Utilizing Machine Learning for the Identification of Mitochondrial Fission and Fusion

Forty-eight percent of adults over the age of 20 in the United States are affected by cardiovascular disease (CVD), a condition largely influenced by the metabolic function of endothelial cells (ECs) lining the blood vessels. Understanding the physiological processes underlying CVD involves examining EC mitochondrial networks, as mitochondrial function and ATP production are crucial for EC metabolism, thereby impacting CVD progression. Currently, biochemical assays and immunofluorescence microscopy provide insights into how mitochondrial function influences cellular metabolism, but they lack the ability for live observation and tracking changes in mitochondrial networks through fusion and fission events. Holotomographic microscopy (HTM) emerges as a promising technique for real-time, label-free visualization of ECs and their organelles, such as mitochondria. This non-destructive and non-interfering live cell imaging method offers unprecedented opportunities to observe and quantify mitochondrial network dynamics. However, existing image processing tools, based on immunofluorescence microscopy techniques, are incompatible with HTM images, which necessitates the utilization of a machine-learning model. This model will segment HTM images into four classes: mitochondrial networks, cell border, cell, and background, accurately identifying mitochondrial structures and positions, and quantifying network dynamics. By enabling the study of mitochondrial networks and their effects on CVD, this approach promises to deepen our understanding of the disease's mechanisms.