Publications by authors named "T Heimann"
Article Synopsis
- The study aimed to create an automated system using convolutional neural networks (CNNs) to assess bone erosions, osteitis, and synovitis in hand MRIs of patients with inflammatory arthritis.
- The CNNs were trained and validated using MRI images from patients with rheumatoid and psoriatic arthritis, and their performance was compared to expert rheumatologists through metrics like receiver operating characteristic curve (AUC) and balanced accuracy.
- The results showed that the CNNs performed well, achieving high accuracy in detecting conditions related to arthritis, which could lead to quicker and more standardized assessments in clinical settings.
Purpose: Ileo-anal pull through (IAPT) is a commonly performed operation for the surgical management of ulcerative colitis. The effect of body weight on outcomes for patients undergoing this operation has not been extensively studied.
Methods: This was a prospective cohort study at a single tertiary care inflammatory bowel disease (IBD) center.
Extreme events, such as those caused by climate change, economic or geopolitical shocks, and pest or disease epidemics, threaten global food security. The complexity of causation, as well as the myriad ways that an event, or a sequence of events, creates cascading and systemic impacts, poses significant challenges to food systems research and policy alike. To identify priority food security risks and research opportunities, we asked experts from a range of fields and geographies to describe key threats to global food security over the next two decades and to suggest key research questions and gaps on this topic.
View Article and Find Full Text PDFBackground: 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.