Clinical implementation and evaluation of deep learning-assisted automatic radiotherapy treatment planning for lung cancer

Purpose: The purpose of the study is to investigate the clinical application of deep learning (DL)-assisted automatic radiotherapy planning for lung cancer. Methods: A DL model was developed for predicting patient-specific doses, trained and validated on a dataset of 235 patients with diverse target volumes and prescriptions. The model was integrated into clinical workflow with DL-predicted objective functions. The automatic plans were retrospectively designed for additional 50 treated manual volumetric modulated arc therapy (VMAT) plans. A comparison was made between automatic and manual plans in terms of dosimetric indexes, monitor units (MUs) and planning time. Plan quality metric (PQM) encompassing these indexes was evaluated, with higher PQM values indicating superior plan quality. Qualitative evaluations of two plans were conducted by four reviewers. Results: The PQM score was 40.7 f 13.1 for manual plans and 40.8 f 13.5 for automatic plans (P = 0.75). Compared to manual plans, the targets coverage and homogeneity of automatic plans demonstrated no significant difference. Manual plans exhibited better sparing for lung in V5 (difference: 1.8 f 4.2 %, P = 0.02), whereas automatic plans showed enhanced sparing for heart in V30 (difference: 1.4 f 4.7 %, P = 0.02) and for spinal cord in Dmax (difference: 0.7 f 4.7 Gy, P = 0.04). The planning time and MUs of automatic plans were significantly reduced by 70.5 f 20.0 min and 97.4 f 82.1. Automatic plans were deemed acceptable in 88 % of the reviews (176/200). Conclusions: The DL-assisted approach for lung cancer notably decreased planning time and MUs, while demonstrating comparable or superior quality relative to manual plans. It has the potential to provide benefit to lung cancer patients.