Abstract
The ability to extract and quantify three-dimensional (3D) morphological parameters of the mitral valve (MV) apparatus from transesophageal 3D echocardiographic (T3DE) imaging constitutes a valuable tool in diagnosis, treatment and follow-up of patients with MV disease. Mitral annulus (MA) and leaflets (ML) quantification is still challenging, and commonly based on intensive user interaction that limits its applicability. We proposed a fast and accurate model-free, nearly-automated method for segmenting and extracting MA and ML morphological parameters, requiring a set of only 8 user-defined points. The algorithm accuracy was tested on 12 patients compared to 'gold standard' manual analysis, resulting in narrow limits of agreement, and good inter- and intra-observer variability, except for MA height computation. The proposed technique appears promising for clinical application.
Original language | English |
---|---|
Title of host publication | Computing in Cardiology |
Pages | 145-148 |
Number of pages | 4 |
Volume | 39 |
Publication status | Published - 2012 |
Event | 39th Computing in Cardiology Conference, CinC 2012 - Krakow, Poland Duration: Sep 9 2012 → Sep 12 2012 |
Other
Other | 39th Computing in Cardiology Conference, CinC 2012 |
---|---|
Country/Territory | Poland |
City | Krakow |
Period | 9/9/12 → 9/12/12 |
ASJC Scopus subject areas
- Cardiology and Cardiovascular Medicine
- Computer Science(all)