Deep-learning-based fast TOF-PET image reconstruction using direction information.

Kibo Ote,Fumio Hashimoto

doi:10.1007/s12194-022-00652-8

Abstract

Although deep learning for application in positron emission tomography (PET) image reconstruction has attracted the attention of researchers, the image quality must be further improved. In this study, we propose a novel convolutional neural network (CNN)-based fast time-of-flight PET (TOF-PET) image reconstruction method to fully utilize the direction information of coincidence events. The proposed method inputs view-grouped histo-images into a 3D CNN as a multi-channel image to use the direction information of such events. We evaluated the proposed method using Monte Carlo simulation data obtained from a digital brain phantom. Compared with a case without direction information, the peak signal-to-noise ratio and structural similarity were improved by 1.2dB and 0.02, respectively, at a coincidence time resolution of 300ps. The calculation times of the proposed method were significantly lower than those of a conventional iterative reconstruction. These results indicate that the proposed method improves both the speed and image quality of a TOF-PET image reconstruction.

Highlights

Positron emission tomography (PET) is a functional imaging tool for various medical applications, such as oncology, cardiology, and neurology [1]
The calculation times of the proposed method were significantly faster than the conventional iterative reconstruction. These results indicate that the proposed method improves both the speed and image quality of TOF-PET image reconstruction
The peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) increased as the number of views increased

Summary

Introduction

Positron emission tomography (PET) is a functional imaging tool for various medical applications, such as oncology, cardiology, and neurology [1]. It has a unique ability to quantitatively estimate radiotracer concentrations as low as picomolar concentrations; the radiotracer concentration cannot be directly imaged from a line of response measured by the coincidence detection of annihilation photons. An image reconstruction process is required to estimate the distribution of the radiotracer concentration. There are two main methods for image reconstruction: analytic and iterative methods [2]. The iterative method models the noise distribution and reconstructs an image by iterative updating. The iterative method improves the signalto-noise ratio (SNR) of the reconstructed image better than the analytic method; it is computationally expensive. An image reconstruction method that improves both the speed and SNR is desired

Methods

Results

Conclusion