Search

In this study, we aimed to enhance the contouring accuracy of cardiac pacemakers by improving their visualization using deep learning models to predict MV CBCT images based on kV CT or CBCT images. Ten pacemakers and four thorax phantoms were included, creating a total of 35 combinations. Each combination was imaged on a Varian Halcyon (kV/MV CBCT images) and Siemens SOMATOM CT scanner (kV CT images). Two generative adversarial network (GAN)-based models, cycleGAN and conditional GAN (cGAN), were trained to generate synthetic MV (sMV) CBCT images from kV CT/CBCT images using twenty-eight datasets (80%). The pacemakers in the sMV CBCT images and original MV CBCT images were manually delineated and reviewed by three users. The Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and mean surface distance (MSD) were used to compare contour accuracy. Visual inspection showed the improved visualization of pacemakers on sMV CBCT images compared to original kV CT/CBCT images. Moreover, cGAN demonstrated superior performance in enhancing pacemaker visualization compared to cycleGAN. The mean DSC, HD95, and MSD for contours on sMV CBCT images generated from kV CT/CBCT images were 0.91 ± 0.02/0.92 ± 0.01, 1.38 ± 0.31 mm/1.18 ± 0.20 mm, and 0.42 ± 0.07 mm/0.36 ± 0.06 mm using the cGAN model. Deep learning-based methods, specifically cycleGAN and cGAN, can effectively enhance the visualization of pacemakers in thorax kV CT/CBCT images, therefore improving the contouring precision of these devices.

PURPOSEFormal education in the radiation sciences is critical for the safe and effective delivery of radiotherapy. Practices and patterns of radiation sciences education and trainee performance in the radiation sciences are poorly described. This study assesses the current state of radiation sciences education in Africa and evaluates a high-yield, on-site educational program in radiation biology and radiation physics for oncology and radiation therapy trainees in Africa.METHODSAn anonymous survey was distributed to members of the African Organization for Research and Treatment in Cancer Training Interest Group to assess current attitudes and practices toward radiation sciences education. A 2-week, on-site educational course in radiation biology and radiation physics was conducted at the Cancer Diseases Hospital in Lusaka, Zambia. Pre- and postcourse assessments in both disciplines were administered to gauge the effectiveness of an intensive high-yield course in the radiation sciences.RESULTSSignificant deficiencies were identified in radiation sciences education, especially in radiation biology. Lack of expert instructors in radiation biology was reported by half of all respondents and was the major contributing factor to deficient education in the radiation sciences. The educational course resulted in marked improvements in radiation biology assessment scores (median pre- and posttest scores, 27% and 55%, respectively; P < .0001) and radiation physics assessment scores (median pre- and posttest scores, 30% and 57.5%, respectively; P < .0001).CONCLUSIONRadiation sciences education in African oncology training programs is inadequate. International collaboration between expert radiation biology and radiation physics instructors can address this educational deficiency and improve trainee competence in the foundational radiation sciences that is critical for the safe and effective delivery of radiotherapy.