Dataset Information

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

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).

SUBMITTER: Mergenthaler P

PROVIDER: S-EPMC7932518 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Mergenthaler Philipp P Hariharan Santosh S Pemberton James M JM Lourenco Corey C Penn Linda Z LZ Andrews David W DW

PLoS computational biology 20210222 2

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, w ...[more]

PMID: 33617523

Similar Datasets

Project description:Parkinson's disease (PD) is the second most common neurodegenerative disease and is characterized by the loss of midbrain dopaminergic neurons. Endocrine disrupting chemicals (EDCs) are active substances that interfere with hormonal signaling. Among EDCs, bisphenols (BPs) and perfluoroalkyls (PFs) are chemicals leached from plastics and other household products, and humans are unavoidably exposed to these xenobiotics. Data from animal studies suggest that EDCs exposure may play a role in PD, but data about the effect of BPs and PFs on human models of the nervous system are lacking. Previous studies demonstrated that machine learning (ML) applied to microscopy data can classify different cell phenotypes based on image features. In this study, the effect of BPs and PFs at different concentrations within the real-life exposure range (0.01, 0.1, 1, and 2 µM) on the phenotypic profile of human stem cell-derived midbrain dopaminergic neurons (mDANs) was analyzed. Cells exposed for 72 h to the xenobiotics were stained with neuronal markers and evaluated using high content microscopy yielding 126 different phenotypic features. Three different ML models (LDA, XGBoost and LightGBM) were trained to classify EDC-treated versus control mDANs. EDC treated mDANs were identified with high accuracies (0.88-0.96). Assessment of the phenotypic feature contribution to the classification showed that EDCs induced a significant increase of alpha-synuclein (αSyn) and tyrosine hydroxylase (TH) staining intensity within the neurons. Moreover, microtubule-associated protein 2 (MAP2) neurite length and branching were significantly diminished in treated neurons. Our study shows that human mDANs are adversely impacted by exposure to EDCs, causing their phenotype to shift and exhibit more characteristics of PD. Importantly, ML-supported high-content imaging can identify concrete but subtle subcellular phenotypic changes that can be easily overlooked by visual inspection alone and that define EDCs effects in mDANs, thus enabling further pathological characterization in the future.

Project description:Chromatin-sensitive Partial Wave Spectroscopic (csPWS) microscopy offers a non-invasive glimpse into the mass density distribution of cellular structures at the nanoscale, leveraging the spectroscopic information. Such capability allows us to analyze the chromatin structure and organization and the global transcriptional state of the cell nuclei for the study of its role in carcinogenesis. Accurate segmentation of the nuclei in csPWS microscopy images is an essential step in isolating them for further analysis. However, manual segmentation is error-prone, biased, time-consuming, and laborious, resulting in disrupted nuclear boundaries with partial or over-segmentation. Here, we present an innovative deep-learning-driven approach to automate the accurate nuclei segmentation of label-free live cell csPWS microscopy imaging data. Our approach, csPWS-seg, harnesses the Convolutional Neural Networks-based U-Net model with an attention mechanism to automate the accurate cell nuclei segmentation of csPWS microscopy images. We leveraged the structural, physical, and biological differences between the cytoplasm, nucleus, and nuclear periphery to construct three distinct csPWS feature images for nucleus segmentation. Using these images of HCT116 cells, csPWS-seg achieved superior performance with a median Intersection over Union (IoU) of 0.80 and a Dice Similarity Coefficient (DSC) score of 0.88. The csPWS-seg overcame the segmentation performance over the baseline U-Net model and another attention-based model, SE-U-Net, marking a significant improvement in segmentation accuracy. Further, we analyzed the performance of our proposed model with four loss functions: binary cross-entropy loss, focal loss, dice loss, and Jaccard loss. The csPWS-seg with focal loss provided the best results compared to other loss functions. The automatic and accurate nuclei segmentation offered by the csPWS-seg not only automates, accelerates, and streamlines csPWS data analysis but also enhances the reliability of subsequent chromatin analysis research, paving the way for more accurate diagnostics, treatment, and understanding of cellular mechanisms for carcinogenesis.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets