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

Abstract

Background: Attenuation 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 [ 18 F]FDG-PET AC which is independent of other imaging modalities for acquiring the attenuation map. Methods: The proposed method is investigated on whole body [ 18 F]FDG-PET data using a Generative Adversarial Networks (GAN) deep learning framework. It is trained to generate pseudo CT images (CT GAN) based on paired training data of non-attenuation corrected PET data (PET NAC) and corresponding CT data. Generated pseudo CTs are then used for subsequent PET AC. One hundred data sets of whole body PET NAC 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 CT GAN resulting in the corresponding PET data sets PET AC and PET GAN. CT GAN and PET GAN 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 PET AC and PET GAN. Results: Qualitative analysis revealed no major SUV deviations on PET GAN 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 PET GAN 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%]). Conclusion: Independent AC of whole body [ 18 F]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.

A Review of Deep-Learning-Based Approaches for Attenuation Correction in Positron Emission Tomography

“…In the applications that do not require detailed anatomical information provided by CT, emission-only approaches, as described in the following sections, are effective for the realization of extremely low-dose studies. In particular, the DLbased conversion of non-attenuation-corrected PET to attenuation-corrected PET [29][30][31][32][33], in addition to the DLenhanced simultaneous activity and attenuation reconstruction [25][26][27][28], are suitable.…”

“…Alternative approaches are as follows: the derivation of pseudo-CT or attenuation-corrected PET images from non-attenuationcorrected (NAC) PET, and the improvement of the outputs of simultaneous activity and attenuation reconstruction using DL [25][26][27][28][29][30][31][32][33].…”

“…One of these emission-only approaches is utilizing NAC PET images as input to generate pseudo-CT [30,31,33] or attenuation-corrected PET images [29,32]. Liu et al trained a CAE modified to have a U-net-like structure through the addition of symmetrical short connections between encoding and decoding stages to generate pseudo-CT images from NAC PET by using 100 18 F-FDG brain PET/CT datasets [30].…”

“…25). Armanious et al also demonstrated the feasibility of generating pseudo-CT from NAC 18 F-FDG brain PET images for which they used generative adversarial networks (GANs) trained with 50 PET/CT datasets [33]. To translate 2D NAC PET slices into corresponding pseudo-CT slices, they utilized the conditional GAN framework.…”

“…Many DL studies were focused on the transformation of MR images into a synthetic pseudo-CT or μ-map [34][35][36][37][38][39][40][41][42][43][44]52]. Other approaches that are not dependent on the anatomical images (CT or MRI) can overcome limitations with respect to current CT-and MRI-based ACs and allow for more accurate PET quantification in stand-alone PET scanners for the realization of low radiation doses [25][26][27][28][29][30][31][32][33].…”