MOrgAna: accessible quantitative analysis of organoids with machine learning.

Area of Science:

• Developmental Biology
• Biomedical Imaging
• Translational Research

Background:

• Organoids are increasingly used in biological research, generating large, complex image datasets.
• Current methods for analyzing organoid images are time-consuming and difficult to scale.
• A need exists for automated, user-friendly software for rapid organoid image analysis.

Purpose of the Study:

• To introduce MOrgAna, a novel Python-based software for automated organoid image analysis.
• To provide a coding-free, intuitive, and scalable solution for quantifying organoid morphology and fluorescence.
• To demonstrate the software's versatility across different organoid types and imaging platforms.

Main Methods:

• MOrgAna utilizes machine learning algorithms for image segmentation.
• The software quantifies morphological and fluorescence features from organoid images.
• It processes hundreds of images rapidly, providing visualization of results.

Main Results:

• MOrgAna successfully segmented and quantified organoid images across diverse systems and microscopes.
• The software demonstrated rapid analysis, completing tasks within minutes.
• Its modular design allows for customization by advanced users.

Conclusions:

• MOrgAna offers an efficient and accessible solution for analyzing large-scale organoid image data.
• The software facilitates faster insights in developmental biology and translational studies.
• Its broad applicability makes it a valuable tool for researchers using organoids.