{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T13:23:33Z","timestamp":1777555413359,"version":"3.51.4"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,1,28]],"date-time":"2022-01-28T00:00:00Z","timestamp":1643328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,1,28]],"date-time":"2022-01-28T00:00:00Z","timestamp":1643328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Digit Imaging"],"published-print":{"date-parts":[[2022,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Deep learning (DL) strategies applied to magnetic resonance (MR) images in positron emission tomography (PET)\/MR can provide synthetic attenuation correction (AC) maps, and consequently PET images, more accurate than segmentation or atlas-registration strategies. As first objective, we aim to investigate the best MR image to be used and the best point of the AC pipeline to insert the synthetic map in. Sixteen patients underwent a 18F-fluorodeoxyglucose (FDG) PET\/computed tomography (CT) and a PET\/MR brain study in the same day. PET\/CT images were reconstructed with attenuation maps obtained: (1) from CT (reference), (2) from MR with an atlas-based and a segmentation-based method and (3) with a 2D UNet trained on MR image\/attenuation map pairs. As for MR, T1-weighted and Zero Time Echo (ZTE) images were considered; as for attenuation maps, CTs and 511\u00a0keV low-resolution attenuation maps were assessed. As second objective, we assessed the ability of DL strategies to provide proper AC maps in presence of cranial anatomy alterations due to surgery. Three 11C-methionine (METH) PET\/MR studies were considered. PET images were reconstructed with attenuation maps obtained: (1) from diagnostic coregistered CT (reference), (2) from MR with an atlas-based and a segmentation-based method and (3) with 2D UNets trained on the sixteen FDG anatomically normal patients. Only UNets taking ZTE images in input were considered. FDG and METH PET images were quantitatively evaluated. As for anatomically normal FDG patients, UNet AC models generally provide an uptake estimate with lower bias than atlas-based or segmentation-based methods. The intersubject average bias on images corrected with UNet AC maps is always smaller than 1.5%, except for AC maps generated on too coarse grids. The intersubject bias variability is the lowest (always lower than 2%) for UNet AC maps coming from ZTE images, larger for other methods. UNet models working on MR ZTE images and generating synthetic CT or 511\u00a0keV low-resolution attenuation maps therefore provide the best results in terms of both accuracy and variability. As for METH anatomically altered patients, DL properly reconstructs anatomical alterations. Quantitative results on PET images confirm those found on anatomically normal FDG patients.<\/jats:p>","DOI":"10.1007\/s10278-021-00551-1","type":"journal-article","created":{"date-parts":[[2022,1,28]],"date-time":"2022-01-28T17:02:40Z","timestamp":1643389360000},"page":"432-445","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Evaluation of a 2D UNet-Based Attenuation Correction Methodology for PET\/MR Brain Studies"],"prefix":"10.1007","volume":"35","author":[{"given":"Luca","family":"Presotto","sequence":"first","affiliation":[]},{"given":"Valentino","family":"Bettinardi","sequence":"additional","affiliation":[]},{"given":"Matteo","family":"Bagnalasta","sequence":"additional","affiliation":[]},{"given":"Paola","family":"Scifo","sequence":"additional","affiliation":[]},{"given":"Annarita","family":"Savi","sequence":"additional","affiliation":[]},{"given":"Emilia Giovanna","family":"Vanoli","sequence":"additional","affiliation":[]},{"given":"Federico","family":"Fallanca","sequence":"additional","affiliation":[]},{"given":"Maria","family":"Picchio","sequence":"additional","affiliation":[]},{"given":"Daniela","family":"Perani","sequence":"additional","affiliation":[]},{"given":"Luigi","family":"Gianolli","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8394-0342","authenticated-orcid":false,"given":"Elisabetta","family":"De Bernardi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,28]]},"reference":[{"issue":"4","key":"551_CR1","doi-asserted-by":"publisher","first-page":"1408","DOI":"10.1002\/mp.12155","volume":"44","author":"X Han","year":"2017","unstructured":"Han X. MR\u2010based synthetic CT generation using a deep convolutional neural network method. Medical Physics 2017;44(4):1408-1419.","journal-title":"Medical Physics"},{"issue":"5","key":"551_CR2","doi-asserted-by":"publisher","first-page":"852","DOI":"10.2967\/jnumed.117.198051","volume":"59","author":"AP Leynes","year":"2018","unstructured":"Leynes A. P., Yang J., Wiesinger F., Kaushik S. S., Shanbhag D. D., Seo Y., Hope A.H., Larson P. E. Z. Zero-echo-time and Dixon deep pseudo-CT (ZeDD CT): direct generation of pseudo-CT images for pelvic PET\/MR attenuation correction using deep convolutional neural networks with multiparametric MR. Journal of Nuclear Medicine 2018;59(5):852-858.","journal-title":"Journal of Nuclear Medicine"},{"issue":"4","key":"551_CR3","doi-asserted-by":"publisher","first-page":"555","DOI":"10.2967\/jnumed.118.214320","volume":"60","author":"KD Spuhler","year":"2019","unstructured":"Spuhler K. D., Gardus J., Gao Y., DeLorenzo C., Parsey R., Huang C. Synthesis of patient-specific transmission data for PET attenuation correction for PET\/MR neuroimaging using a convolutional neural network. Journal of Nuclear Medicine 2019;60(4):555-560.","journal-title":"Journal of Nuclear Medicine"},{"key":"551_CR4","doi-asserted-by":"crossref","unstructured":"Blanc-Durand P., Khalife M., Sgard B., Kaushik S., Soret M., Tiss A., El Fakiri G., Habert M-O., Wiesinger F., Kas A. Attenuation correction using 3D deep convolutional neural network for brain 18F-FDG PET\/MR: Comparison with Atlas, ZTE and CT based attenuation correction. PloS one 2019;14(10):e0223141.","DOI":"10.1371\/journal.pone.0223141"},{"key":"551_CR5","doi-asserted-by":"crossref","unstructured":"Liu Y., Lei Y., Wang Y., Wang T., Ren L., Lin L., McDonald M., Curran W.J., Liu T., Zhou J., Yang X. MR-based treatment planning for proton radiotherapy: dosimetric validation of a deep learning-based liver synthetic CT generation method. Physics in Medicine & Biology 2019;64(14):145015.","DOI":"10.1088\/1361-6560\/ab25bc"},{"issue":"3","key":"551_CR6","doi-asserted-by":"publisher","first-page":"429","DOI":"10.2967\/jnumed.118.209288","volume":"60","author":"A Torrado-Carvajal","year":"2019","unstructured":"Torrado-Carvajal A., Vera-Olmos J., Izquierdo-Garcia D., Catalano O. A., Morales M. A., Margolin J.,Soricelli A., Salvatore M., Malpica N., Catana C. Dixon-VIBE deep learning (DIVIDE) pseudo-CT synthesis for pelvis PET\/MR attenuation correction. Journal of Nuclear Medicine 2019;60(3):429-435.","journal-title":"Journal of Nuclear Medicine"},{"key":"551_CR7","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.radonc.2019.03.026","volume":"136","author":"S Kazemifar","year":"2019","unstructured":"Kazemifar S., McGuire S., Timmerman R., Wardak Z., Nguyen D., Park Y., Jiang S., Owrangi A. MR-only brain radiotherapy: Assessing the dosimetric accuracy of synthetic CT images generated using a deep learning approach. Radiotherapy and Oncology 2019;136: 56-63.","journal-title":"Radiotherapy and Oncology"},{"key":"551_CR8","doi-asserted-by":"crossref","unstructured":"Yu B., Wang Y., Wang L., Shen D., Zhou L. Medical Image Synthesis via Deep Learning 2020:23\u201344. In: Lee G., Fujita H. (eds) Deep Learning in Medical Image Analysis. Advances in Experimental Medicine and Biology, vol 1213. Springer, Cham.","DOI":"10.1007\/978-3-030-33128-3_2"},{"issue":"2","key":"551_CR9","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1109\/TRPMS.2020.3009269","volume":"5","author":"JS Lee","year":"2020","unstructured":"Lee, J. S. A Review of Deep-Learning-Based Approaches for Attenuation Correction in Positron Emission Tomography. IEEE Transactions on Radiation and Plasma Medical Sciences 2020, 5(2), 160-184.","journal-title":"IEEE Transactions on Radiation and Plasma Medical Sciences"},{"issue":"12","key":"551_CR10","doi-asserted-by":"publisher","first-page":"1927","DOI":"10.2967\/jnumed.116.175398","volume":"57","author":"T Sekine","year":"2016","unstructured":"Sekine T., Ter Voert E. E., Warnock G., Buck A., Huellner M., Veit-Haibach P., Delso G. Clinical evaluation of zero-echo-time attenuation correction for brain 18F-FDG PET\/MR: comparison with atlas attenuation correction. Journal of Nuclear Medicine 2016;57(12):1927-1932.","journal-title":"Journal of Nuclear Medicine"},{"issue":"4","key":"551_CR11","doi-asserted-by":"publisher","first-page":"1440","DOI":"10.1002\/mrm.27134","volume":"80","author":"F Wiesinger","year":"2018","unstructured":"Wiesinger F., Bylund M., Yang J., Kaushik S., Shanbhag D., Ahn S., Jonsson J.H., Lundman J.A., Hope T., Nyholm T., Larson P., Cozzini C. Zero TE\u2010based pseudo\u2010CT image conversion in the head and its application in PET\/MR attenuation correction and MR\u2010guided radiation therapy planning. Magnetic Resonance in Medicine 2018;80(4):1440-1451.","journal-title":"Magnetic Resonance in Medicine"},{"issue":"13","key":"551_CR12","doi-asserted-by":"publisher","first-page":"2746","DOI":"10.1007\/s00259-019-04380-x","volume":"46","author":"H Arabi","year":"2019","unstructured":"Arabi H., Zeng G., Zheng G., Zaidi H. Novel adversarial semantic structure deep learning for MR-guided attenuation correction in brain PET\/MR. European Journal of Nuclear Medicine and Molecular Imaging 2019;46(13): 2746-2759.","journal-title":"European Journal of Nuclear Medicine and Molecular Imaging"},{"issue":"2","key":"551_CR13","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1109\/TRPMS.2020.2989073","volume":"5","author":"L Tao","year":"2021","unstructured":"Tao, L., Fisher, J., Anaya, E., Li, X., Levin, C. S. Pseudo CT image synthesis and bone segmentation from MR images using adversarial networks with residual blocks for MR-based attenuation correction of brain PET data. IEEE Transactions on Radiation and Plasma Medical Sciences 2021, 5(2), 193-201.","journal-title":"IEEE Transactions on Radiation and Plasma Medical Sciences"},{"key":"551_CR14","doi-asserted-by":"crossref","unstructured":"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 & Biology 2018;63(12):125011.","DOI":"10.1088\/1361-6560\/aac763"},{"issue":"5","key":"551_CR15","doi-asserted-by":"publisher","first-page":"1351","DOI":"10.1007\/s00259-020-05061-w","volume":"48","author":"K Gong","year":"2021","unstructured":"Gong, K., Han, P. K., Johnson, K. A., El Fakhri, G., Ma, C., Li, Q. Attenuation correction using deep Learning and integrated UTE\/multi-echo Dixon sequence: evaluation in amyloid and tau PET imaging. European Journal of Nuclear Medicine and Molecular Imaging 2021, 48(5), 1351-1361.","journal-title":"European Journal of Nuclear Medicine and Molecular Imaging"},{"key":"551_CR16","doi-asserted-by":"publisher","first-page":"211","DOI":"10.3389\/fphy.2019.00211","volume":"7","author":"G Schramm","year":"2019","unstructured":"Schramm G., Koole M., Willekens S., Rezaei A., Van Weehaeghe D., Delso G., Peeters R., Mertens N., Nuyts J., Van Laere K. Regional accuracy of ZTE-based attenuation correction in static [18 F] FDG and dynamic [18 F] PE2I brain PET\/MR. Frontiers in Physics 2019;7:211.","journal-title":"Frontiers in Physics"},{"key":"551_CR17","doi-asserted-by":"crossref","unstructured":"Ronneberger O., Fischer P., Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab N., Hornegger J., Wells W., Frangi A. (eds) Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015. MICCAI 2015:pp 234\u2013241. Lecture Notes in Computer Science, vol 9351. Springer, Cham.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"551_CR18","doi-asserted-by":"crossref","unstructured":"Varrone A., Asenbaum S., Vander Borght T., Booij J.,Nobili F.,N\u00e5gren K.,Darcourt J.,L Kapucu O.,Tatsch K.,Bartenstein P.,Van Laere K.,European Association of Nuclear Medicine Neuroimaging Committee. European Journal of Nuclear Medicine and Molecular Imaging 2009;36(12):2103\u20132110.","DOI":"10.1007\/s00259-009-1264-0"},{"key":"551_CR19","doi-asserted-by":"crossref","unstructured":"Friston K.J. Statistical Parametric Mapping. In:K\u00f6tter R. (eds) Neuroscience Databases. Springer, Boston, MA. Chapter 16:237\u2013250.","DOI":"10.1007\/978-1-4615-1079-6_16"},{"issue":"6","key":"551_CR20","doi-asserted-by":"publisher","first-page":"1310","DOI":"10.1109\/TMI.2010.2046908","volume":"29","author":"NJ Tustison","year":"2010","unstructured":"Tustison N.J.,Avants B.B., Cook P.A., Zheng Y., Egan A., Yushkevich P.A., Gee J.C. N4ITK: Improved N3 Bias Correction. IEEE Trans Med Imaging 2010;29(6):1310-1320.","journal-title":"IEEE Trans Med Imaging"},{"issue":"9","key":"551_CR21","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1016\/j.mri.2012.05.001","volume":"30","author":"A Fedorov","year":"2012","unstructured":"Fedorov A., Beichel R., Kalpathy-Cramer J., Finet J., Fillion-Robin J-C., Pujol S., Bauer C., Jennings D., Fennessy F.M., Sonka M., Buatti J., Aylward S.R., Miller J.V., Pieper S., Kikinis R.\u00a03D Slicer as an Image Computing Platform for the Quantitative Imaging Network.\u00a0Magn Reson Imaging. 2012;30(9):1323-1341.","journal-title":"Magn Reson Imaging."},{"issue":"1","key":"551_CR22","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1006\/nimg.2001.0978","volume":"15","author":"N Tzourio-Mazoyer","year":"2002","unstructured":"Tzourio-Mazoyer N., Landeau B., Papathanassiou D., Crivello F., Etard O., Delcroix N., Mazoyer B., Joliot M. Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MR single subject brain. NeuroImage 2002; 15(1):273-289.","journal-title":"NeuroImage"},{"issue":"2","key":"551_CR23","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s12021-016-9322-9","volume":"15","author":"L Presotto","year":"2017","unstructured":"Presotto L., Ballarini T., Caminiti S. P., Bettinardi V., Gianolli L., Perani D. Validation of 18 F\u2013FDG-PET Single-Subject Optimized SPM Procedure with Different PET Scanners. Neuroinformatics 2017; 15(2), 151-163.","journal-title":"Neuroinformatics"}],"container-title":["Journal of Digital Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-021-00551-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10278-021-00551-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-021-00551-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,31]],"date-time":"2022-05-31T16:39:16Z","timestamp":1654015156000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10278-021-00551-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,28]]},"references-count":23,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["551"],"URL":"https:\/\/doi.org\/10.1007\/s10278-021-00551-1","relation":{},"ISSN":["0897-1889","1618-727X"],"issn-type":[{"value":"0897-1889","type":"print"},{"value":"1618-727X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,28]]},"assertion":[{"value":"27 November 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 November 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 November 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 January 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The double study protocol was approved by the IRCCS San Raffaele Hospital local ethical committee.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval"}},{"value":"Patients signed a written informed consent form.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Participate"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}]}}