ABSTRACT
Background: Continuing medical education in stereotactic technology are scarcely accessible in developing countries. We report the results of upscaling a longitudinal telehealth training course on stereotactic body radiation therapy (SBRT) and stereotactic radiosurgery (SRS), after successfully developing a pilot course in Latin America. Methods: Longitudinal training on SBRT and SRS was provided to radiation oncology practitioners in Peru and Colombia at no cost. The program included sixteen weekly 1-hour live conferencing sessions with interactive didactics and a cloud-based platform for case-based learning. Participant-reported confidence was measured in 16 SBRT/SRS practical domains, based on a 1-to-5 Likert scale. Pre- and post-curriculum exams were required for participation credit. Knowledge-baseline, pre- and post-curriculum surveys, overall and single professional-group confidence changes, and exam results were assessed. Results: One hundred and seventy-three radiotherapy professionals participated. An average of 56 (SD ±18) attendees per session were registered. Fifty (29.7%) participants completed the pre- and post-curriculum surveys, of which 30% were radiation oncologists (RO), 26% radiation therapists (RTT), 20% residents, 18% medical physicists and 6% neurosurgeons. Significant improvements were found across all 16 domains with overall mean +0.55 (SD ±0.17, p<0.001) Likert-scale points. Significant improvements in individual competences were most common among medical physicists, RTT and residents. Pre- and post-curriculum exams yielded a mean 16.15/30 (53.8 ± 20.3%) and 23.6/30 (78.7 ± 19.3%) correct answers (p<0.001). Conclusion: Longitudinal telehealth training is an effective method for improving confidence and knowledge on SBRT/SRS amongst professionals. Remote continuing medical education should be widely adopted in lower-middle income countries.
ABSTRACT
PURPOSE: Automatic segmentation of medical images with deep learning (DL) algorithms has proven highly successful in recent times. With most of these automation networks, inter-observer variation is an acknowledged problem that leads to suboptimal results. This problem is even more significant in segmenting postoperative clinical target volumes (CTV) because they lack a macroscopic visible tumor in the image. This study, using postoperative prostate CTV segmentation as the test case, tries to determine 1) whether physician styles are consistent and learnable, 2) whether physician style affects treatment outcome and toxicity, and 3) how to explicitly deal with different physician styles in DL-assisted CTV segmentation to facilitate its clinical acceptance. METHODS: A dataset of 373 postoperative prostate cancer patients from UT Southwestern Medical Center was used for this study. We used another 83 patients from Mayo Clinic to validate the developed model and its adaptability. To determine whether physician styles are consistent and learnable, we trained a 3D convolutional neural network classifier to identify which physician had contoured a CTV from just the contour and the corresponding CT scan. Next, we evaluated whether adapting automatic segmentation to specific physician styles would be clinically feasible based on a lack of difference between outcomes. Here, biochemical progression-free survival (BCFS) and grade 3+ genitourinary and gastrointestinal toxicity were estimated with the Kaplan-Meier method and compared between physician styles with the log rank test and subsequently with a multivariate Cox regression. When we found no statistically significant differences in outcome or toxicity between contouring styles, we proposed a concept called physician style-aware (PSA) segmentation by developing an encoder-multidecoder network with perceptual loss to model different physician styles of CTV segmentation. RESULTS: The classification network captured the different physician styles with 87% accuracy. Subsequent outcome analysis showed no differences in BCFS and grade 3+ toxicity among physicians. With the proposed physician style-aware network (PSA-Net), Dice similarity coefficient (DSC) accuracy for all physicians was 3.4% higher on average than with a general model that does not differentiate physician styles. We show that these stylistic contouring variations also exist between institutions that follow the same segmentation guidelines, and we show the proposed method's effectiveness in adapting to new institutional styles. We observed an accuracy improvement of 5% in terms of DSC when adapting to the style of a separate institution. CONCLUSION: The performance of the classification network established that physician styles are learnable, and the lack of difference between outcomes among physicians shows that the network can feasibly adapt to different styles in the clinic. Therefore, we developed a novel PSA-Net model that can produce contours specific to the treating physician, thus improving segmentation accuracy and avoiding the need to train multiple models to achieve different style segmentations. We successfully validated this model on data from a separate institution, thus supporting the model's generalizability to diverse datasets.