{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T16:21:53Z","timestamp":1790612513283,"version":"4.1.0"},"reference-count":44,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T00:00:00Z","timestamp":1704844800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["SNSF 320030_176052"],"award-info":[{"award-number":["SNSF 320030_176052"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2024,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Attenuation and scatter correction is crucial for quantitative positron emission tomography (PET) imaging. Direct attenuation correction (AC) in the image domain using deep learning approaches has been recently proposed for combined PET\/MR and standalone PET modalities lacking transmission scanning devices or anatomical imaging.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>In this study, different input settings were considered in the model training to investigate deep learning\u2010based AC in the image space.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      Three different deep learning methods were developed for direct AC in the image space: (i) use of non\u2010attenuation\u2010corrected PET images as input (NonAC\u2010PET), (ii) use of attenuation\u2010corrected PET images with a simple two\u2010class AC map (composed of soft\u2010tissue and background air) obtained from NonAC\u2010PET images (PET segmentation\u2010based AC [SegAC\u2010PET]), and (iii) use of both NonAC\u2010PET and SegAC\u2010PET images in a Double\u2010Channel fashion to predict ground truth attenuation corrected PET images with Computed Tomography images (CTAC\u2010PET). Since a simple two\u2010class AC map (generated from NonAC\u2010PET images) can easily be generated, this work assessed the added value of incorporating SegAC\u2010PET images into direct AC in the image space. A 4\u2010fold cross\u2010validation scheme was adopted to train and evaluate the different models based using 80 brain\n                      <jats:sup>18<\/jats:sup>\n                      F\u2010Fluorodeoxyglucose PET\/CT images. The voxel\u2010wise and region\u2010wise accuracy of the models were examined via measuring the standardized uptake value (SUV) quantification bias in different regions of the brain.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The overall root mean square error (RMSE) for the Double\u2010Channel setting was 0.157\u00a0\u00b1\u00a00.08 SUV in the whole brain region, while RMSEs of 0.214\u00a0\u00b1\u00a00.07 and 0.189\u00a0\u00b1\u00a00.14 SUV were observed in NonAC\u2010PET and SegAC\u2010PET models, respectively. A mean SUV bias of 0.01\u00a0\u00b1\u00a00.26% was achieved by the Double\u2010Channel model regarding the activity concentration in cerebellum region, as opposed to 0.08\u00a0\u00b1\u00a00.28% and 0.05\u00a0\u00b1\u00a00.28% SUV biases for the network that uniquely used NonAC\u2010PET or SegAC\u2010PET as input, respectively. SegAC\u2010PET images with an SUV bias of \u20101.15\u00a0\u00b1\u00a00.54%, served as a benchmark for clinically accepted errors. In general, the Double\u2010Channel network, relying on both SegAC\u2010PET and NonAC\u2010PET images, outperformed the other AC models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Since the generation of two\u2010class AC maps from non\u2010AC PET images is straightforward, the current study investigated the potential added value of incorporating SegAC\u2010PET images into a deep learning\u2010based direct AC approach. Altogether, compared with models that use only NonAC\u2010PET and SegAC\u2010PET images, the Double\u2010Channel deep learning network exhibited superior attenuation correction accuracy.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.16914","type":"journal-article","created":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T06:54:32Z","timestamp":1704869672000},"page":"870-880","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Strategies for deep learning\u2010based attenuation and scatter correction of brain\n                    <sup>18<\/sup>\n                    F\u2010FDG PET images in the image domain"],"prefix":"10.1002","volume":"51","author":[{"given":"Reza","family":"Jahangir","sequence":"first","affiliation":[{"name":"Department of Medical Radiation Engineering Shahid Beheshti University  Tehran Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alireza","family":"Kamali\u2010Asl","sequence":"additional","affiliation":[{"name":"Department of Medical Radiation Engineering Shahid Beheshti University  Tehran Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hossein","family":"Arabi","sequence":"additional","affiliation":[{"name":"Division of Nuclear Medicine and Molecular Imaging Geneva University Hospital  Geneva Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Habib","family":"Zaidi","sequence":"additional","affiliation":[{"name":"Division of Nuclear Medicine and Molecular Imaging Geneva University Hospital  Geneva Switzerland"},{"name":"Geneva University Neurocenter Geneva University  Geneva Switzerland"},{"name":"Department of Nuclear Medicine and Molecular Imaging University of Groningen University Medical Center Groningen  Groningen Netherlands"},{"name":"Department of Nuclear Medicine University of Southern Denmark  Odense Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,1,10]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"crossref","unstructured":"BrusaferriL BousseA EfthimiouN et\u00a0al.Potential benefits of incorporating energy information when estimating attenuation from PET data.Paper presented at: 2017 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS\/MIC); October 21\u201028 2017;Atlanta GA.","DOI":"10.1109\/NSSMIC.2017.8532765"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ac62fc"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRPMS.2020.2978449"},{"key":"e_1_2_8_5_1","doi-asserted-by":"crossref","unstructured":"HamillJJ.Phantom evaluation of energy\u2010based scatter estimation in an SiPM PET scanner.Paper presented at: 2020 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS\/MIC); October 31\u2010November 7 2020;Boston MA.","DOI":"10.1109\/NSS\/MIC42677.2020.9507822"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/51\/11\/016"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4941014"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNS.2002.998689"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRPMS.2018.2846745"},{"issue":"192","key":"e_1_2_8_10_1","first-page":"14","article-title":"Technical advances in current PET and hybrid imaging systems","volume":"2","author":"Lee JS","year":"2010","journal-title":"Open Nucl Med J"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab0606"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/23.159770"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1097\/00004728-198204000-00022"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.116.188268"},{"key":"e_1_2_8_15_1","doi-asserted-by":"crossref","unstructured":"KopsER HerzogH Alternative methods for attenuation correction for PET images in MR\u2010PET scanners.Paper presented at: 2007 IEEE Nuclear Science Symposium Conference Record; October 26\u2010November 3 2007;Honolulu HI.","DOI":"10.1109\/NSSMIC.2008.4774281"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.115.159228"},{"key":"e_1_2_8_17_1","doi-asserted-by":"crossref","unstructured":"KobayashiT KitamuraK A solution for scaling problem in joint estimation of activity and attenuation.Paper presented at: 2017 IEEE nuclear science symposium and medical imaging conference (NSS\/MIC); October 21\u201028 2017;Atlanta GA.","DOI":"10.1109\/NSSMIC.2017.8532856"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40658-018-0225-8"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13550-020-00644-y"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12149-021-01611-w"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10151836"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-023-01984-7"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.117.202317"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-019-06229-1"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab652c"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNS.2013.2278624"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.29003"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.25039"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/56\/10\/013"},{"key":"e_1_2_8_30_1","doi-asserted-by":"crossref","unstructured":"BortolinK ArabiH ZaidiH Deep learning\u2010guided attenuation and scatter correction without using anatomical images in brain PET\/MRI.Paper presented at: 2019 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS\/MIC); October 26\u2010November 2 2019;Manchester UK.","DOI":"10.1109\/NSS\/MIC42101.2019.9059943"},{"key":"e_1_2_8_31_1","doi-asserted-by":"crossref","unstructured":"BurgosN ThielemansK CardosoMJ et\u00a0al.Effect of scatter correction when comparing attenuation maps: application to brain PET\/MR.Paper presented at: 2014 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS\/MIC); November 8\u201015 2014;Seattle WA.","DOI":"10.1109\/NSSMIC.2014.7430775"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/23.873020"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/56\/8\/004"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2018.01.025"},{"key":"e_1_2_8_35_1","doi-asserted-by":"crossref","unstructured":"LiW WangG FidonL OurselinS CardosoMJ VercauterenT On the compactness efficiency and representation of 3D convolutional networks: brain parcellation as a pretext task.Paper presented at: International conference on information processing in medical imaging 2017.","DOI":"10.1007\/978-3-319-59050-9_28"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.1006\/nimg.2001.0978"},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.1158\/0008-5472.CAN-18-0125"},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2020.117221"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0223141"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2018.01005"},{"key":"e_1_2_8_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-019-04380-x"},{"key":"e_1_2_8_42_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.2548468"},{"key":"e_1_2_8_43_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/abb02c"},{"key":"e_1_2_8_44_1","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2020200137"},{"key":"e_1_2_8_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNS.2007.901227"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.16914","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,8]],"date-time":"2024-02-08T15:18:27Z","timestamp":1707405507000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.16914"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,10]]},"references-count":44,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["10.1002\/mp.16914"],"URL":"https:\/\/doi.org\/10.1002\/mp.16914","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,10]]},"assertion":[{"value":"2023-01-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-12-06","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-01-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}