Publications by authors named "S M Niehues"
Purpose To develop and evaluate a publicly available deep learning model for segmenting and classifying cardiac implantable electronic devices (CIEDs) on Digital Imaging and Communications in Medicine (DICOM) and smartphone-based chest radiographs. Materials and Methods This institutional review board-approved retrospective study included patients with implantable pacemakers, cardioverter defibrillators, cardiac resynchronization therapy devices, and cardiac monitors who underwent chest radiography between January 2012 and January 2022. A U-Net model with a ResNet-50 backbone was created to classify CIEDs on DICOM and smartphone images.
View Article and Find Full Text PDFArticle Synopsis
- The study aimed to explore computed tomography-based thermography (CTT) for predicting ablation zones during microwave ablation (MWA) in a porcine liver model.
- CTT effectively visualized ablation zones, showing a significant correlation between CT attenuation values and temperature changes, implying that the technique can be used to accurately assess treatment areas.
- The findings suggest that CTT could be beneficial in clinical settings to improve patient outcomes and potentially reduce the risk of local cancer recurrence.
Article Synopsis
- Computed tomography-based Thermography (CTT) is being explored as a non-invasive way to monitor temperature during ablation procedures, but it faces challenges from inter-scan motion artifacts that require registration.
- The study analyzed different registration algorithms to minimize these artifacts during microwave ablation of liver tissue in a porcine model, using feedback from 15 radiologists to assess effectiveness.
- Results indicated that combined registration methods were more effective at reducing ablation probe movement compared to using a single registration method, highlighting the importance of proper registration in these procedures.