Faculty

Imon Banerjee, Ph.D.

Clinical Studies

Training And Evaluation Of Machine Learning Models For Medical Imaging Red Wing, Minn., Minneapolis, Minn., Owatonna, Minn., Rochester, Minn., La Crosse, Wis., Lake City, Minn., Mankato, Minn., Cannon Falls, Minn., Eau Claire, Wis., Jacksonville, Fla., Albert Lea, Minn., Scottsdale/Phoenix, Ariz., Austin, Minn.
The purpose of this study is to evaluate machine learning (ML)/AI models used for medical imaging.

AI-Flex: An Artificial Neural Network Integrated Flexible Multi-Modal Sensor Patch for Real-Time Continuous Physiological Monitoring and Inference (AI-Flex) Scottsdale/Phoenix, Ariz.
The purpose of this study is to test AI inference capability in a flexible multi-modal bio-sensor to allow in-situ active monitoring of patient health in real-time.

We developed AI-Flex - a flexible multi-modal bio-sensing device with integrated AI capability that will predict short-term risks of 3 medical events - arrhythmia, cardiac arrest and sepsis.
Feasibility of AI to enhance low contrast CT imaging: A pilot study. Jacksonville, Fla., Scottsdale/Phoenix, Ariz.
The purpose of this study is to generate an additional series (reconstruction) of the low contrast dose CT exam utilizing an AI model (general adversarial network (GAN)) to simulate high contrast on CT exams.