Publications by authors named "J E Rosenman"
Background: We describe and evaluate a deep network algorithm which automatically contours organs at risk in the thorax and pelvis on computed tomography (CT) images for radiation treatment planning.
Methods: The algorithm identifies the region of interest (ROI) automatically by detecting anatomical landmarks around the specific organs using a deep reinforcement learning technique. The segmentation is restricted to this ROI and performed by a deep image-to-image network (DI2IN) based on a convolutional encoder-decoder architecture combined with multi-level feature concatenation.
Article Synopsis
- Colonoscopy is the preferred method for screening and treating pre-cancerous polyps, but current techniques struggle with complete examination of the colonic surface due to camera limitations and occlusions.
- An automatic system is proposed to identify and compute the regions of the colon that haven't been examined during a colonoscopy in real-time, alerting the doctors to any significant gaps.
- The new approach combines traditional SLAM technology with advanced depth and pose prediction networks to improve tracking accuracy and reduce errors during colonoscopic procedures.
Children and adolescents from minority and low income backgrounds face social and environmental challenges to engaging in physical activity and healthy eating to maintain a healthy weight. In this study, we present pilot work to develop and implement a multi-component physical activity and healthy eating intervention at a Boys & Girls Club (BGC) afterschool program. Using a community-based participatory approach, BGC staff and academic researchers developed intervention components informed by formative studies and based on a Social Ecological Theory framework.
View Article and Find Full Text PDF