Optimizing ensemble U-Net architectures for robust coronary vessel segmentation in angiographic images

Abstract Automated coronary angiography assessment requires precise vessel segmentation, a task complicated by uneven contrast filling and background noise. Our research introduces an ensemble U-Net model, SE-RegUNet, designed to accurately segment coronary vessels using 100 labeled angiographies fr...

Full description

Saved in:
Bibliographic Details
Main Authors: Shih-Sheng Chang, Ching-Ting Lin, Wei-Chun Wang, Kai-Cheng Hsu, Ya-Lun Wu, Chia-Hao Liu, Yang C. Fann
Format: Article
Language:English
Published: Nature Portfolio 2024-03-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-024-57198-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850172363243520000
author Shih-Sheng Chang
Ching-Ting Lin
Wei-Chun Wang
Kai-Cheng Hsu
Ya-Lun Wu
Chia-Hao Liu
Yang C. Fann
author_facet Shih-Sheng Chang
Ching-Ting Lin
Wei-Chun Wang
Kai-Cheng Hsu
Ya-Lun Wu
Chia-Hao Liu
Yang C. Fann
author_sort Shih-Sheng Chang
collection DOAJ
description Abstract Automated coronary angiography assessment requires precise vessel segmentation, a task complicated by uneven contrast filling and background noise. Our research introduces an ensemble U-Net model, SE-RegUNet, designed to accurately segment coronary vessels using 100 labeled angiographies from angiographic images. SE-RegUNet incorporates RegNet encoders and squeeze-and-excitation blocks to enhance feature extraction. A dual-phase image preprocessing strategy further improves the model's performance, employing unsharp masking and contrast-limited adaptive histogram equalization. Following fivefold cross-validation and Ranger21 optimization, the SE-RegUNet 4GF model emerged as the most effective, evidenced by performance metrics such as a Dice score of 0.72 and an accuracy of 0.97. Its potential for real-world application is highlighted by its ability to process images at 41.6 frames per second. External validation on the DCA1 dataset demonstrated the model's consistent robustness, achieving a Dice score of 0.76 and an accuracy of 0.97. The SE-RegUNet 4GF model's precision in segmenting blood vessels in coronary angiographies showcases its remarkable efficiency and accuracy. However, further development and clinical testing are necessary before it can be routinely implemented in medical practice.
format Article
id doaj-art-dc7222da7b2c4dfe8c3ef3a8d9183d2e
institution OA Journals
issn 2045-2322
language English
publishDate 2024-03-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-dc7222da7b2c4dfe8c3ef3a8d9183d2e2025-08-20T02:20:06ZengNature PortfolioScientific Reports2045-23222024-03-0114111110.1038/s41598-024-57198-5Optimizing ensemble U-Net architectures for robust coronary vessel segmentation in angiographic imagesShih-Sheng Chang0Ching-Ting Lin1Wei-Chun Wang2Kai-Cheng Hsu3Ya-Lun Wu4Chia-Hao Liu5Yang C. Fann6Division of Cardiovascular Medicine, China Medical University HospitalArtificial Intelligence Center, China Medical University HospitalDepartment of Neurology, China Medical University HospitalArtificial Intelligence Center, China Medical University HospitalArtificial Intelligence Center, China Medical University HospitalDivision of Cardiovascular Medicine, China Medical University HospitalDivision of Intramural Research, National Institute of Neurological Disorders and Stroke, National Institutes of HealthAbstract Automated coronary angiography assessment requires precise vessel segmentation, a task complicated by uneven contrast filling and background noise. Our research introduces an ensemble U-Net model, SE-RegUNet, designed to accurately segment coronary vessels using 100 labeled angiographies from angiographic images. SE-RegUNet incorporates RegNet encoders and squeeze-and-excitation blocks to enhance feature extraction. A dual-phase image preprocessing strategy further improves the model's performance, employing unsharp masking and contrast-limited adaptive histogram equalization. Following fivefold cross-validation and Ranger21 optimization, the SE-RegUNet 4GF model emerged as the most effective, evidenced by performance metrics such as a Dice score of 0.72 and an accuracy of 0.97. Its potential for real-world application is highlighted by its ability to process images at 41.6 frames per second. External validation on the DCA1 dataset demonstrated the model's consistent robustness, achieving a Dice score of 0.76 and an accuracy of 0.97. The SE-RegUNet 4GF model's precision in segmenting blood vessels in coronary angiographies showcases its remarkable efficiency and accuracy. However, further development and clinical testing are necessary before it can be routinely implemented in medical practice.https://doi.org/10.1038/s41598-024-57198-5
spellingShingle Shih-Sheng Chang
Ching-Ting Lin
Wei-Chun Wang
Kai-Cheng Hsu
Ya-Lun Wu
Chia-Hao Liu
Yang C. Fann
Optimizing ensemble U-Net architectures for robust coronary vessel segmentation in angiographic images
Scientific Reports
title Optimizing ensemble U-Net architectures for robust coronary vessel segmentation in angiographic images
title_full Optimizing ensemble U-Net architectures for robust coronary vessel segmentation in angiographic images
title_fullStr Optimizing ensemble U-Net architectures for robust coronary vessel segmentation in angiographic images
title_full_unstemmed Optimizing ensemble U-Net architectures for robust coronary vessel segmentation in angiographic images
title_short Optimizing ensemble U-Net architectures for robust coronary vessel segmentation in angiographic images
title_sort optimizing ensemble u net architectures for robust coronary vessel segmentation in angiographic images
url https://doi.org/10.1038/s41598-024-57198-5
work_keys_str_mv AT shihshengchang optimizingensembleunetarchitecturesforrobustcoronaryvesselsegmentationinangiographicimages
AT chingtinglin optimizingensembleunetarchitecturesforrobustcoronaryvesselsegmentationinangiographicimages
AT weichunwang optimizingensembleunetarchitecturesforrobustcoronaryvesselsegmentationinangiographicimages
AT kaichenghsu optimizingensembleunetarchitecturesforrobustcoronaryvesselsegmentationinangiographicimages
AT yalunwu optimizingensembleunetarchitecturesforrobustcoronaryvesselsegmentationinangiographicimages
AT chiahaoliu optimizingensembleunetarchitecturesforrobustcoronaryvesselsegmentationinangiographicimages
AT yangcfann optimizingensembleunetarchitecturesforrobustcoronaryvesselsegmentationinangiographicimages