Cardiology Fluoroscopy AI Interpolation

In cardiac and other angiography video x-ray images are used to guide the physician in inserting the catheter (wire) into the heart or other organs. The greater the number of x-rays or frames taken per second, the better the quality of the images. However, this also leads to higher radiation dose and risk to the patient and the operator.

The research question for this project is to use AI generated synthetic images with a special Real-time Intermediate Flow Estimation (RIFE) algorithm to replace some of the frames or x-ray pictures and assess whether they are useful in guiding the physician or diagnosis. This should allow one to reduce the number of x-ray images the patient is getting and subsequently radiation dose to both the patient and to cardiology staff members present during the examination.