SADiff: Coronary Artery Segmentation in CT Angiography Using Spatial Attention and Diffusion Model

Coronary artery disease (CAD) is a highly prevalent cardiovascular disease and one of the leading causes of death worldwide. The accurate segmentation of coronary arteries from CT angiography (CTA) images is essential for the diagnosis and treatment of coronary artery disease. However, due to small...

Full description

Saved in:
Bibliographic Details
Main Authors: Ruoxuan Xu, Longhui Dai, Jianru Wang, Lei Zhang, Yuanquan Wang
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Journal of Imaging
Subjects:
Online Access:https://www.mdpi.com/2313-433X/11/6/192
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849432775649656832
author Ruoxuan Xu
Longhui Dai
Jianru Wang
Lei Zhang
Yuanquan Wang
author_facet Ruoxuan Xu
Longhui Dai
Jianru Wang
Lei Zhang
Yuanquan Wang
author_sort Ruoxuan Xu
collection DOAJ
description Coronary artery disease (CAD) is a highly prevalent cardiovascular disease and one of the leading causes of death worldwide. The accurate segmentation of coronary arteries from CT angiography (CTA) images is essential for the diagnosis and treatment of coronary artery disease. However, due to small vessel diameters, large morphological variations, low contrast, and motion artifacts, conventional segmentation methods, including classical image processing (such as region growing and level sets) and early deep learning models with limited receptive fields, are unsatisfactory. We propose SADiff, a hybrid framework that integrates a dilated attention network (DAN) for ROI extraction, a diffusion-based subnet for noise suppression in low-contrast regions, and a striped attention network (SAN) to refine tubular structures affected by morphological variations. Experiments on the public ImageCAS dataset show that it has a Dice score of 83.48% and a Hausdorff distance of 19.43 mm, which is 6.57% higher than U-Net3D in terms of Dice. The cross-dataset validation on the private ImageLaPP dataset verifies its generalizability with a Dice score of 79.42%. This comprehensive evaluation demonstrates that SADiff provides a more efficient and versatile method for coronary segmentation and shows great potential for improving the diagnosis and treatment of CAD.
format Article
id doaj-art-20d9fd6fdb2a4e8bbc8b4bee245795a0
institution Kabale University
issn 2313-433X
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Journal of Imaging
spelling doaj-art-20d9fd6fdb2a4e8bbc8b4bee245795a02025-08-20T03:27:17ZengMDPI AGJournal of Imaging2313-433X2025-06-0111619210.3390/jimaging11060192SADiff: Coronary Artery Segmentation in CT Angiography Using Spatial Attention and Diffusion ModelRuoxuan Xu0Longhui Dai1Jianru Wang2Lei Zhang3Yuanquan Wang4School of Artificial Intelligence, Hebei University of Technology (HeBUT), Tianjin 300401, ChinaSchool of Artificial Intelligence, Hebei University of Technology (HeBUT), Tianjin 300401, ChinaSchool of Artificial Intelligence, Hebei University of Technology (HeBUT), Tianjin 300401, ChinaSchool of Artificial Intelligence, Hebei University of Technology (HeBUT), Tianjin 300401, ChinaSchool of Artificial Intelligence, Hebei University of Technology (HeBUT), Tianjin 300401, ChinaCoronary artery disease (CAD) is a highly prevalent cardiovascular disease and one of the leading causes of death worldwide. The accurate segmentation of coronary arteries from CT angiography (CTA) images is essential for the diagnosis and treatment of coronary artery disease. However, due to small vessel diameters, large morphological variations, low contrast, and motion artifacts, conventional segmentation methods, including classical image processing (such as region growing and level sets) and early deep learning models with limited receptive fields, are unsatisfactory. We propose SADiff, a hybrid framework that integrates a dilated attention network (DAN) for ROI extraction, a diffusion-based subnet for noise suppression in low-contrast regions, and a striped attention network (SAN) to refine tubular structures affected by morphological variations. Experiments on the public ImageCAS dataset show that it has a Dice score of 83.48% and a Hausdorff distance of 19.43 mm, which is 6.57% higher than U-Net3D in terms of Dice. The cross-dataset validation on the private ImageLaPP dataset verifies its generalizability with a Dice score of 79.42%. This comprehensive evaluation demonstrates that SADiff provides a more efficient and versatile method for coronary segmentation and shows great potential for improving the diagnosis and treatment of CAD.https://www.mdpi.com/2313-433X/11/6/192coronary arteryimage segmentationdiffusion modelmulti-scale spatial attention
spellingShingle Ruoxuan Xu
Longhui Dai
Jianru Wang
Lei Zhang
Yuanquan Wang
SADiff: Coronary Artery Segmentation in CT Angiography Using Spatial Attention and Diffusion Model
Journal of Imaging
coronary artery
image segmentation
diffusion model
multi-scale spatial attention
title SADiff: Coronary Artery Segmentation in CT Angiography Using Spatial Attention and Diffusion Model
title_full SADiff: Coronary Artery Segmentation in CT Angiography Using Spatial Attention and Diffusion Model
title_fullStr SADiff: Coronary Artery Segmentation in CT Angiography Using Spatial Attention and Diffusion Model
title_full_unstemmed SADiff: Coronary Artery Segmentation in CT Angiography Using Spatial Attention and Diffusion Model
title_short SADiff: Coronary Artery Segmentation in CT Angiography Using Spatial Attention and Diffusion Model
title_sort sadiff coronary artery segmentation in ct angiography using spatial attention and diffusion model
topic coronary artery
image segmentation
diffusion model
multi-scale spatial attention
url https://www.mdpi.com/2313-433X/11/6/192
work_keys_str_mv AT ruoxuanxu sadiffcoronaryarterysegmentationinctangiographyusingspatialattentionanddiffusionmodel
AT longhuidai sadiffcoronaryarterysegmentationinctangiographyusingspatialattentionanddiffusionmodel
AT jianruwang sadiffcoronaryarterysegmentationinctangiographyusingspatialattentionanddiffusionmodel
AT leizhang sadiffcoronaryarterysegmentationinctangiographyusingspatialattentionanddiffusionmodel
AT yuanquanwang sadiffcoronaryarterysegmentationinctangiographyusingspatialattentionanddiffusionmodel