APPARATUS AND METHOD FOR ULTRA-FAST ACQUIRING POSITRON EMISSION TOMOGRAPHIC IMAGE BASED ON DEEP LEARNING

摘要

Provides a deep learning-based high-speed positron tomography image acquisition device and method, and the high-speed positron tomography image acquisition device collects a positron electron tomography (PET) image captured by a positron tomography for each preset duration. The image collector to perform, the database in which PET images for each shooting period input through the image collector are stored, and the PET images for each shooting period are grouped according to a plurality of preset time units, and the grouped PET images are used as training images to create a preset deep learning model. When a PET image captured during the first period is input from a data learner for pre-learning and a positron tomography, the PET image captured during the first period is input with the pre-learned deep learning model to predict the reconstructed PET to correspond to the second period. It includes an image generator that generates and outputs an image.