High-speed video microscopy and artificial intelligence are used to calculate statistics such as diastolic and systolic diameters, fractional shortening, and ejection fraction in fruit fly hearts. This method reduces the need for human intervention and minimizes errors in measuring cardiac dynamics. The research conducted at the University of Alabama at Birmingham demonstrates a faster and more accurate way to analyze heart function in fruit flies using deep learning and high-speed video microscopy.
The study shows that this approach can be applied to other small animal models and potentially to human heart models, providing valuable insights into cardiac health and disease. The automated assessments of heart performance in fruit flies were validated against experimental datasets, showing promising results in predicting cardiac aging and pathology.
The trained model can provide detailed statistics on various parameters of heart function, paving the way for more comprehensive studies in Drosophila. This innovative platform for deep learning-assisted segmentation is the first of its kind for high-resolution optical microscopy of fruit fly hearts. The research holds potential for translating findings from fruit fly models to human cardiovascular research.
The study was published in the journal Communications Biology, with support from various grants. Lead author Girish Melkani and his team aim to further explore the pathophysiological basis of human cardiovascular diseases using fruit fly models and automated analysis techniques.
Source link
Source link: https://www.uab.edu/news/research/item/14236-deep-machine-learning-speeds-assessment-of-fruit-fly-heart-aging-and-disease-a-model-for-human-disease