Search

Purpose/Objective(s) To develop and evaluate a deep unsupervised learning (DUL) framework based on a regional deformable model for automated prostate contour propagation from planning computed tomography (pCT) to cone-beam CT (CBCT). Materials/Methods A DUL model was introduced to map the prostate contour from pCT to on-treatment CBCT. The DUL framework used a regional deformable model via narrow band mapping to augment the conventional strategy. 251 anonymized CBCT images from prostate cancer patients were retrospectively selected and divided into three sets: 180 were used for training, 12 for validation, and 59 for testing. The testing dataset was divided into two Groups. Group one contained 50 CBCT volumes, with one physician-generated prostate contour on CBCT image. Group two contained 9 CBCT images, each including prostate contours delineated by four independent physicians and a consensus contour generated using the STAPLE method. Results were compared between the proposed DUL and physician-generated contours through the Dice similarity coefficients (DSC), the Hausdorff distances, and the distances of the center-of-mass. Results The average DSCs between DUL-based prostate contours and reference contours for test data in Group one and Group two-consensus were 0.83 ± 0.04, and 0.85 ± 0.04, respectively. Correspondingly, the mean center-of-mass distances were 3.52 mm ± 1.15 mm, and 2.98 mm ± 1.42 mm, respectively. Conclusion This novel DUL technique can automatically propagate the contour of the prostate from pCT to CBCT. The proposed method shows that highly accurate contour propagation for CBCT-guided adaptive radiotherapy is achievable via the deep learning technique.

Background: The management of prostate cancer (PCa) that has been diagnosed after PSA testing relies on risk stratification. Treatments have significant urinary, digestive and sexual toxicities that can impact the patients’ quality of life. Many patients do not benefit from treatment because their cancer is indolent or because they die from other competitive causes. New models are needed to stratify patients at diagnosis and decide whether treatment could have an interest or not. Artificial Intelligence (AI) techniques can provide solutions in that setting. Methods: We used data from the prospective clinical trial PLCO and selected patients who were diagnosed with PCa during follow-up. We trained two gradient-boosting models to predict 10-year cancer-specific (CSS) and overall survival (OS) with features that described the general health status of the patients and PCa. Using shapley values, we provided a graphical and interpretable prediction, at the individual level. Findings: During follow-up, 8,776 patients were diagnosed with PCa. The dataset was split into a training (n=7,021) and a testing (n=1,755) dataset. Accuracy was 0.87 (± 0.02) and 0.98 (± 0.01) for OS and CSS respectively. The area under the receiver operating characteristic was 0.84 (± 0.02) and 0.81 (± 0.04) and the area under precision-recall was 0.6 (± 0.03) and 0.55 (± 0.07) for OS and CSS respectively. The models are available online. Interpretation: The clinical question of who to treat and who to observe is a major unmet need in prostate cancer. Using prospective data, we trained two models to predict 10-year CSS and OS with high accuracy. These models can be used online to provide predictions and support informed decision-making in PCa treatment. AI interpretability provides a novel understanding of the predictions to the clinicians and the patients using the models. Funding Statement: None. Declaration of Interests: The authors declare no conflict of interest. Ethics Approval Statement: The authors stated that since this was a secondary analysis of a previously approved clinical trial, no ethics committee approval was required.

Purpose Social media and mobile technology are transforming the way in which young physicians are learning and practicing medicine. The true impact of such technologies has yet to be evaluated. Methods and Materials We performed a nationwide cross-sectional survey to better assess how young radiation oncologists used these technologies. An online survey was sent out between April 24, 2013, and June 1, 2013. All residents attending the 2013 radiation oncology French summer course were invited to complete the survey. Logistic regressions were performed to assess predictors of use of these tools in the hospital on various clinical endpoints. Results In all, 131 of 140 (93.6%) French young radiation oncologists answered the survey. Of these individuals, 93% owned a smartphone and 32.8% owned a tablet. The majority (78.6%) of the residents owning a smartphone used it to work in their department. A total of 33.5% had more than 5 medical applications installed. Only 60.3% of the residents verified the validity of the apps that they used. In all, 82.9% of the residents had a social network account. Conclusions Most of the residents in radiation oncology use their smartphone to work in their department for a wide variety of tasks. However, the residents do not consistently check the validity of the apps that they use. Residents also use social networks, with only a limited impact on their relationship with their patients. Overall, this study highlights the irruption and the risks of new technologies in the clinical practice and raises the question of a possible regulation of their use in the hospital.