Biography

Dual background (MS, MBA) with 15 years of experience in data science and medical imaging

I work at the Scientific Computing and Imaging Institute (SCI), as director of the Biomedical imaging and data science core (BIDAC), a University of Utah health science service center. By leveraging the expertise of the SCI Institute, BIDAC offers application-oriented consulting services in the areas of deep learning, machine learning, computer vision, data science and data engineering. My role entails both business administration and scientific expertise, helping partners turn data into insights.

Expertise

Technical skills

  • Data science
  • Artificial intelligence
  • Deep learning
  • Machine learning
  • Medical imaging
  • Computer vision
  • Data analytics

Business skills

  • Consulting
  • Account management
  • Project management
  • Product management
  • Budget management

Areas of Interests

  • AI
  • Neuroscience
  • Data science
  • Data analytics

Project collaborations

I have been leading and developing end-to-end data science solutions, working in multi-institutional, interdisciplinary teams of computer scientists, software engineers, and medical investigators. I have been an active member of the multi-center National Alliance for Medical Image Computing (NA-MIC) from 2007 to 2012, and the multi-hospital Autism Center of Excellence Network - Infant Brain Imaging Study (ACE-IBIS) from 2010 to 2016. Please find examples of more recent projects below.

Artificial intelligence applied to nuclear forensics via deep learning

Nuclear forensics aims to investigate the origin and history of nuclear or radioactive materials via analytical techniques. Using electron microscopy images, we performed deep learning analysis to assess multiple calcination conditions and processing routes of nuclear samples. We applied, compared and fine-tuned via transfer learning state-of-the-art convolutional neural networks, performing numerous image classification and regression tasks. In addition to applying standard neural network architectures (ResNet, DenseNet), we implemented parallel networks to study multi-magnification acquisitions, and quantified model uncertainty during inference.

Data engineering workflow for AI in radiology imaging

We aimed to investigate the use of machine learning on large retrospective radiology imaging studies, including chest x-rays and related clinical text reports. In partnership with researchers from the Radiology Department, the Enterprise Data Warehouse and the Center for High Performance Computing, we leveraged various software and hardware infrastructure to enable secured data transfer from the hospital PACS system, HIPAA-compliant data storage via a database, and data management of large radiological datasets. We retrieved data from 59,000+ patients (140,000+ studies), to study chronic obstructive pulmonary disease (COPD), COVID-19 and acute respiratory infections.

Data management and data analytics for radiology studies

We aimed to predict the severity of pulmonary function tests in patients with chronic obstructive lung disease from chest radiographs using deep convolutional neural networks. For this clinical project, we transferred and managed a multi-modal dataset including unstructured chest x-ray acquisitions, text reports and metrics from pulmonary function tests. We also performed some data analytics, gaining insights into demographic and clinical information. These initial stages provided a clean dataset of 14,000+ studies from 7,000+ patients available for AI analysis.

Data science for neuroimaging clinical studies

Over 10 years, I led and executed parallel imaging data science projects to support various national clinical research studies. These entailed automated image registration, atlas generation, tissue classification and structural segmentation from brain imaging acquisitions (MRIs, DTIs, CTs), focusing on human, rodent and pig imaging. Driving clinical applications included brain development in autism spectrum disorder, Parkinson's disease, Down syndrome, Huntington's disease, deep brain stimulation, and obsessive-compulsive disorder.