Machine Learning in Cardiac CT

AbstractPurpose of ReviewThis review covers the basic principles of machine learning (ML) and current applications in the subspecialty of cardiac imaging at computed tomography in diagnostic radiology.Recent FindingsThis review covers recent publications for automated image processing, diagnostic and prognostic support, as well as novel integrations of ML into extant imaging applications in advanced cardiac computed tomography. Where available, ML algorithms are compared to current gold standards and descriptions of the nature and value of the advances are described.SummaryMachine learning in clinical imaging is considered by many to represent one of the most promising areas of research and development in diagnostic radiology. Sophisticated Machine Learning systems like IBM ’s Watson have captured the public’s attention in their ability to mimic human capacity for pattern recognition in extremely large data sets. There are numerous recent research publications utilizing Machine Learning algorithms to either automate processes or improve diagnosis or even create ent irely new forms of evaluation previously considered out of reach for cardiac CT imaging.
Source: Current Radiology Reports - Category: Radiology Source Type: research