Automatic pericardium segmentation and quantification of epicardial fat from computed tomography angiography
Journal article, 2016

Recent findings indicate a strong correlation between the risk of future heart disease and the volume ofadipose tissue inside of the pericardium. So far, large-scale studies have been hindered by the fact that manual delin-eation of the pericardium is extremely time-consuming and that existing methods for automatic delineation strugglewith accuracy. In this paper, an efficient and fully automatic approach to pericardium segmentation and epicardial fatvolume estimation is presented, based on a variant of multi-atlas segmentation for spatial initialization and a randomforest classifier for accurate pericardium detection. Experimental validation on a set of 30 manually delineated Com-puter Tomography Angiography (CTA) volumes shows a significant improvement on state-of-the-art in terms of EFVestimation (mean absolute epicardial fat volume difference: 3.8 ml (4.7%), Pearson correlation: 0.99) with run-timessuitable for large-scale studies (52 s). Further, the results compare favorably to inter-observer variability measured on10 volumes.

pericardium

machine learning

epicardial fat quantification

segmentation

computed tomography angiography (CTA)

Author

Alexander Norlén

Chalmers, Signals and Systems, Signalbehandling och medicinsk teknik, Imaging and Image Analysis

Jennifer Alvén

Chalmers, Signals and Systems, Signalbehandling och medicinsk teknik, Imaging and Image Analysis

David Molnar

University of Gothenburg

Olof Enqvist

University of Gothenburg

Rauni Rossi-Norrlund

University of Gothenburg

John Brandberg

University of Gothenburg

Göran Bergström

University of Gothenburg

Fredrik Kahl

Chalmers, Signals and Systems, Signalbehandling och medicinsk teknik, Imaging and Image Analysis

Journal of Medical Imaging

2329-4310 (eISSN)

Vol. 3 3 Article number 034003-

Areas of Advance

Information and Communication Technology

Life Science Engineering

Subject Categories

Medical Engineering

Computer Vision and Robotics (Autonomous Systems)

Medical Image Processing

DOI

10.1117/1.JMI.3.3.034003

More information

Created

10/7/2017