Automated segmentation of cardiac adipose tissue in Dixon magnetic resonance images

Abstract

Objective: Increasing evidence suggests a strong link between excess cardiac adipose tissue (CAT) and the risk of a cardiovascular event. Multi-echo Dixon magnetic resonance imaging (MRI), providing fat-only and water-only images, is a useful tool for quantification but requires the segmentation of CAT from a large number of images. The intent of this study was to evaluate an automated technique for CAT segmentation from Dixon MRI by comparing the contours identified by the automated algorithm to those manually traced by an observer.Methods: An automated segmentation algorithm, based on optimal thresholds and custom morphological processing, was applied to the registered fat-only and water-only images to identify CAT in the volume scans. CAT contours in 446 images, from 10 MRI scans, were selected for validation analysis. Cross-sectional area (CSA) and volume were computed and compared using Bland-Altman analysis. In addition, Hausdorff distance and Dice Similarity Coefficient (DSC) were used for assessment.Results: Linear regression analysis yielded correlation of R 2 = 0.381 for CSA and R 2 = 0.879 for volume. When compared to the observer, the computer algorithm under-estimated CSA by 27.5 ± 40.0% and volume by 26.4 ± 10.4%. The average bidirectional Hausdorff distance was 26.2 ± 16.0 mm while the average unidirectional Hausdorff distances were 24.5 ± 15.7 mm and 12.4 ± 11.7 mm. The average DSC was 0.561 ± 0.100. The time required for manual tracing was 15.84 ± 3.73 min and the time required for the computer algorithm was 2.81 ± 0.12 min. Conclusions:This study provided a technique, faster and less tedious than manual tracing (p < 0.00001), for quantification of CAT in Dixon MRI data, demonstrating feasibility of this approach for cardiac risk stratification.

Lower limb in sprinters with larger relative mass but not larger normalized moment of inertia

“…To create a temporal body mask, we first created fat-only and water-only temporal binary images using a low intensity threshold. These binary images were added together, and the temporal body mask was defined by filling any internal holes in the added masks based on a binary morphology operation (Klingensmith et al, 2017). After creating the temporal body mask, we removed the pixel intensity in the unwanted areas (other than the range of interest, such as the part of the opposite leg segment included in the image).…”

“…The threshold for the foreground and background signal intensity of each of the fat-only and water-only images was determined using Otsu’s method (Otsu, 1996), which created water-binary and fat-binary images. We created a definitive body mask by adding the two masks together and filling any internal holes with a binary morphology operation (Klingensmith et al, 2017). We classified each pixel as a fat tissue, lean (muscle or skin) tissue, or a background using water- and fat-binary images.…”

“…These binary images were added together, and the temporal body mask was defined by filling any internal holes in the added masks based on a binary morphology operation (Klingensmith et al, 2017).…”

Three-dimensional modeling and assessment of cardiac adipose tissue distribution.

“…Briefly, the MRI volumes were analyzed in three main steps: (1) rectification of the volumes from the 2 coils, (2) labeling of anatomical landmarks to facilitate segmentation, and (3) a sequential segmentation of anatomical structures and ectopic fat depots. Details of the algorithm are described in previous work [17] . It provides segmentation of both the heart and the cardiac fat.…”

“…In addition, automated and semi-automated algorithms have been developed to assess CAT volume from cardiac MRI, aiding in the cumbersome process of analyzing the large number of images involved with the 3D scans [15,16] . In a previous study, our group has also worked to develop and test an automated segmentation algorithm to identify the CAT in 3D Dixon MRI images [17] . In addition, the shape of cardiac structures has been investigated extensively.…”