Deep Learning Resolves Myovascular Dynamics in the Failing Human Heart

IF 8.4 1区医学 Q1 CARDIAC & CARDIOVASCULAR SYSTEMS

JACC: Basic to Translational Science Pub Date : 2024-05-01 DOI:10.1016/j.jacbts.2024.02.007

Anish Karpurapu BS , Helen A. Williams BS , Paige DeBenedittis PhD , Caroline E. Baker BS , Simiao Ren PhD , Michael C. Thomas BS , Anneka J. Beard MS , Garth W. Devlin BS , Josephine Harrington MD , Lauren E. Parker BS , Abigail K. Smith , Boyla Mainsah PhD , Michelle Mendiola Pla MD , Aravind Asokan PhD , Dawn E. Bowles PhD , Edwin Iversen PhD , Leslie Collins PhD , Ravi Karra MD, MHS

{"title":"Deep Learning Resolves Myovascular Dynamics in the Failing Human Heart","authors":"Anish Karpurapu BS , Helen A. Williams BS , Paige DeBenedittis PhD , Caroline E. Baker BS , Simiao Ren PhD , Michael C. Thomas BS , Anneka J. Beard MS , Garth W. Devlin BS , Josephine Harrington MD , Lauren E. Parker BS , Abigail K. Smith , Boyla Mainsah PhD , Michelle Mendiola Pla MD , Aravind Asokan PhD , Dawn E. Bowles PhD , Edwin Iversen PhD , Leslie Collins PhD , Ravi Karra MD, MHS","doi":"10.1016/j.jacbts.2024.02.007","DOIUrl":null,"url":null,"abstract":"<div><p>The adult mammalian heart harbors minute levels of cycling cardiomyocytes (CMs). Large numbers of images are needed to accurately quantify cycling events using microscopy-based methods. CardioCount is a new deep learning–based pipeline to rigorously score nuclei in microscopic images. When applied to a repository of 368,434 human microscopic images, we found evidence of coupled growth between CMs and cardiac endothelial cells in the adult human heart. Additionally, we found that vascular rarefaction and CM hypertrophy are interrelated in end-stage heart failure. CardioCount is available for use via GitHub and via Google Colab for users with minimal machine learning experience.</p></div>","PeriodicalId":14831,"journal":{"name":"JACC: Basic to Translational Science","volume":"9 5","pages":"Pages 674-686"},"PeriodicalIF":8.4000,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2452302X24000548/pdfft?md5=978db936761ec0f6df1d5fdff07202dc&pid=1-s2.0-S2452302X24000548-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"JACC: Basic to Translational Science","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2452302X24000548","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}

引用次数: 0

Abstract

The adult mammalian heart harbors minute levels of cycling cardiomyocytes (CMs). Large numbers of images are needed to accurately quantify cycling events using microscopy-based methods. CardioCount is a new deep learning–based pipeline to rigorously score nuclei in microscopic images. When applied to a repository of 368,434 human microscopic images, we found evidence of coupled growth between CMs and cardiac endothelial cells in the adult human heart. Additionally, we found that vascular rarefaction and CM hypertrophy are interrelated in end-stage heart failure. CardioCount is available for use via GitHub and via Google Colab for users with minimal machine learning experience.

查看原文本刊更多论文

深度学习解析衰竭人体心脏的肌血管动态变化

成年哺乳动物心脏中含有微量的循环心肌细胞（CMs）。使用基于显微镜的方法准确量化循环事件需要大量图像。CardioCount 是一种基于深度学习的新管道，可对显微图像中的细胞核进行严格评分。当应用于一个包含 368,434 幅人体显微图像的存储库时，我们发现了成人心脏中 CM 与心脏内皮细胞之间耦合生长的证据。此外，我们还发现在终末期心力衰竭中，血管稀疏和CM肥大是相互关联的。CardioCount 可通过 GitHub 使用，也可通过 Google Colab 提供给只有少量机器学习经验的用户使用。

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

JACC: Basic to Translational Science CARDIAC & CARDIOVASCULAR SYSTEMS-

CiteScore

14.20

自引率

1.00%

发文量

161

审稿时长

16 weeks

期刊介绍： JACC: Basic to Translational Science is an open access journal that is part of the renowned Journal of the American College of Cardiology (JACC). It focuses on advancing the field of Translational Cardiovascular Medicine and aims to accelerate the translation of new scientific discoveries into therapies that improve outcomes for patients with or at risk for Cardiovascular Disease. The journal covers thematic areas such as pre-clinical research, clinical trials, personalized medicine, novel drugs, devices, and biologics, proteomics, genomics, and metabolomics, as well as early phase clinical trial methodology.