Attenuation correction using 3D deep convolutional neural network for brain 18F-FDG PET/MR: Comparison with Atlas, ZTE and CT based attenuation correction

Autoři: Paul Blanc-Durand aff001;  Maya Khalife aff002;  Brian Sgard aff001;  Sandeep Kaushik aff003;  Marine Soret aff001;  Amal Tiss aff004;  Georges El Fakhri aff004;  Marie-Odile Habert aff001;  Florian Wiesinger aff006;  Aurélie Kas aff001
Působiště autorů: Nuclear Medicine Department, Groupe Hospitalier Pitié-Salpêtrière C. Foix, APHP, Paris, France aff001;  Centre de Neuroimagerie de Recherche (CENIR), Institut du Cerveau et de la Moëlle, Paris, France aff002;  GE Healthcare, Bangalore, India aff003;  Gordon Center for Medical Imaging, Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, United States of America aff004;  Laboratoire d’Imagerie Biomédicale, Sorbonne Université, Paris, France aff005;  GE Healthcare, Munich, Germany aff006
Vyšlo v časopise: PLoS ONE 14(10)
Kategorie: Research Article


One of the main technical challenges of PET/MRI is to achieve an accurate PET attenuation correction (AC) estimation. In current systems, AC is accomplished by generating an MRI-based surrogate computed tomography (CT) from which AC-maps are derived. Nevertheless, all techniques currently implemented in clinical routine suffer from bias. We present here a convolutional neural network (CNN) that generated AC-maps from Zero Echo Time (ZTE) MR images. Seventy patients referred to our institution for 18FDG-PET/MR exam (SIGNA PET/MR, GE Healthcare) as part of the investigation of suspected dementia, were included. 23 patients were added to the training set of the manufacturer and 47 were used for validation. Brain computed tomography (CT) scan, two-point LAVA-flex MRI (for atlas-based AC) and ZTE-MRI were available in all patients. Three AC methods were evaluated and compared to CT-based AC (CTAC): one based on a single head-atlas, one based on ZTE-segmentation and one CNN with a 3D U-net architecture to generate AC maps from ZTE MR images. Impact on brain metabolism was evaluated combining voxel and regions-of-interest based analyses with CTAC set as reference. The U-net AC method yielded the lowest bias, the lowest inter-individual and inter-regional variability compared to PET images reconstructed with ZTE and Atlas methods. The impact on brain metabolism was negligible with average errors of -0.2% in most cortical regions. These results suggest that the U-net AC is more reliable for correcting photon attenuation in brain FDG-PET/MR than atlas-AC and ZTE-AC methods.

Klíčová slova:

Cerebellum – Computed axial tomography – Imaging techniques – Magnetic resonance imaging – Neural networks – Neuroimaging – Positron emission tomography – Mastoid process


1. Chen KT, Salcedo S, Gong K, Chonde DB, Izquierdo-Garcia D, Drzezga AE, et al. An Efficient Approach to Perform MR-Assisted PET Data Optimization in Simultaneous PET/MR Neuroimaging Studies. Journal of Nuclear Medicine. 2018; p. jnumed.117.207142.

2. Martinez-Moller A, Souvatzoglou M, Delso G, Bundschuh RA, Chefd’hotel C, Ziegler SI, et al. Tissue Classification as a Potential Approach for Attenuation Correction in Whole-Body PET/MRI: Evaluation with PET/CT Data. Journal of Nuclear Medicine. 2009;50(4):520–526. doi: 10.2967/jnumed.108.054726 19289430

3. Liu F, Jang H, Kijowski R, Bradshaw T, McMillan AB. Deep Learning MR Imaging–Based Attenuation Correction for PET/MR Imaging. Radiology. 2017; p. 170700.

4. Khalifé M, Fernandez B, Jaubert O, Soussan M, Brulon V, Buvat I, et al. Subject-Specific Bone Attenuation Correction for Brain PET/MR: Can ZTE-MRI Substitute CT Scan Accurately? Physics in Medicine & Biology. 2017;62(19):7814–7832. doi: 10.1088/1361-6560/aa8851

5. Delso G, Wiesinger F, Sacolick LI, Kaushik SS, Shanbhag DD, Hullner M, et al. Clinical Evaluation of Zero-Echo-Time MR Imaging for the Segmentation of the Skull. Journal of Nuclear Medicine. 2015;56(3):417–422. doi: 10.2967/jnumed.114.149997 25678489

6. Gong K, Yang J, Kim K, El Fakhri G, Seo Y, Li Q. Attenuation Correction for Brain PET Imaging Using Deep Neural Network Based on Dixon and ZTE MR Images. Physics in Medicine and Biology. 2018. doi: 10.1088/1361-6560/aac763

7. Leynes AP, Yang J, Wiesinger F, Kaushik SS, Shanbhag DD, Seo Y, et al. Direct PseudoCT Generation for Pelvis PET/MRI Attenuation Correction Using Deep Convolutional Neural Networks with Multi-Parametric MRI: Zero Echo-Time and Dixon Deep pseudoCT (ZeDD-CT). Journal of Nuclear Medicine. 2017; p. jnumed.117.198051.

8. Ladefoged CN, Marner L, Hindsholm A, Law I, Højgaard L, Andersen FL. Deep Learning Based Attenuation Correction of PET/MRI in Pediatric Brain Tumor Patients: Evaluation in a Clinical Setting. Frontiers in Neuroscience. 2019;12. doi: 10.3389/fnins.2018.01005 30666184

9. Sekine T, Buck A, Delso G, Ter Voert EEGW, Huellner M, Veit-Haibach P, et al. Evaluation of Atlas-Based Attenuation Correction for Integrated PET/MR in Human Brain: Application of a Head Atlas and Comparison to True CT-Based Attenuation Correction. Journal of Nuclear Medicine: Official Publication, Society of Nuclear Medicine. 2016;57(2):215–220. doi: 10.2967/jnumed.115.159228

10. Wiesinger F, Sacolick LI, Menini A, Kaushik SS, Ahn S, Veit-Haibach P, et al. Zero TE MR Bone Imaging in the Head. Magnetic Resonance in Medicine. 2016;75(1):107–114. doi: 10.1002/mrm.25545 25639956

11. Delso G, Fernandez B, Wiesinger F, Jian Y, Bobb C, Jansen F. Repeatability of ZTE Bone Maps of the Head. IEEE Transactions on Radiation and Plasma Medical Sciences. 2018;2:244–249. doi: 10.1109/TRPMS.2017.2772329

12. Yang J, Wiesinger F, Kaushik S, Shanbhag D, Hope TA, Larson PEZ, et al. Evaluation of Sinus/Edge-Corrected Zero-Echo-Time-Based Attenuation Correction in Brain PET/MRI. Journal of Nuclear Medicine: Official Publication, Society of Nuclear Medicine. 2017;58(11):1873–1879. doi: 10.2967/jnumed.116.188268

13. Çiçek O, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O. 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer; 2016. p. 424–432.

14. Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer; 2015. p. 234–241.

15. Carney JPJ, Townsend DW, Rappoport V, Bendriem B. Method for Transforming CT Images for Attenuation Correction in PET/CT Imaging: Transforming CT Images for Attenuation Correction in PET/CT. Medical Physics. 2006;33(4):976–983.

16. Abraham A, Pedregosa F, Eickenberg M, Gervais P, Mueller A, Kossaifi J, et al. Machine Learning for Neuroimaging with Scikit-Learn. Frontiers in Neuroinformatics. 2014;8. doi: 10.3389/fninf.2014.00014 24600388

17. Sekine T, ter Voert EEGW, Warnock G, Buck A, Huellner M, Veit-Haibach P, et al. Clinical Evaluation of Zero-Echo-Time Attenuation Correction for Brain 18F-FDG PET/MRI: Comparison with Atlas Attenuation Correction. Journal of Nuclear Medicine. 2016;57(12):1927–1932. doi: 10.2967/jnumed.116.175398 27339875

18. Okazawa H, Tsujikawa T, Higashino Y, Kikuta KI, Mori T, Makino A, et al. No Significant Difference Found in PET/MRI CBF Values Reconstructed with CT-Atlas-Based and ZTE MR Attenuation Correction. EJNMMI Research. 2019;9(1):26. doi: 10.1186/s13550-019-0494-9 30888559

19. Kato T, Inui Y, Nakamura A, Ito K. Brain Fluorodeoxyglucose (FDG) PET in Dementia. Ageing Research Reviews. 2016;30:73–84. doi: 10.1016/j.arr.2016.02.003 26876244

20. Minoshima S, Frey KA, Foster NL, Kuhl DE. Preserved Pontine Glucose Metabolism in Alzheimer Disease: A Reference Region for Functional Brain Image (PET) Analysis. Journal of Computer Assisted Tomography. 1995 Jul-Aug;19(4):541–547. doi: 10.1097/00004728-199507000-00006 7622680

21. Cabello J, Lukas M, Rota Kops E, Ribeiro A, Shah NJ, Yakushev I, et al. Comparison between MRI-Based Attenuation Correction Methods for Brain PET in Dementia Patients. European Journal of Nuclear Medicine and Molecular Imaging. 2016;43(12):2190–2200. doi: 10.1007/s00259-016-3394-5 27094314

22. Hwang D, Kim KY, Kang SK, Seo S, Paeng JC, Lee DS, et al. Improving Accuracy of Simultaneously Reconstructed Activity and Attenuation Maps Using Deep Learning. Journal of Nuclear Medicine. 2018; p. jnumed.117.202317. doi: 10.2967/jnumed.117.202317 29449446

23. Malone IB, Ansorge RE, Williams GB, Nestor PJ, Carpenter TA, Fryer TD. Attenuation Correction Methods Suitable for Brain Imaging with a PET/MRI Scanner: A Comparison of Tissue Atlas and Template Attenuation Map Approaches. Journal of Nuclear Medicine: Official Publication, Society of Nuclear Medicine. 2011;52(7):1142–1149. doi: 10.2967/jnumed.110.085076

24. Ladefoged CN, Law I, Anazodo U, St Lawrence K, Izquierdo-Garcia D, Catana C, et al. A Multi-Centre Evaluation of Eleven Clinically Feasible Brain PET/MRI Attenuation Correction Techniques Using a Large Cohort of Patients. NeuroImage. 2017;147:346–359. doi: 10.1016/j.neuroimage.2016.12.010 27988322

25. Spuhler KD, Gardus J, Gao Y, DeLorenzo C, Parsey R, Huang C. Synthesis of Patient-Specific Transmission Image for PET Attenuation Correction for PET/MR Imaging of the Brain Using a Convolutional Neural Network’. Journal of Nuclear Medicine. 2018; p. jnumed.118.214320. doi: 10.2967/jnumed.118.214320 30166355

Článek vyšel v časopise


2019 Číslo 10
Nejčtenější tento týden