MOrgAna

MOrgAna performs automated segmentation, quantification, and visualization of morphological and fluorescence features from 2D multi-channel organoid images using machine learning in Python to enable high-throughput analysis.

Key Features:

• Automated Image Segmentation: Employs machine learning algorithms to segment complex organoid structures from 2D multi-channel images.
• Morphological and Fluorescence Quantification: Extracts and quantifies morphological features and fluorescence signals from segmented organoids.
• High-throughput Processing: Processes hundreds of single-object images in minutes.
• Multi-platform Image Compatibility: Accepts images from benchtop stereoscopes to high-content confocal-based systems.
• Modular Design: Python-based modular architecture permits customization and integration of additional computational modules.

Scientific Applications:

• Organoid Morphology Analysis: Quantitative analysis of organoid phenotype and morphology in developmental biology and in vitro systems.
• Fluorescence Marker Analysis: Measurement and comparison of fluorescence-based marker expression within organoids.
• High-throughput Phenotypic Screening: Large-scale screening of organoid cultures for biomedical and translational studies.
• Cross-platform Image Analysis: Comparative analysis of images acquired across different microscopy platforms and diverse organoid types.

Methodology:

Implemented in Python; uses machine learning algorithms for image segmentation, extracts morphological and fluorescence features from 2D multi-channel images, employs a modular architecture for customization, and processes hundreds of single-object images in minutes.