001038864 001__ 1038864
001038864 005__ 20250220092004.0
001038864 037__ $$aFZJ-2025-01680
001038864 041__ $$aGerman
001038864 1001_ $$0P:(DE-Juel1)200375$$aMasood, Anum$$b0$$eFirst author
001038864 1112_ $$a62. Jahrestagung der Deutschen Gesellschaft für Nuklearmedizin (DGN e. V.)$$cLeipzig$$d2024-04-10 - 2024-04-13$$gNuklearMedizin 2024$$wGermany
001038864 245__ $$aEnhancing Ultra-Low-Dose Brain PET/MRI Image Quality Using Deep Learning
001038864 260__ $$c2024
001038864 3367_ $$033$$2EndNote$$aConference Paper
001038864 3367_ $$2DataCite$$aOther
001038864 3367_ $$2BibTeX$$aINPROCEEDINGS
001038864 3367_ $$2DRIVER$$aconferenceObject
001038864 3367_ $$2ORCID$$aLECTURE_SPEECH
001038864 3367_ $$0PUB:(DE-HGF)6$$2PUB:(DE-HGF)$$aConference Presentation$$bconf$$mconf$$s1739281716_30399$$xAfter Call
001038864 520__ $$aAim:We developed a deep learning model to enhance the image quality of ultra-low dose brain positron emission tomography (PET). Significantly reducing the injected dose not only minimizes radiation risk in subjects but also provides options for scanning protocols, allowing e.g. for more follow-up studies. Methods:Our dataset comprises 196 brain PET/magnetic resonance (MRI) images (MPRAGE) of healthy volunteers of two sleep deprivation studies, scanned for 100 minutes each using the adenosine A1 receptor ligand [F-18]CPFPX (mean injected activity: 179.5 MBq, 10 MBq SD). From our dataset, low-dose images with Dose Reduction Factors (DRF) of 4, 10, 20, 50, and 100 were created by modifying the acquired listmode data, corresponding to injected activities of 45, 18, 9, 3.5 and 1.8 MBq.We first modified and trained a U-Net model using a dataset of 500 total-body [F-18]FDG PET/MRI images with the same DRFs as well as the corresponding full-dose images [1]. We then used a Transfer Learning approach to train the model with our data. 8 subjects were hold out for testing our model. For evaluation, we used peak signal-to-noise ratio (PSNR), Structural Similarity (SSIM), Contrast to Noise Ratio (CNR) and Normalized Mean Squared Error (NMSE).Results:Our model can synthesize enhanced low dose images that have considerably reduced noise compared to the low-dose PET image and resemble the standard-dose image. We achieved improved metrics compared to the original U-Net model with average PSNR of 28.02 (U-Net: 21.23), SSIM of 0.81 (U-Net: 0.53), CNR of 0.72 (U-Net: 0.61) and NMSE of 0.33 (U-Net: 0.67).Conclusions:Our results highlight the potential of our model for enhancing low-dose brain PET/MRI images, allowing for scans with reduced injected dose, shorter scan times or more follow-up studies. References:[1] S Xue et al., Eur J Nucl Med Mol I 49 (6), 1843 (2022).
001038864 536__ $$0G:(DE-HGF)POF4-5254$$a5254 - Neuroscientific Data Analytics and AI (POF4-525)$$cPOF4-525$$fPOF IV$$x0
001038864 7001_ $$0P:(DE-Juel1)177611$$aDrzezga, Alexander$$b1
001038864 7001_ $$0P:(DE-HGF)0$$aElmenhorst, E. M.$$b2
001038864 7001_ $$0P:(DE-Juel1)179271$$aFoerges, Anna Linea$$b3
001038864 7001_ $$0P:(DE-Juel1)165827$$aLange, Denise$$b4
001038864 7001_ $$0P:(DE-HGF)0$$aHennecke, E.$$b5
001038864 7001_ $$0P:(DE-HGF)0$$aBaur, D. M.$$b6
001038864 7001_ $$0P:(DE-Juel1)131691$$aKroll, Tina$$b7
001038864 7001_ $$0P:(DE-Juel1)166419$$aNeumaier, Bernd$$b8
001038864 7001_ $$0P:(DE-HGF)0$$aAeschbach, D.$$b9
001038864 7001_ $$0P:(DE-Juel1)131672$$aBauer, Andreas$$b10$$ufzj
001038864 7001_ $$0P:(DE-HGF)0$$aLandolt, H. P.$$b11
001038864 7001_ $$0P:(DE-Juel1)131679$$aElmenhorst, David$$b12
001038864 7001_ $$0P:(DE-Juel1)133864$$aBeer, Simone$$b13$$eCorresponding author
001038864 909CO $$ooai:juser.fz-juelich.de:1038864$$pVDB
001038864 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)177611$$aForschungszentrum Jülich$$b1$$kFZJ
001038864 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)179271$$aForschungszentrum Jülich$$b3$$kFZJ
001038864 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131691$$aForschungszentrum Jülich$$b7$$kFZJ
001038864 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)166419$$aForschungszentrum Jülich$$b8$$kFZJ
001038864 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131672$$aForschungszentrum Jülich$$b10$$kFZJ
001038864 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131679$$aForschungszentrum Jülich$$b12$$kFZJ
001038864 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)133864$$aForschungszentrum Jülich$$b13$$kFZJ
001038864 9131_ $$0G:(DE-HGF)POF4-525$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5254$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vDecoding Brain Organization and Dysfunction$$x0
001038864 9141_ $$y2024
001038864 920__ $$lyes
001038864 9201_ $$0I:(DE-Juel1)INM-2-20090406$$kINM-2$$lMolekulare Organisation des Gehirns$$x0
001038864 980__ $$aconf
001038864 980__ $$aVDB
001038864 980__ $$aI:(DE-Juel1)INM-2-20090406
001038864 980__ $$aUNRESTRICTED