{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T04:09:34Z","timestamp":1792037374051,"version":"4.4.0"},"reference-count":37,"publisher":"Wiley","issue":"10","license":[{"start":{"date-parts":[[2022,8,28]],"date-time":"2022-08-28T00:00:00Z","timestamp":1661644800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01 EB028590"],"award-info":[{"award-number":["R01 EB028590"]}],"id":[{"id":"10.13039\/100000002","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":[[2022,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>Dual\u2010energy CT with virtual noncalcium (VNCa) images allows the evaluation of focal intramedullary bone marrow involvement in patients with multiple myeloma. However, current commercial VNCa techniques suffer from excessive image noise and artifacts due to material decomposition used in synthesizing VNCa images.<\/jats:p><\/jats:sec><jats:sec><jats:title>Objectives<\/jats:title><jats:p>In this work, we aim to improve VNCa image quality for the assessment of focal multiple myeloma, using an <jats:italic>A<\/jats:italic>rtificial intelligence based <jats:italic>G<\/jats:italic>eneralizable <jats:italic>A<\/jats:italic>lgorithm for mul<jats:italic>T<\/jats:italic>i\u2010<jats:italic>E<\/jats:italic>nergy CT (AGATE) method.<\/jats:p><\/jats:sec><jats:sec><jats:title>Materials and methods<\/jats:title><jats:p>AGATE method used a custom dual\u2010task convolutional neural network (CNN) that concurrently carries out material classification and quantification. The material classification task provided an auxiliary regularization to the material quantification task. CNN parameters were optimized using custom loss functions that involved cross\u2010entropy, physics\u2010informed constraints, structural redundancy in spectral and material images, and texture information in spectral images. For training data, CT phantoms (diameters 30 to 45\u00a0cm)\u00a0with\u00a0tissue\u2010mimicking inserts were scanned on a third generation dual\u2010source CT system. Scans were performed at routine dose and half of the routine dose. Small image patches (i.e., 40 \u00d7 40 pixels) of tissue\u2010mimicking inserts with known basis material densities were extracted for training samples. Numerically simulated insert materials with various shapes increased diversity of training samples. Generalizability of AGATE was evaluated using CT images from phantoms and patients. In phantoms, material decomposition accuracy was estimated using mean\u2010absolute\u2010percent\u2010error (MAPE), using physical inserts that were not used during the training. Noise power spectrum (NPS) and modulation transfer function (MTF) were compared across phantom sizes and radiation dose levels. Five patients with multiple myeloma underwent dual\u2010energy CT, with VNCa images generated using a commercial method and AGATE. Two fellowship\u2010trained musculoskeletal radiologists reviewed the VNCa images (commercial and AGATE) side\u2010by\u2010side using a dual\u2010monitor display, blinded to VNCa type, rating the image quality for focal multiple myeloma lesion visualization using a 5\u2010level Likert comparison scale (\u22122\u00a0=\u00a0worse visualization and diagnostic confidence, \u22121\u00a0=\u00a0worse visualization but equivalent diagnostic confidence, 0\u00a0=\u00a0equivalent visualization and diagnostic confidence, 1\u00a0=\u00a0improved visualization but equivalent diagnostic confidence, 2\u00a0=\u00a0improved visualization and diagnostic confidence). A post hoc assignment of comparison ratings was performed to rank AGATE images in comparison to commercial ones.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>AGATE demonstrated consistent material quantification accuracy across phantom sizes and radiation dose levels, with MAPE ranging from 0.7% to 4.4% across all testing materials. Compared to commercial VNCa images, the AGATE\u2010synthesized VNCa images yielded considerably lower image noise (50\u201377% noise reduction) without compromising noise texture or spatial resolution across different phantom sizes and two radiation doses. AGATE VNCa images had markedly reduced area under NPS curves and maintained NPS peak frequency (0.7 lp\/cm to 1.0 lp\/cm), with similar MTF curves (50% MTF at 3.0 lp\/cm). In patients, AGATE demonstrated reduced image noise and artifacts with improved delineation of focal multiple myeloma lesions (all readers comparison scores indicating improved overall diagnostic image quality [scores 1 or 2]).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>AGATE demonstrated reduced noise and artifacts in VNCa images and ability to improve visualization of bone marrow lesions for assessing multiple myeloma.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.15934","type":"journal-article","created":{"date-parts":[[2022,8,19]],"date-time":"2022-08-19T11:44:47Z","timestamp":1660909487000},"page":"6346-6358","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Deep learning\u2010based virtual noncalcium imaging in multiple myeloma using dual\u2010energy CT"],"prefix":"10.1002","volume":"49","author":[{"given":"Hao","family":"Gong","sequence":"first","affiliation":[{"name":"Department of Radiology Mayo Clinic  Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francis I.","family":"Baffour","sequence":"additional","affiliation":[{"name":"Department of Radiology Mayo Clinic  Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katrina N.","family":"Glazebrook","sequence":"additional","affiliation":[{"name":"Department of Radiology Mayo Clinic  Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicholas G.","family":"Rhodes","sequence":"additional","affiliation":[{"name":"Department of Radiology Mayo Clinic  Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christin A.","family":"Tiegs\u2010Heiden","sequence":"additional","affiliation":[{"name":"Department of Radiology Mayo Clinic  Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jamison E.","family":"Thorne","sequence":"additional","affiliation":[{"name":"Department of Radiology Mayo Clinic  Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joselle M.","family":"Cook","sequence":"additional","affiliation":[{"name":"Department of Medicine, Division of Hematology Mayo Clinic  Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaji","family":"Kumar","sequence":"additional","affiliation":[{"name":"Department of Medicine, Division of Hematology Mayo Clinic  Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joel G.","family":"Fletcher","sequence":"additional","affiliation":[{"name":"Department of Radiology Mayo Clinic  Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cynthia H.","family":"McCollough","sequence":"additional","affiliation":[{"name":"Department of Radiology Mayo Clinic  Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Leng","sequence":"additional","affiliation":[{"name":"Department of Radiology Mayo Clinic  Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,8,28]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1200\/EDBK_205583(38)"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1111\/bjh.12007"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(14)70442-5"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1182\/blood-2018-08-825356"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(19)30309-2"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2014.02.008"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1553-2712.2008.00192.x"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2017170281"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-018-5537-5"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.14.12613"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.19.21095"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.13122577"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1148\/rg.2021200102"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.18.19933"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2016.08.004"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4866386"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aa8e13"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12096"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2014.2320284"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aadc90"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2014.2321098"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/61\/3\/1332"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4926780"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13317"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13489"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3056150"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-54176-0"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14523"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2017170896"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14157"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.8.5.052104"},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12812"},{"key":"e_1_2_10_34_1","first-page":"262","article-title":"Texture synthesis using convolutional neural networks","volume":"1","author":"Gatys L","year":"2015","journal-title":"Adv Neural Inform Process Syst"},{"key":"e_1_2_10_35_1","unstructured":"KingmaDP BaJ Adam: a method for stochastic optimization. Paper presented at:International Conference on Learning Representations (ICLR); May 7\u201392015;San Diego CA."},{"key":"e_1_2_10_36_1","unstructured":"GongH FerreroA MarshJ et\u00a0al.Renal stone quantification in contrast enhanced CT using convolutional neural network assisted dual\u2010energy virtual non\u2010contrast imaging. Paper presented at: MEDICAL PHYSICS2021. Accessed July 25\u201329 2021."},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/61\/18\/6707"},{"issue":"11","key":"e_1_2_10_38_1","first-page":"2579","article-title":"Visualizing data using t\u2010SNE","volume":"9","author":"Van der Maaten L","year":"2008","journal-title":"J Mach Learn Res"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15934","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.15934","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15934","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,20]],"date-time":"2023-08-20T09:55:09Z","timestamp":1692525309000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.15934"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,28]]},"references-count":37,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["10.1002\/mp.15934"],"URL":"https:\/\/doi.org\/10.1002\/mp.15934","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,28]]},"assertion":[{"value":"2022-02-16","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-08-04","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-08-28","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}