The use of weather nowcasting convolutional neural network extrapolators in cardiac PET imaging.

Journal: Journal of medical radiation sciences
Published Date:

Abstract

INTRODUCTION: Algorithms to predict short-term changes in local weather modalities have been used in meteorology for many years. These algorithms predict the temporospatial change in the movement of weather patterns such as cloud cover or precipitation. This paper extends convolutional neural network models for weather prediction/nowcasting to predict evolution in the extrapolation of sequentially acquired count data seen with cardiac positron tomography (PET) data to expected value temporally rather than spatially.

Authors

  • Scott Sloka
    Waterloo, Ontario, Canada.