Effect of PET-MR Inconsistency in the Kernel Image Reconstruction Method.

Daniel Deidda,Nikos Efthimiou,Robert G Aykroyd,N A Karakatsanis,Philip M Robson,Charalampos Tsoumpas,Zahi A Fayad

doi:10.1109/trpms.2018.2884176

Daniel Deidda, Nikos Efthimiou + Show 5 more

Open Access

https://doi.org/10.1109/trpms.2018.2884176

Copy DOI

Abstract

Anatomically-driven image reconstruction algorithms have become very popular in positron emission tomography (PET) where they have demonstrated improved image resolution and quantification. This work, consider the effect of spatial inconsistency between MR and PET images in hot and cold regions of the PET image. We investigate these effects on the kernel method from machine learning, in particular, the hybrid kernelized expectation maximization (HKEM). These were applied to Jaszczak phantom and patient data acquired with the Biograph Siemens mMR. The results show that even a small shift can cause a significant change in activity concentration. In general, the PET-MR inconsistencies can induce the partial volume effect, more specifically the 'spill-in' of the affected cold regions and the 'spill-out' from the hot regions. The maximum change was about 100% for the cold region and 10% for the hot lesion using KEM, against the 37% and 8% obtained with HKEM. The findings of this work suggest that including PET information in the kernel enhances the flexibility of the reconstruction in case of spatial inconsistency. Nevertheless, accurate registration and choice of the appropriate MR image for the creation of the kernel is essential to avoid artifacts, blurring, and bias.

Highlights

M ACHINE learning techniques are being frequently exploited for positron emission tomography (PET) image reconstruction [1]
We show the effect on the PET image of PET-MR inconsistencies, for PET cold and hot regions that are crossed by MR regions
We show the effect of the anatomically driven kernel method on the PET reconstructed images, with a focus on those occasions where MR and PET information do not match

Summary

Introduction

M ACHINE learning techniques are being frequently exploited for positron emission tomography (PET) image reconstruction [1]. Techniques for PET image de-noising involving neural network approaches have been proposed [2], [3], as well as deep learning [4] and support vector machine [5] techniques. The latter with the kernel method has been frequently used to include anatomical information in the reconstruction [6]–[9]. There are two different ways of including anatomical information in the reconstruction algorithm: 1) Bayesian techniques and 2) the kernel method. The kernel method can be divided into hybrid [7], [8], where the kernel matrix is extracted from more than one source (for example, PET and MR) and nonhybrid [5], [6], [9], [25], [26], where the kernel is estimated from one source

Objectives

Methods

Results

Discussion

Conclusion