TDAExplore: Quantitative analysis of fluorescence microscopy images through topology-based machine learning

Parker Edwards; Kristen Skruber; Nikola Milićević; James B Heidings; Tracy-Ann Read; Peter Bubenik; Eric A Vitriol

doi:10.1016/j.patter.2021.100367

TDAExplore: Quantitative analysis of fluorescence microscopy images through topology-based machine learning

Patterns (N Y). 2021 Oct 12;2(11):100367. doi: 10.1016/j.patter.2021.100367. eCollection 2021 Nov 12.

Authors

Parker Edwards¹, Kristen Skruber², Nikola Milićević³, James B Heidings⁴, Tracy-Ann Read⁵, Peter Bubenik⁶, Eric A Vitriol⁵

Affiliations

¹ Department of Applied and Computational Mathematics and Statistics, University of Notre Dame, Notre Dame, IN 46556, USA.
² Department of Cellular and Molecular Pharmacology and Howard Hughes Medical Institute, University of California, San Francisco, CA 94143, USA.
³ Department of Mathematics, Pennsylvania State University, University Park, PA 16802, USA.
⁴ Department of Pharmacology and Therapeutics, University of Florida College of Medicine, Gainesville, FL 32601, USA.
⁵ Department of Neuroscience and Regenerative Medicine, Medical College of Georgia, Augusta University, Augusta, GA 30912, USA.
⁶ Department of Mathematics, University of Florida, Gainesville, FL 32611, USA.

Abstract

Recent advances in machine learning have greatly enhanced automatic methods to extract information from fluorescence microscopy data. However, current machine-learning-based models can require hundreds to thousands of images to train, and the most readily accessible models classify images without describing which parts of an image contributed to classification. Here, we introduce TDAExplore, a machine learning image analysis pipeline based on topological data analysis. It can classify different types of cellular perturbations after training with only 20-30 high-resolution images and performs robustly on images from multiple subjects and microscopy modes. Using only images and whole-image labels for training, TDAExplore provides quantitative, spatial information, characterizing which image regions contribute to classification. Computational requirements to train TDAExplore models are modest and a standard PC can perform training with minimal user input. TDAExplore is therefore an accessible, powerful option for obtaining quantitative information about imaging data in a wide variety of applications.

Keywords: actin cytoskeleton; fluorescence microscopy; image classification; image segmentation; machine learning; persistence landscapes; persistent homology; topological data analysis.

Abstract

Grants and funding