Cardiac image analysis with deep learning methods
Radiological Society of North America (RSNA) 104th Scientific Assembly and Annual Meeting, Digital Education Exhibit
Abstract
An abstract is not available in the lab archive. View the paper at its source.
This RSNA 2018 digital education exhibit surveyed deep learning methods and cardiac imaging applications, including analysis of the ventricles, myocardium, left atrium, pulmonary veins and coronary arteries. Its outline also addressed challenges such as data scarcity and annotation.
Summary
Presented as digital education exhibit CA155-ED-X at the Radiological Society of North America’s 104th Scientific Assembly and Annual Meeting, held November 25–30, 2018, in Chicago, this contribution was an educational overview rather than a report of a single evaluated study. The RSNA program lists Aliasghar Mortazi as presenter and Georgios Z. Papadakis, Uygar Teomete and Ulas Bagci as co-authors. Its outline covers deep learning methods and applications across cardiac imaging, and identifies challenges including disease diversity, data scarcity, annotation and motion correctness. The source does not report a specific dataset, quantitative evaluation or clinical validation. View the RSNA program entry.
Cite this work
Aliasghar Mortazi; Georgios Z. Papadakis; Uygar Teomete; Ulas Bagci (2018). Cardiac image analysis with deep learning methods. Radiological Society of North America (RSNA) 104th Scientific Assembly and Annual Meeting, Digital Education Exhibit https://archive.rsna.org/2018/ArtificialIntelligence.pdf
BibTeX