Speaker
Konrad Klimaszewski
(National Centre for Nuclear Research)
Description
In Positron Emission Tomography the problem of image distortion due to scattered photons or accidental coincidences becomes more pronounced for large field-of-view scanners capable of measuring the whole patient in one scan. We propose a novel method of encoding coincidence event information to enhance the efficiency of noise filtration classification. The proposed encoding enables the usage of Convolutional Neural Networks as feature extractors in the classification task. We take advantage of the voxel nature of underlying data and evaluate the performance of the 3-D CNN network to classify true, scattered and accidental coincidences for imaging quality improvement with large field-of-view PET scanners.
Primary authors
Konrad Klimaszewski
(National Centre for Nuclear Research)
Michał Obara
(National Centre for Nuclear Research)
Wojciech Krzemien
(National Centre for Nuclear Research)
