TDAExplore: quantitative image analysis through topology-based machine learning
TDAExplore: quantitative image analysis through topology-based machine learning
Abstract Machine learning has greatly expanded the ability to classify images. However, many machine learning classifiers require thousands of images for training and lack quantitative descriptors of how images were grouped. We overcome these limitations with a machine learning approach based on topological data analysis, where a data set of 20-30 images is sufficient to accurately train the classifier. Our method quantifies differences between groups and identifies subcellular regions with the largest dissimilarities.
Mili?evi? Nikola、Edwards Parker、Heidings James B.、Bubenik Peter、Vitriol Eric A.、Skruber Kristen、Read Tracy-Ann
Department of Mathematics, University of FloridaDepartment of Applied and Computational Mathematics and Statistics, University of Notre DameDepartment of Pharmacology and Therapeutics, University of Florida College of MedicineDepartment of Mathematics, University of FloridaDepartment of Neuroscience and Regenerative Medicine, Medical College of Georgia, Augusta UniversityDepartment of Cellular and Molecular Pharmacology and Howard Hughes Medical Institute, University of CaliforniaDepartment of Neuroscience and Regenerative Medicine, Medical College of Georgia, Augusta University
生物科学研究方法、生物科学研究技术计算技术、计算机技术生物物理学
Mili?evi? Nikola,Edwards Parker,Heidings James B.,Bubenik Peter,Vitriol Eric A.,Skruber Kristen,Read Tracy-Ann.TDAExplore: quantitative image analysis through topology-based machine learning[EB/OL].(2025-03-28)[2025-04-27].https://www.biorxiv.org/content/10.1101/2021.06.13.448249.点此复制
评论