Search results for "Infarctus"
showing 2 items of 12 documents
Deep learning architectures for automatic detection of viable myocardiac segments
2021
Thesis abstract: Deep learning architectures for automatic detection of viable myocardiac segmentsAccurate myocardial segmentation in LGE-MRI is an important purpose for diagnosis assistance of infarcted patients. Nevertheless, manual delineation of target volumes is time-consuming and depends on intra- and inter-observer variability. This thesis aims at developing efficient deep learning-based methods for automatically segmenting myocardial tissues (healthy myocardium, myocardial infarction, and microvascular obstruction) on LGE-MRI. In this regard, we first proposed a 2.5D SegU-Net model based on a fusion framework (U-Net and SegNet) to learn different feature representations adaptively. …
In-hospital outcomes and 5-year mortality following an acute myocardial infarction in patients with a history of cancer: Results from the French regi…
2019
Summary Background Cancer and acute myocardial infarction (AMI) have important prognostic consequences. Treatment of some cancers may affect coronary artery disease, myocardial function and/or AMI management. Whether the early and long-term mortality of patients with AMI differ according to their history of cancer remains questionable. Aims To determine in-hospital outcomes and 5-year mortality following AMI according to patient history of cancer. Methods The FAST-MI registry is a nationwide French survey collecting data on characteristics, management and outcomes of 3670 consecutive patients admitted for AMI during October 2005. Results Overall, 246/3664 patients (6.7%) admitted for an AMI…