Artificial intelligence based automatic quantification of epicardial adipose tissue suitable for large scale population studies

David Molnar,Olof Enqvist,John Brandberg,Johannes Ulén,Måns Larsson,Åse A Johnsson,Göran Bergström,Ola Hjelmgren,Elias Björnson

doi:10.1038/s41598-021-03150-w

Abstract

To develop a fully automatic model capable of reliably quantifying epicardial adipose tissue (EAT) volumes and attenuation in large scale population studies to investigate their relation to markers of cardiometabolic risk. Non-contrast cardiac CT images from the SCAPIS study were used to train and test a convolutional neural network based model to quantify EAT by: segmenting the pericardium, suppressing noise-induced artifacts in the heart chambers, and, if image sets were incomplete, imputing missing EAT volumes. The model achieved a mean Dice coefficient of 0.90 when tested against expert manual segmentations on 25 image sets. Tested on 1400 image sets, the model successfully segmented 99.4% of the cases. Automatic imputation of missing EAT volumes had an error of less than 3.1% with up to 20% of the slices in image sets missing. The most important predictors of EAT volumes were weight and waist, while EAT attenuation was predicted mainly by EAT volume. A model with excellent performance, capable of fully automatic handling of the most common challenges in large scale EAT quantification has been developed. In studies of the importance of EAT in disease development, the strong co-variation with anthropometric measures needs to be carefully considered.

Highlights

To develop a fully automatic model capable of reliably quantifying epicardial adipose tissue (EAT) volumes and attenuation in large scale population studies to investigate their relation to markers of cardiometabolic risk
All computed tomography (CT) imaging is subject to noise, which can cause both difficulties in delineating the pericardium and errors in the classification and quantification of EAT when thresholding is applied
For the estimation of EAT volume (EATV) we developed two convolutional neural network (CNN) models which work in series

Summary

Introduction

To develop a fully automatic model capable of reliably quantifying epicardial adipose tissue (EAT) volumes and attenuation in large scale population studies to investigate their relation to markers of cardiometabolic risk. Five of the featured works comprise small samples, in the range of 20–53 individuals, while two works have studied larger populations, both by Commandeur et al They describe a fully automated model based on a trained convolutional neural network (CNN)[21], which achieved a Dice coefficient of 0.82 for EATV. This model was later adapted for multi-center s tudies[23], where it was used for analysis of 776 cases and applied in a population based study[24] comprising 2068 individuals. A more sophisticated approach based on a CNN trained to identify anatomical regions devoid of adipose tissue would be preferable

Objectives

Methods

Discussion

Conclusion