Simultaneous Attenuation Correction, Scatter Correction, and Denoising in PET Imaging with Deep Learning

Abstract

Low radiation dose is desirable in PET/CT imaging. The delivered dose originates from both CT scans and injected PET radioisotopes. CT data is used for attenuation and scatter corrections in PET image formation. A standard PET dose is usually needed to generate PET images of clinical quality so that physicians can make diagnosis with confidence. In this work, we eliminated the CT scans and reduced the PET dose while maintaining image quality by performing simultaneous attenuation correction, scatter correction, and denoising using a deep learning approach. We trained a multi-layer convolutional neural network (CNN) with non-attenuation corrected, non-scatter corrected, and low dose PET images as input, and fully corrected standard dose PET images as labels. After the CNN is trained, it is used to generate fully corrected standard dose PET images from low dose PET data alone. This capability will make CT scan unnecessary and save PET dose significantly. We validated our methodology with patient data. The results showed that attenuation correction, scatter correction, and denoising can be performed simultaneously using the deep learning method.