Validation of a deep learning approach for epicardial adipose tissue segmentation in computed tomography.
Authors
Affiliations (7)
Affiliations (7)
- Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), Rua Dr Roberto Frias, Porto, 4200-465, Portugal. [email protected].
- Faculty of Engineering University of Porto (FEUP), Porto, Portugal. [email protected].
- Faculty of Medicine University of Porto (FMUP), Porto, Portugal.
- Unidade Local de Saúde de Gaia e Espinho (ULSGE), Vila Nova de Gaia, Portugal.
- Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), Rua Dr Roberto Frias, Porto, 4200-465, Portugal.
- Faculty of Science University of Porto (FCUP), Porto, Portugal.
- Faculty of Engineering University of Porto (FEUP), Porto, Portugal.
Abstract
The link between epicardial adipose tissue (EAT) and cardiovascular risk is well established, with EAT volume being strongly associated with inflammation, coronary artery disease (CAD) risk, and mortality. However, its EAT quantification is hindered by the time-consuming nature of manual EAT segmentation in cardiac computed tomography (CT). 300 non-contrast cardiac CT scans were collected and the pericardium was manually delineated. In a subset of this data (N = 30), manual delineation was repeated by the same operator and by a second operator. Two automatic methods were then used for pericardial segmentation: a commercially available tool, Siemens Cardiac Risk Assessment (CRA) software; and a deep learning solution based on a U-Net architecture trained exclusively with external public datasets (CardiacFat and OSIC). EAT segmentations were obtained through thresholding to [- 150,- 50] Hounsfield units. Pericardial and EAT segmentation performance was evaluated considering the segmentations by the first operator as reference. Statistical significance of differences for all metrics and segmentation methods was tested through Student t-tests. Pericardial segmentation intra-/interobserver variability was excellent, with the U-Net outperforming Siemens CRA (p < 0.0001). The intra- and interobserver agreement for EAT segmentation was lower with Dice Scores (DSC) of 0.862 and 0.775 respectively, while the U-Net and Siemens CRA obtained DSCs of 0.723 and 0.679 respectively. EAT volume quantification showed that the agreement between a human observer and the U-Net was better than that of two human observers (p = 0.0141), with a Pearson Correlation Coefficient (PCC) of 0.896 and a bias of - 2.83 cm<sup>3</sup> (below the interobserver bias of 9.05 cm3). The lower performances of EAT segmentation highlight the difficulty in segmenting this structure. For both pericardial and EAT segmentation, the deep learning method outperformed the commercial solution. While the segmentation performance of the U-Net solution was below interobserver variability, EAT volume quantification performance was competitive with human readers, motivating future use of these tools.Clinical trial number: NCT03280433, registered retrospectively on 2017-09-08.