Imperial College London
Portrait Picture

DrGrahamCole

Faculty of Medicine, National Heart & Lung Institute

Honorary Clinical Senior Lecturer
 
 
 
//

Contact

 

g.cole

 
 
//

Location

 

ICTEM buildingHammersmith Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Li:2022:10.1007/978-3-031-23443-9_33,
author = {Li, Z and Petri, C and Howard, J and Cole, G and Varela, M},
doi = {10.1007/978-3-031-23443-9_33},
pages = {359--368},
publisher = {Springer Nature Switzerland},
title = {PAT-CNN: automatic segmentation and quantification of pericardial adipose tissue from t2-weighted cardiac magnetic resonance images},
url = {http://dx.doi.org/10.1007/978-3-031-23443-9_33},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Background: Increased pericardial adipose tissue (PAT) is associated with many types of cardiovascular disease (CVD). Although cardiac magnetic resonance images (CMRI) are often acquired in patients with CVD, there are currently no tools to automatically identify and quantify PAT from CMRI. The aim of this study was to create a neural network to segment PAT from T2-weighted CMRI and explore the correlations between PAT volumes (PATV) and CVD outcomes and mortality.Methods: We trained and tested a deep learning model, PAT-CNN, to segment PAT on T2-weighted cardiac MR images. Using the segmentations from PAT-CNN, we automatically calculated PATV on images from 391 patients. We analysed correlations between PATV and CVD diagnosis and 1-year mortality post-imaging.Results: PAT-CNN was able to accurately segment PAT with Dice score/ Hausdorff distances of 0.74 ± 0.03/27.1 ± 10.9 mm, similar to the values obtained when comparing the segmentations of two independent human observers (0.76 ± 0.06/21.2 ± 10.3 mm). Regression models showed that, independently of sex and body-mass index, PATV is significantly positively correlated with a diagnosis of CVD and with 1-year all cause mortality (p-value < 0.01).Conclusions: PAT-CNN can segment PAT from T2-weighted CMR images automatically and accurately. Increased PATV as measured automatically from CMRI is significantly associated with the presence of CVD and can independently predict 1-year mortality.
AU  - Li,Z
AU  - Petri,C
AU  - Howard,J
AU  - Cole,G
AU  - Varela,M
DO  - 10.1007/978-3-031-23443-9_33
EP  - 368
PB  - Springer Nature Switzerland
PY  - 2022///
SN  - 0302-9743
SP  - 359
TI  - PAT-CNN: automatic segmentation and quantification of pericardial adipose tissue from t2-weighted cardiac magnetic resonance images
UR  - http://dx.doi.org/10.1007/978-3-031-23443-9_33
UR  - https://link.springer.com/chapter/10.1007/978-3-031-23443-9_33
UR  - http://hdl.handle.net/10044/1/103882
ER  -
Download