The overall goal of this project is to develop an infrastructure platform that will facilitate continuous testing and monitoring of diagnostic AI devices operating at real-world clinical practice sites. The platform will also enable data collection for real-world performance evaluation of AI/ML-enabled, computer-aided, detection/characterization/triaging (CAD) devices in radiology and health care applications in clinical practices.

We are currently collaborating with the U.S. Food and Drug Administration (FDA), research institutes, and clinical centers to build an AI-testbed. This testbed will serve as the platform for post-market, AI/ML-enabled device evaluation and monitoring to handle the challenges at clinical practices, such as:

• Complexity of clinical records and backwards observation
• Complexity of measuring algorithmic performance
• Complexity of EHR/PACS interoperability

The potential AI devices that will be used for testing and monitoring are:

• Early lung cancer screening using CT scans
• Breast cancer screening using mammography
• Brain tumor classification using CT scans/PET scans

 

Other Projects

Artificial Intelligence in Biomedical Imaging

AI/NLP for EHR Analytics

NIH AIM-AHEAD Program

AI/ML for Marine Atmospheric Boundary Layer Profiles via Satellite Remote Sensing Data Fusion

Intelligently Secured Distributed Solution

Networking with Human in the Loop

Cyberphysical Security Research for Biopharma Production and Personalized Medicine