AI-Driven segmentation and morphogeometric profiling of epicardial adipose tissue in type 2 diabetes

Abstract Background Epicardial adipose tissue (EAT) is associated with cardiometabolic risk in type 2 diabetes (T2D), but its spatial distribution and structural alterations remain understudied. We aim to develop a shape-aware, AI-based method for automated segmentation and morphogeometric analysis...

Full description

Saved in:
Bibliographic Details
Main Authors: Fan Feng, Abdallah I. Hasaballa, Ting Long, Xinyi Sun, Justin Fernandez, Carl-Johan Carlhäll, Jichao Zhao
Format: Article
Language:English
Published: BMC 2025-07-01
Series:Cardiovascular Diabetology
Subjects:
Online Access:https://doi.org/10.1186/s12933-025-02829-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849238030508883968
author Fan Feng
Abdallah I. Hasaballa
Ting Long
Xinyi Sun
Justin Fernandez
Carl-Johan Carlhäll
Jichao Zhao
author_facet Fan Feng
Abdallah I. Hasaballa
Ting Long
Xinyi Sun
Justin Fernandez
Carl-Johan Carlhäll
Jichao Zhao
author_sort Fan Feng
collection DOAJ
description Abstract Background Epicardial adipose tissue (EAT) is associated with cardiometabolic risk in type 2 diabetes (T2D), but its spatial distribution and structural alterations remain understudied. We aim to develop a shape-aware, AI-based method for automated segmentation and morphogeometric analysis of EAT in T2D. Methods A total of 90 participants (45 with T2D and 45 age-, sex-matched controls) underwent cardiac 3D Dixon MRI, enrolled between 2014 and 2018 as part of the sub-study of the Swedish SCAPIS cohort. We developed EAT-Seg, a multi-modal deep learning model incorporating signed distance maps (SDMs) for shape-aware segmentation. Segmentation performance was evaluated using the Dice similarity coefficient (DSC), the 95% Hausdorff distance (HD95), and the average symmetric surface distance (ASSD). Statistical shape analysis combined with partial least squares discriminant analysis (PLS-DA) was applied to point cloud representations of EAT to capture latent spatial variations between groups. Morphogeometric features, including volume, 3D local thickness map, elongation and fragmentation index, were extracted and correlated with PLS-DA latent variables using Pearson correlation. Features with high-correlation were identified as key differentiators and evaluated using a Random Forest classifier. Results EAT-Seg achieved a DSC of 0.881, a HD95 of 3.213 mm, and an ASSD of 0.602 mm. Statistical shape analysis revealed spatial distribution differences in EAT between T2D and control groups. Morphogeometric feature analysis identified volume and thickness gradient-related features as key discriminators (r > 0.8, P < 0.05). Random Forest classification achieved an AUC of 0.703. Conclusions This AI-based framework enables accurate segmentation for structurally complex EAT and reveals key morphogeometric differences associated with T2D, supporting its potential as a biomarker for cardiometabolic risk assessment. Graphical abstract
format Article
id doaj-art-e5b7f68121e143f4b720447f852eb3df
institution Kabale University
issn 1475-2840
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series Cardiovascular Diabetology
spelling doaj-art-e5b7f68121e143f4b720447f852eb3df2025-08-20T04:01:47ZengBMCCardiovascular Diabetology1475-28402025-07-0124111410.1186/s12933-025-02829-yAI-Driven segmentation and morphogeometric profiling of epicardial adipose tissue in type 2 diabetesFan Feng0Abdallah I. Hasaballa1Ting Long2Xinyi Sun3Justin Fernandez4Carl-Johan Carlhäll5Jichao Zhao6Auckland Bioengineering Institute, The University of AucklandDepartment of Computer Science, University of OxfordAuckland Bioengineering Institute, The University of AucklandFaculty of Medical and Health Sciences, School of Medicine, The University of AucklandAuckland Bioengineering Institute, The University of AucklandCenter for Medical Image Science and Visualization (CMIV), Linköping UniversityAuckland Bioengineering Institute, The University of AucklandAbstract Background Epicardial adipose tissue (EAT) is associated with cardiometabolic risk in type 2 diabetes (T2D), but its spatial distribution and structural alterations remain understudied. We aim to develop a shape-aware, AI-based method for automated segmentation and morphogeometric analysis of EAT in T2D. Methods A total of 90 participants (45 with T2D and 45 age-, sex-matched controls) underwent cardiac 3D Dixon MRI, enrolled between 2014 and 2018 as part of the sub-study of the Swedish SCAPIS cohort. We developed EAT-Seg, a multi-modal deep learning model incorporating signed distance maps (SDMs) for shape-aware segmentation. Segmentation performance was evaluated using the Dice similarity coefficient (DSC), the 95% Hausdorff distance (HD95), and the average symmetric surface distance (ASSD). Statistical shape analysis combined with partial least squares discriminant analysis (PLS-DA) was applied to point cloud representations of EAT to capture latent spatial variations between groups. Morphogeometric features, including volume, 3D local thickness map, elongation and fragmentation index, were extracted and correlated with PLS-DA latent variables using Pearson correlation. Features with high-correlation were identified as key differentiators and evaluated using a Random Forest classifier. Results EAT-Seg achieved a DSC of 0.881, a HD95 of 3.213 mm, and an ASSD of 0.602 mm. Statistical shape analysis revealed spatial distribution differences in EAT between T2D and control groups. Morphogeometric feature analysis identified volume and thickness gradient-related features as key discriminators (r > 0.8, P < 0.05). Random Forest classification achieved an AUC of 0.703. Conclusions This AI-based framework enables accurate segmentation for structurally complex EAT and reveals key morphogeometric differences associated with T2D, supporting its potential as a biomarker for cardiometabolic risk assessment. Graphical abstracthttps://doi.org/10.1186/s12933-025-02829-yEpicardial adipose tissueType 2 diabetesMRIMulti-modal deep learningStatistical shape analysis
spellingShingle Fan Feng
Abdallah I. Hasaballa
Ting Long
Xinyi Sun
Justin Fernandez
Carl-Johan Carlhäll
Jichao Zhao
AI-Driven segmentation and morphogeometric profiling of epicardial adipose tissue in type 2 diabetes
Cardiovascular Diabetology
Epicardial adipose tissue
Type 2 diabetes
MRI
Multi-modal deep learning
Statistical shape analysis
title AI-Driven segmentation and morphogeometric profiling of epicardial adipose tissue in type 2 diabetes
title_full AI-Driven segmentation and morphogeometric profiling of epicardial adipose tissue in type 2 diabetes
title_fullStr AI-Driven segmentation and morphogeometric profiling of epicardial adipose tissue in type 2 diabetes
title_full_unstemmed AI-Driven segmentation and morphogeometric profiling of epicardial adipose tissue in type 2 diabetes
title_short AI-Driven segmentation and morphogeometric profiling of epicardial adipose tissue in type 2 diabetes
title_sort ai driven segmentation and morphogeometric profiling of epicardial adipose tissue in type 2 diabetes
topic Epicardial adipose tissue
Type 2 diabetes
MRI
Multi-modal deep learning
Statistical shape analysis
url https://doi.org/10.1186/s12933-025-02829-y
work_keys_str_mv AT fanfeng aidrivensegmentationandmorphogeometricprofilingofepicardialadiposetissueintype2diabetes
AT abdallahihasaballa aidrivensegmentationandmorphogeometricprofilingofepicardialadiposetissueintype2diabetes
AT tinglong aidrivensegmentationandmorphogeometricprofilingofepicardialadiposetissueintype2diabetes
AT xinyisun aidrivensegmentationandmorphogeometricprofilingofepicardialadiposetissueintype2diabetes
AT justinfernandez aidrivensegmentationandmorphogeometricprofilingofepicardialadiposetissueintype2diabetes
AT carljohancarlhall aidrivensegmentationandmorphogeometricprofilingofepicardialadiposetissueintype2diabetes
AT jichaozhao aidrivensegmentationandmorphogeometricprofilingofepicardialadiposetissueintype2diabetes