Related Experiment Video
Updated: Jun 8, 2026
Anatomical Reconstructions of the Human Cardiac Venous System using Contrast-computed Tomography of Perfusion-fixed Specimens
Published on: April 18, 2013
Automated algorithm for atlas-based segmentation of the heart and pericardium from non-contrast CT
Damini Dey1, Amit Ramesh, Piotr J Slomka
1Departments of Imaging and Medicine, Cedars Sinai Medical Center, Los Angeles, CA.
Insights
An automated atlas-based algorithm efficiently segments the heart and pericardium from non-contrast CT scans. This method provides accurate cardiac region segmentation, crucial for calcium and fat quantification.
Area of Science:
- Medical Imaging
- Computational Anatomy
- Radiology
Background:
- Accurate segmentation of the heart and pericardium from non-contrast CT is essential for quantifying coronary calcium and pericardial fat.
- Existing methods may be time-consuming or lack efficiency.
Purpose of the Study:
- To develop and validate an automated, efficient atlas-based algorithm for segmenting the heart and pericardium from non-contrast CT data.
Main Methods:
- Creation of a co-registered non-contrast CT atlas from manually segmented data.
- Iterative affine and deformable (iterative demons algorithm) registration for atlas creation.
- Voxel classification using a weighted decision function for segmenting new CT datasets.
Main Results:
- The algorithm's cardiac region volume (609.0 ± 39.8 cc) was not significantly different from expert quantification (624.4 ± 38.4 cc) (p=0.1).
- Excellent correlation (r=0.98, p<0.0001) and a mean voxel overlap of 0.89 (range 0.86-0.91) were achieved.
- Segmentation was completed in under 45 seconds on a standard computer.
Conclusions:
- Fast, robust, and automated atlas-based segmentation of the heart and pericardium from non-contrast CT is feasible.
- This algorithm offers an efficient solution for pre-processing CT data for cardiac analysis.
Abstract:
Automated segmentation of the 3D heart region from non-contrast CT is a pre-requisite for automated quantification of coronary calcium and pericardial fat. We aimed to develop and validate an automated, efficient atlas-based algorithm for segmentation of the heart and pericardium from non-contrast CT.A co-registered non-contrast CT atlas is first created from multiple manually segmented non-contrast CT data. Non-contrast CT data included in the atlas are co-registered to each other using iterative affine registration, followed by a deformable transformation using the iterative demons algorithm; the final transformation is also applied to the segmented masks. New CT datasets are segmented by first co-registering to an atlas image, and by voxel classification using a weighted decision function applied to all co-registered/pre-segmented atlas images. This automated segmentation method was applied to 12 CT datasets, with a co-registered atlas created from 8 datasets. Algorithm performance was compared to expert manual quantification.Cardiac region volume quantified by the algorithm (609.0 ± 39.8 cc) and the expert (624.4 ± 38.4 cc) were not significantly different (p=0.1, mean percent difference 3.8 ± 3.0%) and showed excellent correlation (r=0.98, p<0.0001). The algorithm achieved a mean voxel overlap of 0.89 (range 0.86-0.91). The total time was <45 sec on a standard windows computer (100 iterations). Fast robust automated atlas-based segmentation of the heart and pericardium from non-contrast CT is feasible.
