{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T20:57:04Z","timestamp":1790801824209,"version":"4.1.0"},"reference-count":29,"publisher":"Wiley","issue":"12","license":[{"start":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T00:00:00Z","timestamp":1763596800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T00:00:00Z","timestamp":1763596800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2025,12]]},"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:bold>\n : Recently, CT manufacturers have developed deep\u2010learning\u2010based reconstruction (DLR) algorithms for conventional and spectral CT images. On dual\u2010energy CT platforms, DLR algorithms have been developed in particular to reduce image noise in virtual monoenergetic images (VMIs), and to improve the accuracy of iodine concentrations on iodine maps.\n <\/jats:p>\n \n Purpose<\/jats:bold>\n : To assess the impact of a prototype, dedicated Spectral AI Reconstruction (SAIR) algorithm (Spectral Precise Image; Philips Healthcare) compared with a hybrid iterative reconstruction (HIR) algorithm (\u201cSpectral\u201d, Philips Healthcare) on the quality of low\u2010keV VMIs and iodine maps in abdomen\u2010pelvis CT conditions.\n <\/jats:p>\n \n Methods<\/jats:bold>\n : A spectral phantom was scanned on the dual\u2010layer spectral CT system at 120 kVp and a CTDI\n vol<\/jats:sub>\n of 12 mGy. VMIs at 40\/50\/60\/70\u00a0keV were generated using Level 4 of HIR algorithm and the five levels of SAIR algorithm named Smoother\/Smooth\/Standard\/Sharp\/Sharper. Noise power spectrum (NPS) was computed to assess noise magnitude and noise texture (\n f<\/jats:italic>\n av<\/jats:sub>\n ). Task\u2010based transfer function (TTF) was calculated to assess spatial resolution (f\n 50<\/jats:sub>\n ) on blood\u2010mimicking material plus iodine inserts at 2 and 4\u00a0mg\/mL. A detectability index (d\u2019) was computed to model the detection task of two contrast\u2010enhanced lesion according to keV. The accuracy of the iodine concentrations measured from six iodine inserts was calculated on iodine maps for HIR and all SAIR levels.\n <\/jats:p>\n \n Results<\/jats:bold>\n : For all keV, noise magnitude values were higher than with HIR using the Sharp (11.9\u00a0\u00b1\u00a05.6%;\n p<\/jats:italic>\n \u00a0>\u00a00.05) and Sharper (39.3\u00a0\u00b1\u00a07.3%;\n p<\/jats:italic>\n \u00a0=\u00a00.004) levels and lower than HIR for the other SAIR levels, decreasing from Standard (\u221215.3\u00a0\u00b1\u00a03.9%;\n p<\/jats:italic>\n \u00a0>\u00a00.05) to Smooth (\u221242.3\u00a0\u00b1\u00a02.2%;\n p<\/jats:italic>\n \u00a0=\u00a00.004) and Smoother levels (\u221270.5\u00a0\u00b1\u00a01.1%;\n p<\/jats:italic>\n \u00a0<\u00a00.001). For all energy levels,\n f<\/jats:italic>\n av<\/jats:sub>\n values were higher with all SAIR levels than with HIR, except when using the Smoother level. For both inserts, differences in f\n 50<\/jats:sub>\n values between the five SAIR levels and HIR did not exceed\u00a0\u00b1\u00a00.05\u00a0mm\n \u22121<\/jats:sup>\n . For all energy levels and both simulated lesions, d\u2019 values were only higher than with HIR when using the Standard (32.4\u00a0\u00b1\u00a07.5%;\n p<\/jats:italic>\n \u00a0>\u00a00.05), Smooth (95.6\u00a0\u00b1\u00a010.1%;\n p<\/jats:italic>\n \u00a0=\u00a00.008) and Smoother (303.4\u00a0\u00b1\u00a016.6%;\n p<\/jats:italic>\n \u00a0<\u00a00.001) levels. The accuracy of measured iodine values, calculated for each type of reconstruction, was similar (\n p<\/jats:italic>\n \u00a0>\u00a00.05) and equal to 0.25\u00a0\u00b1\u00a00.03\u00a0mg\/mL.\n <\/jats:p>\n \n Conclusion<\/jats:bold>\n : Compared to the HIR algorithm used in clinical practice for low\u2010keV VMIs, Standard, Smooth and Smoother levels of SAIR reduced image noise and improved the detectability of contrast\u2010enhanced lesions. Better noise texture was found only with the Standard and Smooth levels compared to HIR.\n <\/jats:p>","DOI":"10.1002\/mp.70093","type":"journal-article","created":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T05:20:27Z","timestamp":1763702427000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Impact of a prototype, dedicated AI\u2010based spectral image reconstruction algorithm on the quality of low\u2010keV virtual monoenergetic images and iodine maps: A phantom study"],"prefix":"10.1002","volume":"52","author":[{"given":"Jo\u00ebl","family":"Greffier","sequence":"first","affiliation":[{"name":"IMAGINE UR UM 103, Montpellier University, Department of Medical Imaging N\u00eemes University Hospital N\u00eemes France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Djamel","family":"Dabli","sequence":"additional","affiliation":[{"name":"IMAGINE UR UM 103, Montpellier University, Department of Medical Imaging N\u00eemes University Hospital N\u00eemes France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maxime","family":"Pastor","sequence":"additional","affiliation":[{"name":"IMAGINE UR UM 103, Montpellier University, Department of Medical Imaging N\u00eemes University Hospital N\u00eemes France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicolas","family":"Rossetto","sequence":"additional","affiliation":[{"name":"Philips Healthcare Suresnes France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elodie","family":"Dhombres","sequence":"additional","affiliation":[{"name":"IMAGINE UR UM 103, Montpellier University, Department of Medical Imaging N\u00eemes University Hospital N\u00eemes France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philippe","family":"Coulon","sequence":"additional","affiliation":[{"name":"Philips Healthcare Suresnes France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jean\u2010Paul","family":"Beregi","sequence":"additional","affiliation":[{"name":"IMAGINE UR UM 103, Montpellier University, Department of Medical Imaging N\u00eemes University Hospital N\u00eemes France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,11,20]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2015142631"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11547\u2010019\u201001107\u20108"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.diii.2022.11.003"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1148\/rg.343135041"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1097\/RCT.0000000000000546"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.14131480"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010021\u201090508\u20109"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330\u2010020\u201007379\u20103"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00261\u2010020\u201002888\u20107"},{"key":"e_1_2_10_11_1","article-title":"Deep learning spectral CT\u2014Faster, easier and more intelligent","author":"Boedeker KL","year":"2020","journal-title":"Whitepaper\u2014Canon Medical Systems"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2020.12.018"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.21037\/qims\u201021\u2010708"},{"key":"e_1_2_10_14_1","unstructured":"ThibaultJB NettB TangJ LiuE TrueFidelity\u2122 for Gemstone\u2122 Spectral Imaging.A new generation of spectral imaging powered by deep learning.Technical white paper on deep learning image reconstruction for spectral imaging. GE Healthcare.2021."},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17651"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.15558"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16300"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2023.3334488"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3449817"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16411"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.21037\/qims.2018.11.12"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.15807"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.diii.2022.05.007"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.diii.2024.02.009"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13763"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4903899"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1364\/OE.11.000460"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.diii.2024.11.003"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330\u2010020\u201007671\u20102"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4725171"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70093","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.70093","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70093","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T07:39:25Z","timestamp":1768203565000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.70093"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,20]]},"references-count":29,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["10.1002\/mp.70093"],"URL":"https:\/\/doi.org\/10.1002\/mp.70093","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,20]]},"assertion":[{"value":"2025-07-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70093"}}