{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T14:01:53Z","timestamp":1789740113551,"version":"4.0.1"},"reference-count":27,"publisher":"Wiley","issue":"8","license":[{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100004809","name":"Financiadora de Estudos e Projetos","doi-asserted-by":"publisher","award":["03.24.0248.00"],"award-info":[{"award-number":["03.24.0248.00"]}],"id":[{"id":"10.13039\/501100004809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["J Applied Clin Med Phys"],"published-print":{"date-parts":[[2026,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Current bone scintigraphy protocols often demand full\u2010count, 10\u201315\u00a0min scans to preserve image quality, and existing deep\u2010learning (DL) denoisers typically need to be retrained or retuned for each camera manufacturer. We introduce a scanner\u2010agnostic adaptive\u2010diffusion U\u2010Net designed to reconstruct diagnostic\u2010grade images from half\u2010time or half\u2010dose acquisitions without scanner\u2010specific retraining.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A multi\u2010institutional retrospective set of 3635 studies from four gamma\u2010camera models was Poisson\u2010thinned to 10%\u201370% counts and partitioned for training\/validation\/testing. The network couples a U\u2010Net backbone to a trainable isotropic diffusion layer. Quantitative evaluation (SSIM, PSNR, LPIPS) used 182 test scans. Prospective validation in 60 patients, including 20 studies acquired on an unseen Philips BrightView scanner not represented in the training set, was performed, and images were rated by three blinded nuclear medicine physicians on a 5\u2010point Likert scale. Head\u2010to\u2010head comparisons evaluated the diagnostic fidelity of the DL approach.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      At 50% counts, DL reconstructions increased SSIM from 0.903\u00a0\u00b1\u00a00.045 to 0.963\u00a0\u00b1\u00a00.032 and PSNR from 30.50\u00a0\u00b1\u00a04.13\u00a0dB to 40.85\u00a0\u00b1\u00a04.55\u00a0dB compared with noisy images, while reducing LPIPS from 0.05\u00a0\u00b1\u00a00.01 to 0.03\u00a0\u00b1\u00a00.01 (\n                      <jats:italic>p<\/jats:italic>\n                      \u00a0&lt;\u00a00.001). Reader studies showed that double\u2010speed DL images achieved Likert scores comparable to standard acquisitions (4.4\u00a0\u00b1\u00a00.7\u00a0vs 4.5\u00a0\u00b1\u00a00.5), with no diagnostic discrepancies reported between DL and routine clinical images.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>In this multicenter, multi\u2010vendor study, the adaptive\u2010diffusion U\u2010Net effectively supported half\u2010time, and\/or lower\u2010activity whole\u2010body bone scintigraphy protocols while preserving diagnostic integrity across scanners and avoiding scanner\u2010specific retraining, supporting scalable, radiation\u2010sparing clinical adoption.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/acm2.70709","type":"journal-article","created":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T07:34:03Z","timestamp":1784705643000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Scanner\u2010agnostic artificial intelligence approach for fast bone scintigraphy"],"prefix":"10.1002","volume":"27","author":[{"given":"Vinicius de Oliveira","family":"Menezes","sequence":"first","affiliation":[{"name":"Department of Diagnostic Imaging, Nuclear Medicine Division Hospital das Cl\u00ednicas, Federal University of Pernambuco (HC\/UFPE\u2013HU Brasil)  Recife Pernambuco Brazil"},{"name":"Klar Intelig\u00eancia Artificial  Recife Pernambuco Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cleiton Cavalcante","family":"Queiroz","sequence":"additional","affiliation":[{"name":"Klar Intelig\u00eancia Artificial  Recife Pernambuco Brazil"},{"name":"Hospital Universit\u00e1rio Professor Alberto Antunes Universidade Federal de Alagoas (HUPAA\u2013UFAL\u2013HU Brasil)  Macei\u00f3 Alagoas Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ant\u00f4nio Augusto Silva","family":"Oliveira","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Imaging, Nuclear Medicine Division Hospital das Cl\u00ednicas, Federal University of Pernambuco (HC\/UFPE\u2013HU Brasil)  Recife Pernambuco Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aur\u00edlio Jos\u00e9 dos","family":"Santos Filho","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Imaging, Nuclear Medicine Division Hospital das Cl\u00ednicas, Federal University of Pernambuco (HC\/UFPE\u2013HU Brasil)  Recife Pernambuco Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3007-3290","authenticated-orcid":false,"given":"Allisson Francisco","family":"de Morais","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Imaging, Nuclear Medicine Division Hospital das Cl\u00ednicas, Federal University of Pernambuco (HC\/UFPE\u2013HU Brasil)  Recife Pernambuco Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adriano de Oliveira","family":"Vig\u00e1rio","sequence":"additional","affiliation":[{"name":"N\u00facleo Diagn\u00f3stico  Maring\u00e1 Paran\u00e1 Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria Eduarda","family":"Flamini","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Imaging, Nuclear Medicine Division Hospital das Cl\u00ednicas, Federal University of Pernambuco (HC\/UFPE\u2013HU Brasil)  Recife Pernambuco Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felipe Alves","family":"Mourato","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Imaging, Nuclear Medicine Division Hospital das Cl\u00ednicas, Federal University of Pernambuco (HC\/UFPE\u2013HU Brasil)  Recife Pernambuco Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tsang Ing","family":"Ren","sequence":"additional","affiliation":[{"name":"Centro de Inform\u00e1tica Universidade Federal de Pernambuco (CIn\u2010UFPE)  Recife Pernambuco Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcos Ant\u00f4nio D\u00f3rea","family":"Machado","sequence":"additional","affiliation":[{"name":"Klar Intelig\u00eancia Artificial  Recife Pernambuco Brazil"},{"name":"Hospital Universit\u00e1rio Professor Edgard Santos Universidade Federal da Bahia (HUPES\u2013UFBA\u2013HU Brasil)  Salvador Bahia Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,7,22]]},"reference":[{"key":"e_1_2_13_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00259\u2010016\u20103410\u2010x"},{"key":"e_1_2_13_3_1","doi-asserted-by":"publisher","DOI":"10.2967\/jnmt.118.218750"},{"key":"e_1_2_13_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12149\u2010018\u20101232\u20104"},{"key":"e_1_2_13_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2022.06.008"},{"key":"e_1_2_13_6_1","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.119.229758"},{"key":"e_1_2_13_7_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics14242686"},{"key":"e_1_2_13_8_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4939875"},{"key":"e_1_2_13_9_1","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume":"34","author":"Dhariwal P","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_13_10_1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho J","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_13_11_1","unstructured":"ZamoraJC Cruz VargasJA TickooO \u201cAdaptive convolutional neural networks.\u201d [Online]. Available:https:\/\/arxiv.org\/abs\/1803.02742"},{"key":"e_1_2_13_12_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17123"},{"key":"e_1_2_13_13_1","doi-asserted-by":"crossref","unstructured":"ChowdaryGJ YinZ \u201cDiffusion transformer U\u2010Net for medical image segmentation \u201d Paper presented at: theInternational Conference on Medical Image Computing and Computer\u2010Assisted Intervention (MICCAI) 2023 622\u2010631.","DOI":"10.1007\/978-3-031-43901-8_59"},{"key":"e_1_2_13_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105012"},{"key":"e_1_2_13_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.nima.2022.167003"},{"key":"e_1_2_13_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2024.3507831"},{"key":"e_1_2_13_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108197"},{"key":"e_1_2_13_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_2_13_19_1","doi-asserted-by":"publisher","DOI":"10.1049\/el:20080522"},{"key":"e_1_2_13_20_1","doi-asserted-by":"crossref","unstructured":"HoreA ZiouD.Image quality metrics: pSNR vs. SSIM. Paper presented at: the20th International Conference on Pattern Recognition (ICPR) 2010 2366\u20102369.","DOI":"10.1109\/ICPR.2010.579"},{"key":"e_1_2_13_21_1","doi-asserted-by":"crossref","unstructured":"ZhangR IsolaP EfrosAA ShechtmanE WangO.The unreasonable effectiveness of deep features as a perceptual metric. Paper presented at: theIEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018 586\u2010595.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_2_13_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11063\u2010015\u20109472\u20109"},{"key":"e_1_2_13_23_1","doi-asserted-by":"crossref","unstructured":"PeeblesW XieS. \u201cScalable diffusion models with transformers \u201d Paper presented at:the IEEE\/CVF International Conference on Computer Vision (ICCV) 2023 4195\u20104205.","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_2_13_24_1","unstructured":"XieH.Dose\u2010aware diffusion model for 3D low\u2010dose PET: multi\u2010institutional validation with reader study and real low\u2010dose data. [Online]. Available:https:\/\/arxiv.org\/abs\/2405.12996"},{"key":"e_1_2_13_25_1","doi-asserted-by":"crossref","unstructured":"HanT.On instabilities of unsupervised denoising diffusion models in magnetic resonance imaging reconstruction. Paper presented at:the International Conference on Medical Image Computing and Computer\u2010Assisted Intervention (MICCAI) 2024 509\u2010517.","DOI":"10.1007\/978-3-031-72104-5_49"},{"key":"e_1_2_13_26_1","doi-asserted-by":"crossref","unstructured":"PfaffL.No\u2010New\u2010Denoiser: a critical analysis of diffusion models for medical image denoising. Paper presented at:the International Conference on Medical Image Computing and Computer\u2010Assisted Intervention (MICCAI) 2024 568\u2010578.","DOI":"10.1007\/978-3-031-72117-5_53"},{"key":"e_1_2_13_27_1","unstructured":"Society of Nuclear Medicine and Molecular Imaging.Imminent 99Mo\/99mTc shortage due to European reactor restart delay. [Online]. Available:https:\/\/snmmi.org\/Web\/News\/Articles\/Imminent\u2010Mo\u201099\u2010Tc\u201099m\u2010Shortage\u2010Due\u2010to\u2010European\u2010Reactor\u2010Restart\u2010Delay.aspx"},{"key":"e_1_2_13_28_1","doi-asserted-by":"crossref","unstructured":"AlizadehN CastorF. \u201cGreen AI: a preliminary empirical study on energy consumption in DL models across different runtime infrastructures \u201d Paper presented at:the IEEE\/ACM 3rd International Conference on AI Engineering\u2014Software Engineering for AI (CAIN) 2024 134\u2010139.","DOI":"10.1145\/3644815.3644967"}],"container-title":["Journal of Applied Clinical Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acm2.70709","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/acm2.70709","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acm2.70709","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T13:07:39Z","timestamp":1789736859000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/acm2.70709"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,22]]},"references-count":27,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["10.1002\/acm2.70709"],"URL":"https:\/\/doi.org\/10.1002\/acm2.70709","archive":["Portico"],"relation":{},"ISSN":["1526-9914","1526-9914"],"issn-type":[{"value":"1526-9914","type":"print"},{"value":"1526-9914","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,22]]},"assertion":[{"value":"2025-12-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-01","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70709"}}