My expertise lies in gleaning insights from biomedical imaging and supply chain data using traditional and cutting-edge AI/machine learning techniques. With a strong understanding of biomedical imaging, from CT and MRI to digital histology, and statistical methods, I have brought forth innovative approaches tailored to address pressing challenges in human health and supply chain efficiency. I have conceived, developed, and executed solutions for processing and analyzing imaging, geometric shape, and time series data using regression, random forests, and (deep) neural networks. Furthermore, I have articulated technical methods and results to diverse audiences.

Projects Portfolio:

•  Statistical analysis of relationships between age-related physiological function and the sizes and shapes of brain structures that support higher cognitive functions (used Matlab, Python, and R).
  
  
• Multi-resolution stochastic diffusion generative model to improve image generation quality and latency (used Python and PyTorch).
  
  
• Created 3D, deformable brain atlases using image and geometry processing algorithms (used Matlab and Python).
  
  
• Forecasted product demand and credit hold time series using random forests and a novel, evolutionary, deep Long Short-Term Memory Network pipeline in the cloud (used Python and Keras).
  
  
• Nanoparticle tracking from video microscopy analysis (used Matlab).
  
  
• Segmentation of brain tissue types from labeled images using conditional random fields (used Matlab).