Conditional Generative Adversarial Networks (cGANs) aided motion correction of dynamic ¹⁸F-FDG PET brain studies

Abstract

This work set out to develop a motion correction approach aided by conditional generative adversarial network (cGAN) methodology that allows reliable, data-driven determination of involuntary subject motion during dynamic ¹⁸F-FDG brain studies. Methods: Ten healthy volunteers (5M/5F, 27 ± 7 years, 70 ± 10 kg) underwent a test-retest ¹⁸F-FDG PET/MRI examination of the brain (N = 20). The imaging protocol consisted of a 60-min PET list-mode acquisition contemporaneously acquired with MRI, including MR navigators and a 3D time-of-flight MR-angiography sequence. Arterial blood samples were collected as a reference standard representing the arterial input function (AIF). Training of the cGAN was performed using 70% of the total data sets (N = 16, randomly chosen), which was corrected for motion using MR navigators. The resulting cGAN mappings (between individual frames and the reference frame (55-60min p.i.)) were then applied to the test data set (remaining 30%, N = 6), producing artificially generated low-noise images from early high-noise PET frames. These low-noise images were then co-registered to the reference frame, yielding 3D motion vectors. Performance of cGAN-aided motion correction was assessed by comparing the image-derived input function (IDIF) extracted from a cGAN-aided motion corrected dynamic sequence against the AIF based on the areas-under-the-curves (AUCs). Moreover, clinical relevance was assessed through direct comparison of the average cerebral metabolic rates of glucose (CMRGlc) values in grey matter (GM) calculated using the AIF and the IDIF. Results: The absolute percentage-difference between AUCs derived using the motion-corrected IDIF and the AIF was (1.2 ± 0.9) %. The GM CMRGlc values determined using these two input functions differed by less than 5% ((2.4 ± 1.7) %). Conclusion: A fully-automated data-driven motion compensation approach was established and tested for ¹⁸F-FDG PET brain imaging. cGAN-aided motion correction enables the translation of non-invasive clinical absolute quantification from PET/MR to PET/CT by allowing the accurate determination of motion vectors from the PET data itself.