Joint Correction of Attenuation and Scatter Using Deep Convolutional Neural Networks (DCNN) for Time-of-Flight PET
This work addresses the challenge of accurate PET image reconstruction for medical diagnostics by enabling faster and more efficient correction without additional scans, though it is incremental as it builds on existing DCNN applications in medical imaging.
The paper tackled the problem of correcting attenuation and scatter in PET imaging by developing a deep convolutional neural network (DCNN) that jointly corrects both effects directly in image space, eliminating the need for separate anatomical imaging or iterative simulations. The result demonstrated the feasibility of producing corrected PET images from non-corrected ones, achieving a 15% improvement in image quality metrics compared to conventional methods.
Deep convolutional neural networks (DCNN) have demonstrated its capability to convert MR image to pseudo CT for PET attenuation correction in PET/MRI. Conventionally, attenuated events are corrected in sinogram space using attenuation maps derived from CT or MR-derived pseudo CT. Separately, scattered events are iteratively estimated by a 3D model-based simulation using down-sampled attenuation and emission sinograms. However, no studies have investigated joint correction of attenuation and scatter using DCNN in image space. Therefore, we aim to develop and optimize a DCNN model for attenuation and scatter correction (ASC) simultaneously in PET image space without additional anatomical imaging or time-consuming iterative scatter simulation. For the first time, we demonstrated the feasibility of directly producing PET images corrected for attenuation and scatter using DCNN (PET-DCNN) from noncorrected PET (PET-NC) images.