Vesseg: An Open-Source Tool for Deep Learning-Based Atherosclerotic Plaque Quantification in Histopathology Images—Brief Report. Issue 10 (12th August 2021)

• Record Type: Journal Article
• Authors: Murray, Jacob M.; Pfeffer, Phillip; Seifert, Robert; Hermann, Alexander; Handke, Jessica; Kummer, Laura; Janssen, Henrike; Weigand, Markus A.; Schlemmer, Heinz-Peter; Larmann, Jan; Kleesiek, Jens
• Is Part Of: Arteriosclerosis, thrombosis, and vascular biology. Volume 41:Issue 10(2021)
• Page Start: 2516
• Page End: 2522
• Publication Date: 2021-08-12
• Subjects: atherosclerosis -- cardiovascular disease -- deep learning -- image interpretation, computer-assisted -- vascular remodeling; Arteriosclerosis -- Periodicals; Thrombosis -- Periodicals; Blood-vessels -- Pathophysiology -- Periodicals; Electronic journals; 616.13
• DOI: 10.1161/ATVBAHA.121.316124
• Languages: English
• ISSNs: 1079-5642

Abstract

Abstract : Supplemental Digital Content is available in the text. Abstract : Objective: Manual plaque segmentation in microscopy images is a time-consuming process in atherosclerosis research and potentially subject to unacceptable user-to-user variability and observer bias. We address this by releasing Vesseg a tool that includes state-of-the-art deep learning models for atherosclerotic plaque segmentation. Approach and Results: Vesseg is a containerized, extensible, open-source, and user-oriented tool. It includes 2 models, trained and tested on 1089 hematoxylin-eosin stained mouse model atherosclerotic brachiocephalic artery sections. The models were compared to 3 human raters. Vesseg can be accessed at https://vesseg .online or downloaded. The models show mean Soerensen-Dice scores of 0.91±0.15 for plaque and 0.97±0.08 for lumen pixels. The mean accuracy is 0.98±0.05. Vesseg is already in active use, generating time savings of >10 minutes per slide. Conclusions: Vesseg brings state-of-the-art deep learning methods to atherosclerosis research, providing drastic time savings, while allowing for continuous improvement of models and the underlying pipeline.