Rapid 3D phenotypic analysis of neurons and organoids using data-driven cell segmentation-free machine learning

TLDR

Phenotypic profiling of large 3D microscopy datasets is limited by segmentation challenges and high computational demands, especially for neurons and organoids. The study introduces a shallow‑learning framework for automated quantitative phenotyping of 3D image data using unsupervised voxel‑based feature learning. The framework enables fast classification, clustering, and advanced visualization, and was applied to complex 3D images to analyze phenotypic changes in neurons exposed to apoptosis‑inducing treatments and in oncogene‑expressing mammary gland acinar organoids. Phindr3D, the implementation, allows rapid data‑driven voxel‑based feature learning in 3D high‑content analysis, preserves biological relevance and heterogeneity, and is available as MATLAB code and a stand‑alone program on GitHub.

Abstract

Phenotypic profiling of large three-dimensional microscopy data sets has not been widely adopted due to the challenges posed by cell segmentation and feature selection. The computational demands of automated processing further limit analysis of hard-to-segment images such as of neurons and organoids. Here we describe a comprehensive shallow-learning framework for automated quantitative phenotyping of three-dimensional (3D) image data using unsupervised data-driven voxel-based feature learning, which enables computationally facile classification, clustering and advanced data visualization. We demonstrate the analysis potential on complex 3D images by investigating the phenotypic alterations of: neurons in response to apoptosis-inducing treatments and morphogenesis for oncogene-expressing human mammary gland acinar organoids. Our novel implementation of image analysis algorithms called Phindr3D allowed rapid implementation of data-driven voxel-based feature learning into 3D high content analysis (HCA) operations and constitutes a major practical advance as the computed assignments represent the biology while preserving the heterogeneity of the underlying data. Phindr3D is provided as Matlab code and as a stand-alone program ( https://github.com/DWALab/Phindr3D ).