Without- / with-OOI workflows generated plans in 8.8 and 9.6 min. The 3%/3 mm gamma passing rates between predicted and clinical doses were median ± interquartile range 99.4 ± 0.7% / 99.3 ± 0.8%. After dose optimisation in the TPS, 25% of plans had a higher number of achieved clinical goals relative to clinical plans in both workflows. The conformity was improved (CI<sub>100</sub> = -5.3% / -3.9% relative to the clinical value, <i>p</i>-values <0.001) at the cost of increased complexity (cpMCS = -19.4% / -19.0%, <i>p</i>-values <0.001). Workflows driven by DL dose prediction could generate a clinically acceptable plan in less than ten minutes for same-day, single-fraction treatment of a tumour in the lung.