Computer aided diagnostics often requires analysis of a region of interest (ROI) within a radiology scan, and the ROI may be an organ or a suborgan. Although deep learning algorithms have the ability to outperform other methods, they rely on the availability of a large amount of annotated data. Motivated by the need to address this limitation, an approach to localisation and detection of multiple organs based on supervised and semi-supervised learning is presented here.
View Article and Find Full Text PDFAnticoagulation with unfractionated heparin has been the standard of care for more than a half-century for patients undergoing cardiac surgery. The risk of heparin-induced adverse reactions dictates the need for a safe and effective alternative, particularly in off-pump coronary artery bypass (OPCAB) surgery, an approach associated with a perioperative prothrombotic condition that may negatively influence graft patency. Between March 2003 and January 2005, 243 consecutive patients underwent OPCAB with bivalirudin (0.
View Article and Find Full Text PDF