Auto-Segmentation and Auto-Planning in Automated Radiotherapy for Prostate Cancer

<b>Objective:</b> The objective of this study was to develop and assess the clinical feasibility of auto-segmentation and auto-planning methodologies for automated radiotherapy in prostate cancer. <b>Methods</b>: A total of 166 patients were used to train a 3D Unet model for segmentation of the gross tumor volume (GTV), clinical tumor volume (CTV), nodal CTV (CTVnd), and organs at risk (OARs). Performance was assessed by the Dice similarity coefficient (<i>DSC</i>), the <i>Recall</i>, <i>Precision</i>, <i>Volume Ratio (VR)</i>, the 95% Hausdorff distance (<i>HD95</i>%), and the volumetric revision degree (<i>VRD</i>). An auto-planning network based on a 3D Unet was trained on 77 treatment plans derived from the 166 patients. Dosimetric differences and clinical acceptability of the auto-plans were studied. The effect of OAR editing on dosimetry was also evaluated. <b>Results</b>: On an independent set of 50 cases, the auto-segmentation process took 1 min 20 s per case. The <i>DSCs</i> for GTV, CTV, and CTVnd were 0.87, 0.88, and 0.82, respectively, with <i>VRD</i>s ranging from 0.09 to 0.14. The segmentation of OARs demonstrated high accuracy (<i>DSC</i> ≥ 0.83, <i>Recall/Precision</i> ≈ 1.0). The auto-planning process required 1-3 optimization iterations for 50%, 40%, and 10% of cases, respectively, and exhibited significant better conformity (<i>p</i> ≤ 0.01) and OAR sparing (<i>p</i> ≤ 0.03) while maintaining comparable target coverage. Only 6.7% of auto-plans were deemed unacceptable compared to 20% of manual plans, with 75% of auto-plans considered superior. Notably, the editing of OARs had no significant impact on doses. <b>Conclusions:</b> The accuracy of auto-segmentation is comparable to that of manual segmentation, and the auto-planning offers equivalent or better OAR protection, meeting the requirements of online automated radiotherapy and facilitating its clinical application.