Prostate cancer treatment strategies are guided by risk-stratification. This stratification can be difficult in some patients with known comorbidities. New models are needed to guide strategies and determine which patients are at risk of prostate cancer mortality. This article presents a gradient-boosting model to predict the risk of prostate cancer mortality within 10 years after a cancer diagnosis, and to provide an interpretable prediction. This work uses prospective data from the PLCO Cancer Screening and selected patients who were diagnosed with prostate cancer. During follow-up, 8776 patients were diagnosed with prostate cancer. The dataset was randomly split into a training (n = 7021) and testing (n = 1755) dataset. Accuracy was 0.98 (±0.01), and the area under the receiver operating characteristic was 0.80 (±0.04). This model can be used to support informed decision-making in prostate cancer treatment. AI interpretability provides a novel understanding of the predictions to the users.
Background: Emerging hypofractionated prostate radiotherapy regimens require solutions for accurate target tracking during beam delivery. The goal of this study is to evaluate the performance of the Clarity ultrasound monitoring system for prostate motion tracking. Methods: Five prostate patients underwent continuous perineum ultrasound imaging during their daily treatments. Initial absolute 3D positions of fiducials implanted in the prostate were estimated from the KV images. Fiducial positions in MV images acquired during beam delivery were compared with predicted positions based on Clarity 3D tracking. The uncertainty in the comparison results was evaluated in a phantom validation study. Results: Continuous real-time ultrasound motion tracking was recorded in 5 patients and 167 fractions for overall of 39.7 h. Phantom validation of the proposed procedure demonstrated that predicted and observed fiducial positions agree within 1.1 mm. In patients agreement between predicted and actual fiducial positions varied between 1.3 mm and 3.3 mm. On average ultrasound tracking reduced the maximum localization error in patients by 20% on average. With the motion corrected, the duration prostate beyond 1 mm from its initial treatment position can be reduced from 37 to 22% of the total treatment time. Conclusion: Real-time ultrasound tracking reduces uncertainty in prostate position due to intra-fractional motion.