Independent attenuation correction of whole body [18F]FDG-PET using a deep learning approach with Generative Adversarial Networks

Karim Armanious,Christian La Fougère,Bin Yang,Helmut Dittmann,Sergios Gatidis,Tobias Hepp,Thomas Küstner,Konstantin Nikolaou

doi:10.1186/s13550-020-00644-y

Abstract

BackgroundAttenuation correction (AC) of PET data is usually performed using a second imaging for the generation of attenuation maps. In certain situations however—when CT- or MR-derived attenuation maps are corrupted or CT acquisition solely for the purpose of AC shall be avoided—it would be of value to have the possibility of obtaining attenuation maps only based on PET information. The purpose of this study was to thus develop, implement, and evaluate a deep learning-based method for whole body [18F]FDG-PET AC which is independent of other imaging modalities for acquiring the attenuation map.MethodsThe proposed method is investigated on whole body [18F]FDG-PET data using a Generative Adversarial Networks (GAN) deep learning framework. It is trained to generate pseudo CT images (CTGAN) based on paired training data of non-attenuation corrected PET data (PETNAC) and corresponding CT data. Generated pseudo CTs are then used for subsequent PET AC. One hundred data sets of whole body PETNAC and corresponding CT were used for training. Twenty-five PET/CT examinations were used as test data sets (not included in training). On these test data sets, AC of PET was performed using the acquired CT as well as CTGAN resulting in the corresponding PET data sets PETAC and PETGAN. CTGAN and PETGAN were evaluated qualitatively by visual inspection and by visual analysis of color-coded difference maps. Quantitative analysis was performed by comparison of organ and lesion SUVs between PETAC and PETGAN.ResultsQualitative analysis revealed no major SUV deviations on PETGAN for most anatomic regions; visually detectable deviations were mainly observed along the diaphragm and the lung border. Quantitative analysis revealed mean percent deviations of SUVs on PETGAN of − 0.8 ± 8.6% over all organs (range [− 30.7%, + 27.1%]). Mean lesion SUVs showed a mean deviation of 0.9 ± 9.2% (range [− 19.6%, + 29.2%]).ConclusionIndependent AC of whole body [18F]FDG-PET is feasible using the proposed deep learning approach yielding satisfactory PET quantification accuracy. Further clinical validation is necessary prior to implementation in clinical routine applications.

Highlights

Attenuation correction (AC) of Positron emission tomography (PET) data is usually performed using a second imaging for the generation of attenuation maps
In 3/25 data sets, significant differences were observed along the diaphragm with so-called banana artifacts in Attenuation-corrected PET using CT AC (PETAC) that were not present in PETGAN (Fig. 3)
In 16/25 data sets, minor differences were observed along the lung borders of the diaphragm, the mediastinum, and the chest wall with sharper contours in PETAC compared to PETGAN

Summary

Introduction

Attenuation correction (AC) of PET data is usually performed using a second imaging for the generation of attenuation maps. With the introduction of integrated PET/MR scanners, MR-based PET AC has been established as a further viable alternative providing satisfactory PET quantification accuracy [6] To this end, a number of methods have been proposed including segmentation-based PET AC [6], atlasbased PET AC [7], and recently deep learning-based PET AC [8, 9], in all cases using anatomic MR information for estimation of tissue attenuation coefficients. With respect to MR-based PET AC, MR image post processing for the purpose of PET AC may fail or generate secondary artifacts [11] In these situations, artifacts occur on reconstructed PET images that can lead to inaccurate PET quantification and may even disturb clinical interpretation of image data. In certain diagnostic situations or research settings, it is conceivable that PET examinations are acquired without the necessity of additional CT imaging, e.g., when performing repetitive PET scans for dosimetry or when examining volunteers or children; in these cases, radiation exposure could be reduced by omitting CT scans

Objectives

Methods

Results

Conclusion