Artery segmentation and atherosclerotic plaque quantification using AI for murine whole slide images stained with oil red O

Abstract Atherosclerosis is the leading cause of death in Western industrial nations. To study the etiology of plaque progression, atherosclerotic mouse models are widely used. Traditionally, analyzing the obtained histological whole slide images of Oil Red O-stained aortic roots required manual seg...

Full description

Saved in:
Bibliographic Details
Main Authors: Johann Christopher Engster, Tobias Reinberger, Nele Blum, Pascal Stagge, Thorsten M. Buzug, Zouhair Aherrahrou, Maik Stille
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-93967-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713689138036736
author Johann Christopher Engster
Tobias Reinberger
Nele Blum
Pascal Stagge
Thorsten M. Buzug
Zouhair Aherrahrou
Maik Stille
author_facet Johann Christopher Engster
Tobias Reinberger
Nele Blum
Pascal Stagge
Thorsten M. Buzug
Zouhair Aherrahrou
Maik Stille
author_sort Johann Christopher Engster
collection DOAJ
description Abstract Atherosclerosis is the leading cause of death in Western industrial nations. To study the etiology of plaque progression, atherosclerotic mouse models are widely used. Traditionally, analyzing the obtained histological whole slide images of Oil Red O-stained aortic roots required manual segmentation. To accelerate this process, an artificial intelligence-driven solution is proposed that comprises three stages: (1) defining the region of interest (ROI) of the aortic root using a YOLOv8l object detector, (2) applying supervised machine learning with ensembles of U-Net++ networks for artery segmentation using ROI masks, and (3) performing plaque segmentation within arterial walls with the unsupervised W-Net method. To establish a robust segmentation pipeline, we benchmark our methods using manually created masks ( $$\text {n}=6085$$ for artery segmentation, $$\text {n}=1089$$ for plaque segmentation). A key finding is that an ensemble of U-Net++ networks applied on ROI masks outperformed single network architectures. Through a novel combination strategy, the ensemble output can be easily modified, paving the way for a quick and robust application in the lab. Finally, a case study utilizing published mouse data ( $$\text {n}=373$$ slices) underscored the ability of our optimized pipeline to replicate human-made plaque predictions with a high correlation (Pearson’s $$\text {r}=0.91$$ ) and reproduce biological insights derived from manual analysis.
format Article
id doaj-art-6805eb0ff2ca4920b638468b956ca054
institution DOAJ
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-6805eb0ff2ca4920b638468b956ca0542025-08-20T03:13:54ZengNature PortfolioScientific Reports2045-23222025-04-0115111110.1038/s41598-025-93967-6Artery segmentation and atherosclerotic plaque quantification using AI for murine whole slide images stained with oil red OJohann Christopher Engster0Tobias Reinberger1Nele Blum2Pascal Stagge3Thorsten M. Buzug4Zouhair Aherrahrou5Maik Stille6Fraunhofer IMTE, Fraunhofer Research Institution for Individualized and Cell-Based Medical EngineeringInstitute for Cardiogenetics, University of LübeckFraunhofer IMTE, Fraunhofer Research Institution for Individualized and Cell-Based Medical EngineeringFraunhofer IMTE, Fraunhofer Research Institution for Individualized and Cell-Based Medical EngineeringFraunhofer IMTE, Fraunhofer Research Institution for Individualized and Cell-Based Medical EngineeringInstitute for Cardiogenetics, University of LübeckFraunhofer IMTE, Fraunhofer Research Institution for Individualized and Cell-Based Medical EngineeringAbstract Atherosclerosis is the leading cause of death in Western industrial nations. To study the etiology of plaque progression, atherosclerotic mouse models are widely used. Traditionally, analyzing the obtained histological whole slide images of Oil Red O-stained aortic roots required manual segmentation. To accelerate this process, an artificial intelligence-driven solution is proposed that comprises three stages: (1) defining the region of interest (ROI) of the aortic root using a YOLOv8l object detector, (2) applying supervised machine learning with ensembles of U-Net++ networks for artery segmentation using ROI masks, and (3) performing plaque segmentation within arterial walls with the unsupervised W-Net method. To establish a robust segmentation pipeline, we benchmark our methods using manually created masks ( $$\text {n}=6085$$ for artery segmentation, $$\text {n}=1089$$ for plaque segmentation). A key finding is that an ensemble of U-Net++ networks applied on ROI masks outperformed single network architectures. Through a novel combination strategy, the ensemble output can be easily modified, paving the way for a quick and robust application in the lab. Finally, a case study utilizing published mouse data ( $$\text {n}=373$$ slices) underscored the ability of our optimized pipeline to replicate human-made plaque predictions with a high correlation (Pearson’s $$\text {r}=0.91$$ ) and reproduce biological insights derived from manual analysis.https://doi.org/10.1038/s41598-025-93967-6Artery segmentationEnsembleMachine learningOil red OPlaque segmentation
spellingShingle Johann Christopher Engster
Tobias Reinberger
Nele Blum
Pascal Stagge
Thorsten M. Buzug
Zouhair Aherrahrou
Maik Stille
Artery segmentation and atherosclerotic plaque quantification using AI for murine whole slide images stained with oil red O
Scientific Reports
Artery segmentation
Ensemble
Machine learning
Oil red O
Plaque segmentation
title Artery segmentation and atherosclerotic plaque quantification using AI for murine whole slide images stained with oil red O
title_full Artery segmentation and atherosclerotic plaque quantification using AI for murine whole slide images stained with oil red O
title_fullStr Artery segmentation and atherosclerotic plaque quantification using AI for murine whole slide images stained with oil red O
title_full_unstemmed Artery segmentation and atherosclerotic plaque quantification using AI for murine whole slide images stained with oil red O
title_short Artery segmentation and atherosclerotic plaque quantification using AI for murine whole slide images stained with oil red O
title_sort artery segmentation and atherosclerotic plaque quantification using ai for murine whole slide images stained with oil red o
topic Artery segmentation
Ensemble
Machine learning
Oil red O
Plaque segmentation
url https://doi.org/10.1038/s41598-025-93967-6
work_keys_str_mv AT johannchristopherengster arterysegmentationandatheroscleroticplaquequantificationusingaiformurinewholeslideimagesstainedwithoilredo
AT tobiasreinberger arterysegmentationandatheroscleroticplaquequantificationusingaiformurinewholeslideimagesstainedwithoilredo
AT neleblum arterysegmentationandatheroscleroticplaquequantificationusingaiformurinewholeslideimagesstainedwithoilredo
AT pascalstagge arterysegmentationandatheroscleroticplaquequantificationusingaiformurinewholeslideimagesstainedwithoilredo
AT thorstenmbuzug arterysegmentationandatheroscleroticplaquequantificationusingaiformurinewholeslideimagesstainedwithoilredo
AT zouhairaherrahrou arterysegmentationandatheroscleroticplaquequantificationusingaiformurinewholeslideimagesstainedwithoilredo
AT maikstille arterysegmentationandatheroscleroticplaquequantificationusingaiformurinewholeslideimagesstainedwithoilredo