Machine learning-based 3D segmentation of mitochondria in polarized epithelial cells

• Published in: Mitochondrion Vol. 76; p. 101882
• Main Authors: Hultgren, Nan W., Zhou, Tianli, Williams, David S.
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01-05-2024
• Subjects: 3D segmentation; ImageJ; Machine learning algorithm; Mitochondrial morphology; Retinal pigment epithelium; Mitochondrial morphology; RPE; BAF; 3D segmentation; 3D OC; Retinal pigment epithelium; ImageJ; 3D; TWS; 2D; NEAA; POS; Machine learning algorithm; GUI; DPBS
• ISSN: 1567-7249; 1872-8278; 1872-8278
• DOI: 10.1016/j.mito.2024.101882

•3D segmentation tool for fluorescent images, ideal for polarized cells.•Plug-and-play for user images with minimal to no additional training required.•Compatible with different cell types, labeling methods and imaging modalities.•No image-cleanup or pre-processing necessary.•Segmentation results suitable for various qualitative or quantitative analysis.
Mitochondria are dynamic organelles that alter their morphological characteristics in response to functional needs. Therefore, mitochondrial morphology is an important indicator of mitochondrial function and cellular health. Reliable segmentation of mitochondrial networks in microscopy images is a crucial initial step for further quantitative evaluation of their morphology. However, 3D mitochondrial segmentation, especially in cells with complex network morphology, such as in highly polarized cells, remains challenging. To improve the quality of 3D segmentation of mitochondria in super-resolution microscopy images, we took a machine learning approach, using 3D Trainable Weka, an ImageJ plugin. We demonstrated that, compared with other commonly used methods, our approach segmented mitochondrial networks effectively, with improved accuracy in different polarized epithelial cell models, including differentiated human retinal pigment epithelial (RPE) cells. Furthermore, using several tools for quantitative analysis following segmentation, we revealed mitochondrial fragmentation in bafilomycin-treated RPE cells.