Quantification of mitral regurgitation: from traditional methods to artificial intelligence.
Authors
Affiliations (9)
Affiliations (9)
- The Baker Heart and Diabetes Research Institute, Melbourne, Australia.
- Cardiac Diagnostic Services Epworth Hospital, Melbourne, Australia.
- The Alfred Hospital, Melbourne, Australia.
- University of Melbourne, Melbourne, Australia.
- Philips, Cambridge, USA.
- Monash University, Melbourne, Australia.
- Cardiac Diagnostic Services Epworth Hospital, Melbourne, Australia. [email protected].
- The Alfred Hospital, Melbourne, Australia. [email protected].
- Heart Centre at the Alfred Hospital, 55 Commercial Road, Melbourne, 3004, Australia. [email protected].
Abstract
Mitral regurgitation (MR) is a common valvular disorder and associated with adverse outcomes. Echocardiography is the primary imaging modality for MR assessment; however, standard methods rely on geometric assumptions and single-frame analysis, which are especially inaccurate in the setting of eccentric, multiple or non-holosystolic jets. Recent developments in machine learning have enabled automated quantification of MR, which analyse regurgitant flow throughout systole, account for non-hemispheric orifice area and jet morphology, and demonstrate favourable agreement with cardiac magnetic resonance. In addition, AI capable of detecting and grading MR directly from echocardiographic clips offer potential utility for screening, particularly in low-resource settings where specialist review is limited. Quantification of Mitral Regurgitation: from traditional methods to Artificial Intelligence.