CNN-Based PET Sinogram Repair to Mitigate Defective Block Detectors

TL;DR

This paper introduces a CNN-based method for repairing PET sinograms affected by defective detectors, significantly improving image quality and quantitative accuracy over previous techniques.

Contribution

The paper presents a novel deep learning approach for sinogram repair in PET imaging, addressing detector malfunctions more effectively than existing methods.

Findings

Outperforms previous methods in normalized mean squared error

Achieves higher structural similarity in reconstructed images

Improves quantitative accuracy in PET reconstructions

Abstract

Positron emission tomography (PET) scanners continue to increase sensitivity and axial coverage by adding an ever expanding array of block detectors. As they age, one or more block detectors may lose sensitivity due to a malfunction or component failure. The sinogram data missing as a result thereof can lead to artifacts and other image degradations. We propose to mitigate the effects of malfunctioning block detectors by carrying out sinogram repair using a deep convolutional neural network. Experiments using whole-body patient studies with varying amounts of raw data removed are used to show that the neural network significantly outperforms previously published methods with respect to normalized mean squared error for raw sinograms, a multi-scale structural similarity measure for reconstructed images and with regard to quantitative accuracy.