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 ([Formula: see text] for artery segmentation, [Formula: see text] 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 ([Formula: see text] slices) underscored the ability of our optimized pipeline to replicate human-made plaque predictions with a high correlation (Pearson's [Formula: see text]) and reproduce biological insights derived from manual analysis.