Application of an artificial intelligence for quantitative analysis of endothelial capillary beds in vitro.

IF 2.1 4区医学 Q3 HEMATOLOGY

Clinical hemorheology and microcirculation Pub Date : 2024-04-16 DOI:10.3233/ch-242157

Marine M. M. Magnusson, Gertraud Schüpbach-Regula, Juliane Rieger, Johanna Plendl, Ilka Marin, Barbara Drews, S. Kaessmeyer

{"title":"Application of an artificial intelligence for quantitative analysis of endothelial capillary beds in vitro.","authors":"Marine M. M. Magnusson, Gertraud Schüpbach-Regula, Juliane Rieger, Johanna Plendl, Ilka Marin, Barbara Drews, S. Kaessmeyer","doi":"10.3233/ch-242157","DOIUrl":null,"url":null,"abstract":"Objective\nBACKGROUND: The use of endothelial cell cultures has become fundamental to study angiogenesis. Recent advances in artificial intelligences (AI) offer opportunities to develop automated assessment methods in medical research, analyzing larger datasets.\n\n\nObjective\nOBJECTIVE: The aim of this study was to compare the application of AI with a manual method to morphometrically quantify in vitro angiogenesis.\n\n\nObjective\nMETHODS: Co-cultures of human microvascular endothelial cells and fibroblasts were incubated mimicking endothelial capillary-beds. An AI-software was trained for segmentation of endothelial capillaries on anti-CD31-labeled light microscope crops. Number of capillaries and branches and average capillary diameter were measured by the AI and manually on 115 crops.\n\n\nObjective\nRESULTS: The crops were analyzed faster by the AI than manually (3 minutes vs 1 hour per crop). Using the AI, systematically more capillaries (mean 48/mm2 vs 27/mm2) and branches (mean 23/mm2 vs 11/mm2) were counted than manually. Both methods had a strong linear relationship in counting capillaries and branches (r-capillaries = 0.88, r-branches = 0.89). No correlation was found for measurements of the diameter (r-diameter = 0.15).\n\n\nObjective\nCONCLUSIONS: The present AI reduces the time required for quantitative analysis of angiogenesis on large datasets, and correlates well with manual analysis.","PeriodicalId":10425,"journal":{"name":"Clinical hemorheology and microcirculation","volume":null,"pages":null},"PeriodicalIF":2.1000,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical hemorheology and microcirculation","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.3233/ch-242157","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"HEMATOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Objective BACKGROUND: The use of endothelial cell cultures has become fundamental to study angiogenesis. Recent advances in artificial intelligences (AI) offer opportunities to develop automated assessment methods in medical research, analyzing larger datasets. Objective OBJECTIVE: The aim of this study was to compare the application of AI with a manual method to morphometrically quantify in vitro angiogenesis. Objective METHODS: Co-cultures of human microvascular endothelial cells and fibroblasts were incubated mimicking endothelial capillary-beds. An AI-software was trained for segmentation of endothelial capillaries on anti-CD31-labeled light microscope crops. Number of capillaries and branches and average capillary diameter were measured by the AI and manually on 115 crops. Objective RESULTS: The crops were analyzed faster by the AI than manually (3 minutes vs 1 hour per crop). Using the AI, systematically more capillaries (mean 48/mm2 vs 27/mm2) and branches (mean 23/mm2 vs 11/mm2) were counted than manually. Both methods had a strong linear relationship in counting capillaries and branches (r-capillaries = 0.88, r-branches = 0.89). No correlation was found for measurements of the diameter (r-diameter = 0.15). Objective CONCLUSIONS: The present AI reduces the time required for quantitative analysis of angiogenesis on large datasets, and correlates well with manual analysis.

查看原文本刊更多论文

应用人工智能对体外内皮毛细血管床进行定量分析。

背景：使用内皮细胞培养物已成为研究血管生成的基础。人工智能（AI）的最新进展为医学研究提供了开发自动评估方法、分析更大数据集的机会。目的：本研究的目的是比较人工智能与手动方法在体外血管生成形态学量化方面的应用。训练人工智能软件在抗 CD31 标记的光镜作物上分割内皮毛细血管。人工智能和人工分别对 115 块作物上的毛细血管和分支数量以及毛细血管平均直径进行了测量。结果：人工智能分析作物的速度比人工快（每块作物 3 分钟对 1 小时）。使用人工智能计算的毛细血管（平均 48 条/平方毫米 vs 27 条/平方毫米）和枝条（平均 23 条/平方毫米 vs 11 条/平方毫米）数量明显多于人工计算。两种方法在毛细血管和分支计数方面都有很强的线性关系（r-毛细血管 = 0.88，r-分支 = 0.89）。在直径测量方面没有发现相关性（r-直径 = 0.15）：本人工智能缩短了对大型数据集进行血管生成定量分析所需的时间，并与人工分析具有良好的相关性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Clinical hemorheology and microcirculation 医学-外周血管病

CiteScore

4.30

自引率

33.30%

发文量

170

期刊介绍： Clinical Hemorheology and Microcirculation, a peer-reviewed international scientific journal, serves as an aid to understanding the flow properties of blood and the relationship to normal and abnormal physiology. The rapidly expanding science of hemorheology concerns blood, its components and the blood vessels with which blood interacts. It includes perihemorheology, i.e., the rheology of fluid and structures in the perivascular and interstitial spaces as well as the lymphatic system. The clinical aspects include pathogenesis, symptomatology and diagnostic methods, and the fields of prophylaxis and therapy in all branches of medicine and surgery, pharmacology and drug research. The endeavour of the Editors-in-Chief and publishers of Clinical Hemorheology and Microcirculation is to bring together contributions from those working in various fields related to blood flow all over the world. The editors of Clinical Hemorheology and Microcirculation are from those countries in Europe, Asia, Australia and America where appreciable work in clinical hemorheology and microcirculation is being carried out. Each editor takes responsibility to decide on the acceptance of a manuscript. He is required to have the manuscript appraised by two referees and may be one of them himself. The executive editorial office, to which the manuscripts have been submitted, is responsible for rapid handling of the reviewing process. Clinical Hemorheology and Microcirculation accepts original papers, brief communications, mini-reports and letters to the Editors-in-Chief. Review articles, providing general views and new insights into related subjects, are regularly invited by the Editors-in-Chief. Proceedings of international and national conferences on clinical hemorheology (in original form or as abstracts) complete the range of editorial features.