Back to Search
Start Over
Using Anatomic Intelligence to Localize Mitral Valve Prolapse on Three-Dimensional Echocardiography.
- Source :
-
Journal of the American Society of Echocardiography : official publication of the American Society of Echocardiography [J Am Soc Echocardiogr] 2016 Oct; Vol. 29 (10), pp. 938-945. Date of Electronic Publication: 2016 Aug 18. - Publication Year :
- 2016
-
Abstract
- Background: Accurate localization of mitral valve prolapse (MVP) is crucial for surgical planning. Despite improved visualization of the mitral valve by three-dimensional transesophageal echocardiography, image interpretation remains expertise dependent. Manual construction of mitral valve topographic maps improves diagnostic accuracy but is time-consuming and requires substantial manual input. A novel computer-learning technique called Anatomical Intelligence in ultrasound (AIUS) semiautomatically tracks the annulus and leaflet anatomy for parametric analysis. The aims of this study were to examine whether AIUS could improve accuracy and efficiency in localizing MVP among operators with different levels of experience.<br />Methods: Two experts and four intermediate-level echocardiographers (nonexperts) retrospectively performed analysis of three-dimensional transesophageal echocardiographic images to generate topographic mitral valve models in 90 patients with degenerative MVP. All echocardiographers performed both AIUS and manual segmentation in sequential weekly sessions. The results were compared with surgical findings.<br />Results: Manual segmentation by nonexperts had significantly lower sensitivity (60% vs 90%, P < .001), specificity (91% vs 97%, P = .001), and accuracy (83% vs 95%, P < .001) compared with experts. AIUS significantly improved the accuracy of nonexperts (from 83% to 89%, P = .003), particularly for lesions involving the A3 (from 81% to 94%, P = .006) and P1 (from 78% to 88%, P = .001) segments, presumably related to anatomic variants of the annulus that made tracking more challenging. AIUS required significantly less time for image analysis by both experts (1.9 ± 0.7 vs 9.9 ± 3.5 min, P < .0001) and nonexperts (5.0 ± 0.5 vs 13 ± 1.5 min, P < .0001), especially for complex lesions.<br />Conclusions: Anatomic assessment of mitral valve pathology by three-dimensional transesophageal echocardiography is experience dependent. A semiautomated algorithm using AIUS improves accuracy and efficiency in localizing MVP by less experienced operators.<br /> (Copyright © 2016 American Society of Echocardiography. Published by Elsevier Inc. All rights reserved.)
- Subjects :
- Algorithms
Female
Humans
Image Enhancement methods
Male
Middle Aged
Reproducibility of Results
Sensitivity and Specificity
Echocardiography, Three-Dimensional methods
Image Interpretation, Computer-Assisted methods
Machine Learning
Mitral Valve Prolapse diagnostic imaging
Mitral Valve Prolapse pathology
Pattern Recognition, Automated methods
Subjects
Details
- Language :
- English
- ISSN :
- 1097-6795
- Volume :
- 29
- Issue :
- 10
- Database :
- MEDLINE
- Journal :
- Journal of the American Society of Echocardiography : official publication of the American Society of Echocardiography
- Publication Type :
- Academic Journal
- Accession number :
- 27545445
- Full Text :
- https://doi.org/10.1016/j.echo.2016.07.002