Researchers at the University of Alabama at Birmingham have developed a novel approach to assess fruit fly heart aging and disease, which could ultimately inform human cardiovascular research. Led by Girish Melkani, PhD, the team utilized high-speed video microscopy and artificial intelligence to analyze fruit fly hearts, providing calculated statistics such as diastolic and systolic diameters, fractional shortening, and ejection fraction.
This machine learning method minimizes human error and can process hundreds of hearts at once, allowing for a more comprehensive understanding of how environmental or genetic factors affect heart aging or pathology. The fruit fly model has already been instrumental in understanding the pathophysiological bases for several human cardiovascular diseases, which remain a leading cause of death and disability in the United States. Melkani envisions adapting this technology to study cardiac mutation models and other small animal models, such as zebrafish and mice, with potential applications in human heart models.
Accelerating Heart Disease Research with Deep Machine Learning and Fruit Flies
The use of fruit flies as a model for human heart pathophysiology has been instrumental in understanding cardiac aging and cardiomyopathy. However, the analysis of fruit fly hearts has been limited by the need for human intervention to measure the heart at moments of its largest expansion or greatest contraction. Researchers at the University of Alabama at Birmingham have now developed a method that significantly cuts the time needed for this analysis while utilizing more of the heart region.
High-Speed Video Microscopy and Artificial Intelligence
The researchers employed high-speed video microscopy and artificial intelligence to provide calculated statistics such as diastolic and systolic diameters, fractional shortening, and ejection fraction. This approach enables the analysis of each heartbeat in the fly, minimizing human error and allowing for the assessment of several hundred hearts simultaneously.
Girish Melkani, Ph.D., associate professor in the UAB Department of Pathology, Division of Molecular and Cellular Pathology, emphasized that their machine learning method is not only fast but also reduces human error. “You don’t have to manually mark each heart wall under systolic and diastolic conditions,” he explained. This approach can expand the ability to test how different environmental or genetic factors affect heart aging or pathology.
Expanding Research Capabilities
Melkani envisions using deep learning-assisted studies to explore cardiac mutation models and other small animal models, such as zebrafish and mice. He also believes that their techniques could be adapted for human heart models, providing valuable insights into cardiac health and disease. Incorporating uncertainty quantification methods could further enhance the reliability of their analyses.
The fruit fly model has already been instrumental in understanding the pathophysiological bases for several human cardiovascular diseases. Cardiovascular disease continues to be one of the leading causes of death and disability in the United States.
Validating the Trained Model
Melkani and his colleagues assessed their trained model on heart performance both in fruit fly cardiac aging and in a fruit fly model of dilated cardiomyopathy caused by the knockdown of a pivotal TCA cycle enzyme, oxoglutarate dehydrogenase. These automated assessments were then validated against existing experimental datasets.
For example, for aging of fruit flies at one week versus five weeks of age, which is about halfway through a fruit fly’s life span, the UAB team used 54 hearts for model training and then validated their measurements against an experimental aging model with 177 hearts. Their trained model was able to reconstruct expected trends in cardiac parameters with aging.
Potential Applications
Melkani’s team’s model can be applied to readily available consumer hardware, and their code can provide calculated statistics including diastolic and systolic diameters/intervals, fractional shortening, ejection fraction, heart period/rate, and quantified heartbeat arrhythmicity. This innovative platform for deep learning-assisted segmentation is the first of its kind to be applied to standard high-resolution high-speed optical microscopy of Drosophila hearts while also quantifying all relevant parameters.
By automating the process and providing detailed cardiac statistics, Melkani’s team paves the way for more accurate, efficient, and comprehensive studies of heart function in Drosophila. This method holds tremendous potential not only for understanding aging and disease in fruit flies but also for translating these insights into human cardiovascular research.
External Link: Click Here For More
