{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T13:45:13Z","timestamp":1792071913573,"version":"4.4.0"},"reference-count":28,"publisher":"Wiley","issue":"9","license":[{"start":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T00:00:00Z","timestamp":1789344000000},"content-version":"vor","delay-in-days":13,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100000070","name":"National Institute of Biomedical Imaging and Bioengineering","doi-asserted-by":"publisher","award":["R01EB030413"],"award-info":[{"award-number":["R01EB030413"]}],"id":[{"id":"10.13039\/100000070","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["U01AG082845"],"award-info":[{"award-number":["U01AG082845"]}],"id":[{"id":"10.13039\/100000049","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":[[2026,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Inter\u2010crystal scattering (ICS) is a fundamental limitation in ultra\u2010high resolution positron emission tomography (PET), particularly in light\u2010sharing detectors with small crystal elements, where frequent Compton scatter across neighboring crystals obscures the initial interaction position and degrades the spatial resolution, image contrast, and quantitative accuracy. In our previous work, a convolutional neural network, Recovery\u2010Net, was proposed and evaluated to recover the crystal location and depth\u2010of\u2010interaction (DOI) of the initial interaction in a light\u2010sharing depth\u2010encoding Prism\u2010PET detector using Monte Carlo (MC) simulations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>This work aims to develop and experimentally validate a scanner\u2010level ICS recovery framework for a light\u2010sharing depth\u2010encoding Prism\u2010PET prototype scanner using a diffusion model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We first developed a novel method to prepare the training dataset by combining scanner\u2010level simulations with experimental measurements. The resulting dataset comprises an 8 \u00d7 8 array of silicon photomultiplier (SiPM) signals for each ICS event with associated ground\u2010truth information, including crystal location, DOI, and deposited energy of the initial interaction. Using the SiPM signal patterns as input, we proposed a new diffusion\u2010driven and physics\u2010informed tripartite framework, named D3Recovery, to estimate the 3D position and deposited energy of the initial interaction. The previously proposed Recovery\u2010Net was also implemented and evaluated for comparison. An ultra\u2010micro Derenzo phantom and a 3D Hoffman brain phantom from the Prism\u2010PET prototype scanner experiment were used to evaluate the impact of ICS recovery on image quality.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Recovery\u2010Net and D3Recovery achieved crystal identification accuracies of 64.1% and 70.1% for ICS events, respectively, with D3Recovery further improving DOI estimation to a full width at half maximum (FWHM) of 3.6\u00a0mm compared with 5.1\u00a0mm for Recovery\u2010Net. Compared with center\u2010of\u2010gravity (CoG) positioning, D3Recovery reduced the mean crystal localization error from 2.18\u00a0mm to 0.99\u00a0mm and recovered the deposited energy with an error FWHM of 34.0\u00a0keV. For the ultra\u2010micro Derenzo phantom images, Recovery\u2010Net and D3Recovery increased peak\u2010to\u2010valley ratios by 13% and 24% for ICS events and by 14% and 17% for all events, respectively. For the Hoffman brain phantom, Recovery\u2010Net and D3Recovery reduced mean absolute error (MAE) by 15.53% and 17.84% for ICS events and by 16.22% and 18.63% for all events, while increasing structural similarity index measure (SSIM) by 14.59% and 15.60% for ICS events and by 4.60% and 4.75% for all events, respectively. In addition, standard deviation (SD) measured in a uniform region decreased by 12.56% and 20.88% for ICS events, and by 5.26% and 8.48% for all events with Recovery\u2010Net and D3Recovery, respectively.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Experimental results demonstrate that D3Recovery significantly improves crystal localization, DOI estimation, and reconstructed image quality in high\u2010resolution PET with small\u2010crystal, light\u2010sharing detectors, while providing a practical scanner\u2010level training dataset acquisition strategy for experimental deployment of AI\u2010based ICS recovery. By retaining a large fraction (\u223c70% in our case) of otherwise discarded coincidences, our results show that we achieve a favorable resolution\u2010sensitivity balance that is most beneficial in count\u2010limited, low\u2010dose imaging.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.70661","type":"journal-article","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T05:49:04Z","timestamp":1789451344000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Inter\u2010crystal scatter recovery of a light\u2010sharing depth\u2010encoding Prism\u2010PET prototype scanner using a diffusion model"],"prefix":"10.1002","volume":"53","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9198-5535","authenticated-orcid":false,"given":"Wanbin","family":"Tan","sequence":"first","affiliation":[{"name":"Department of Radiology Weill Cornell Medical College, Cornell University  New York New York USA"},{"name":"Department of Biomedical Engineering Stony Brook University  Stony Brook New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6836-9731","authenticated-orcid":false,"given":"Saurav","family":"Dosi","sequence":"additional","affiliation":[{"name":"Department of Radiology Weill Cornell Medical College, Cornell University  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soroush","family":"Shabani Sichani","sequence":"additional","affiliation":[{"name":"Department of Radiology Weill Cornell Medical College, Cornell University  New York New York USA"},{"name":"Department of Physics Cornell University  Ithaca New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8162-6026","authenticated-orcid":false,"given":"Yixin","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Radiology Weill Cornell Medical College, Cornell University  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2863-4243","authenticated-orcid":false,"given":"Zipai","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Radiology Weill Cornell Medical College, Cornell University  New York New York USA"},{"name":"Department of Radiation Oncology Icahn School of Medicine at Mount Sinai  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6945-0881","authenticated-orcid":false,"given":"Eric","family":"Petersen","sequence":"additional","affiliation":[{"name":"Department of Radiology Weill Cornell Medical College, Cornell University  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8987-3726","authenticated-orcid":false,"given":"Xinjie","family":"Zeng","sequence":"additional","affiliation":[{"name":"Department of Radiology Weill Cornell Medical College, Cornell University  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinyi","family":"Qi","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering University of California  Davis California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amir H.","family":"Goldan","sequence":"additional","affiliation":[{"name":"Department of Radiology Weill Cornell Medical College, Cornell University  New York New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,9,14]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/52\/13\/007"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ad19f1"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ac215d"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13534-024-00427-7"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNS.2015.2408333"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aabe3a"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab44f4"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/adfe32"},{"key":"e_1_2_8_10_1","unstructured":"BergerM HubbellJ SeltzerS et\u00a0al.NIST Standard Reference Database 8 (XGAM).National Institute of Standards and Technology;2010."},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab9f5c"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/accacb"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNS.2014.2372788"},{"key":"e_1_2_8_14_1","doi-asserted-by":"crossref","unstructured":"WuC LeeMS LevinCS Neural network\u2010based inter\u2010crystal scatter event positioning in a PET system design based on 3D position sensitive detectors.Paper presented at: 2020 IEEE nuclear science symposium and medical imaging conference (NSS\/MIC);2020","DOI":"10.1109\/NSS\/MIC42677.2020.9507821"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17095"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.119.239343"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14654"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16223"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17437"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.1715998"},{"key":"e_1_2_8_21_1","doi-asserted-by":"crossref","unstructured":"WangZ LiY ZengX PetersenE GoldanA Crystal identification for light\u2010sharing prism\u2010PET detectors.Paper presented at: 2023 IEEE Nuclear Science Symposium Medical Imaging Conference and International Symposium on Room\u2010Temperature Semiconductor Detectors (NSS MIC RTSD);2023.","DOI":"10.1109\/NSSMICRTSD49126.2023.10338651"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab8c91"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/49\/19\/007"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.15653"},{"issue":"2","key":"e_1_2_8_25_1","article-title":"Experimental scanner\u2010level inter\u2010crystal scatter recovery for TOF\u2010DOI prototype Prism\u2010PET brain scanner","volume":"65","author":"Wang Z","year":"2024","journal-title":"J Nucl Med"},{"key":"e_1_2_8_26_1","unstructured":"HoJ JainA AbbeelP.Denoising diffusion probabilistic models. In:Advances in Neural Information Processing Systems. Vol33.Curran Associates Inc;2020:6840\u20106851."},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aadac1"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/51\/11\/016"},{"key":"e_1_2_8_29_1","article-title":"Denoising diffusion implicit models","author":"Song J","year":"2020","journal-title":"arXiv"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70661","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.70661","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70661","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T12:53:52Z","timestamp":1792068832000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.70661"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":28,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["10.1002\/mp.70661"],"URL":"https:\/\/doi.org\/10.1002\/mp.70661","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"2026-01-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-13","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70661"}}