Improved CT-based Osteoporosis Assessment with a Fully Automated Deep Learning Tool.

Abdomen/GI CT CT-Quantitative Deep Learning Machine Learning Skeletal-Axial Spine

Journal

Radiology. Artificial intelligence
ISSN: 2638-6100
Titre abrégé: Radiol Artif Intell
Pays: United States
ID NLM: 101746556

Informations de publication

Date de publication:
Sep 2022
Historique:
received: 07 03 2022
revised: 12 08 2022
accepted: 17 08 2022
entrez: 7 10 2022
pubmed: 8 10 2022
medline: 8 10 2022
Statut: epublish

Résumé

To develop, test, and validate a deep learning (DL) tool that improves upon a previous feature-based CT image processing bone mineral density (BMD) algorithm and compare it against the manual reference standard. This single-center, retrospective, Health Insurance Portability and Accountability Act-compliant study included manual L1 trabecular Hounsfield unit measurements from abdominal CT scans in 11 035 patients (mean age, 58 years ± 12 [SD]; 6311 women) as the reference standard. Automated level selection and L1 trabecular region of interest (ROI) placement were then performed in this CT cohort with both a previously validated feature-based image processing tool and a new DL tool. Overall technical success rates and agreement with the manual reference standard were assessed. The overall success rate of the DL tool in this heterogeneous patient cohort was significantly higher than that of the older image processing BMD algorithm (99.3% vs 89.4%, The new DL BMD tool demonstrated a higher success rate than the older feature-based image processing tool, and its outputs can be targeted for higher specificity or sensitivity for osteoporosis assessment.

Identifiants

pubmed: 36204542
doi: 10.1148/ryai.220042
pmc: PMC9530763
doi:

Types de publication

Journal Article

Langues

eng

Pagination

e220042

Subventions

Organisme : NLM NIH HHS
ID : R01 LM013151
Pays : United States

Informations de copyright

© 2022 by the Radiological Society of North America, Inc.

Déclaration de conflit d'intérêts

Disclosures of conflicts of interest: P.J.P. Consulting fees for advisor to Bracco, Nanox, and GE Healthcare; stock/stock options in Nanox. T.N. No relevant relationships. A.A.P. Support for attending meetings and/or travel from UW Health for academic radiology conferences. P.M.G. No relevant relationships. S.J. No relevant relationships. R.M.S. Grant from PingAn (CRADA); royalties for patents or licenses from iCAD, Philips, ScanMed, PingAn, Translation Holdings; associate editor of Radiology: Artificial Intelligence. J.W.G. R01 LM013151/LM/NLM NIH HHS/United States grant.

Références

J Bone Miner Res. 2021 Mar;36(3):425-426
pubmed: 33600607
Osteoporos Int. 2018 Jun;29(6):1359-1366
pubmed: 29520605
Nat Med. 2020 Jan;26(1):77-82
pubmed: 31932801
AJR Am J Roentgenol. 2020 Sep;215(3):582-594
pubmed: 32755187
J Bone Joint Surg Am. 2017 Sep 20;99(18):1580-1590
pubmed: 28926388
J Bone Miner Res. 2016 Aug;31(8):1485-7
pubmed: 27335158
Osteoporos Int. 2016 Mar;27(3):1131-1136
pubmed: 26419470
J Comput Assist Tomogr. 2011 Mar-Apr;35(2):212-6
pubmed: 21412092
J Bone Miner Res. 2021 Mar;36(3):427-435
pubmed: 33145809
J Bone Miner Res. 2007 Mar;22(3):465-75
pubmed: 17144789
J Bone Miner Res. 2011 Sep;26(9):2194-203
pubmed: 21590738
J Bone Miner Res. 2008 Jul;23(7):1061-7
pubmed: 18302495
Ann Intern Med. 2013 Apr 16;158(8):588-95
pubmed: 23588747
Korean J Radiol. 2021 Dec;22(12):1934-1937
pubmed: 34719894
AJR Am J Roentgenol. 2017 Jan;208(1):165-170
pubmed: 27762605
Radiology. 2013 Jul;268(1):120-6
pubmed: 23449956
Abdom Radiol (NY). 2021 Mar;46(3):1229-1235
pubmed: 32948910
J Med Imaging (Bellingham). 2018 Jan;5(1):015006
pubmed: 29487883
J Clin Endocrinol Metab. 2016 Mar;101(3):852-9
pubmed: 26909798
Osteoporos Int. 2016 Jan;27(1):147-52
pubmed: 26153046
Radiographics. 2021 Mar-Apr;41(2):524-542
pubmed: 33646902
Arch Intern Med. 2004 May 24;164(10):1108-12
pubmed: 15159268
Eur Radiol. 2021 Apr;31(4):1831-1842
pubmed: 33001308
AJR Am J Roentgenol. 2017 Sep;209(3):491-496
pubmed: 28639828
J Bone Miner Res. 2018 May;33(5):860-867
pubmed: 29314261
Rheumatology (Oxford). 2022 Aug 3;61(8):3269-3278
pubmed: 34850864
Osteoporos Int. 2019 Jun;30(6):1215-1222
pubmed: 30868182
Radiology. 2022 May;303(2):241-254
pubmed: 35289661
J Am Coll Radiol. 2015 Oct;12(10):1036-41
pubmed: 26435117
Radiology. 2019 May;291(2):360-367
pubmed: 30912719
Curr Osteoporos Rep. 2018 Aug;16(4):411-422
pubmed: 29846870
Br J Radiol. 2019 Feb;92(1094):20180726
pubmed: 30433815
Eur Radiol. 2015 Jul;25(7):2074-9
pubmed: 25591750
Radiology. 2020 Oct;297(1):64-72
pubmed: 32780005
Osteoporos Int. 2020 Nov;31(11):2189-2196
pubmed: 32623489
N Engl J Med. 2016 May 26;374(21):2096-7
pubmed: 27223157
J Bone Miner Res. 2014 Nov;29(11):2520-6
pubmed: 24771492
Eur J Radiol. 2021 Mar;136:109568
pubmed: 33545629
Cleve Clin J Med. 2021 Nov 2;88(11):615-622
pubmed: 34728487

Auteurs

Perry J Pickhardt (PJ)

Department of Radiology, University of Wisconsin School of Medicine & Public Health, E3/311 Clinical Science Center, 600 Highland Ave, Madison, WI 53792-3252 (P.J.P., T.N., A.A.P., P.M.G., S.J., J.W.G.); and Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, Md (R.M.S.).

Thang Nguyen (T)

Department of Radiology, University of Wisconsin School of Medicine & Public Health, E3/311 Clinical Science Center, 600 Highland Ave, Madison, WI 53792-3252 (P.J.P., T.N., A.A.P., P.M.G., S.J., J.W.G.); and Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, Md (R.M.S.).

Alberto A Perez (AA)

Department of Radiology, University of Wisconsin School of Medicine & Public Health, E3/311 Clinical Science Center, 600 Highland Ave, Madison, WI 53792-3252 (P.J.P., T.N., A.A.P., P.M.G., S.J., J.W.G.); and Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, Md (R.M.S.).

Peter M Graffy (PM)

Department of Radiology, University of Wisconsin School of Medicine & Public Health, E3/311 Clinical Science Center, 600 Highland Ave, Madison, WI 53792-3252 (P.J.P., T.N., A.A.P., P.M.G., S.J., J.W.G.); and Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, Md (R.M.S.).

Samuel Jang (S)

Department of Radiology, University of Wisconsin School of Medicine & Public Health, E3/311 Clinical Science Center, 600 Highland Ave, Madison, WI 53792-3252 (P.J.P., T.N., A.A.P., P.M.G., S.J., J.W.G.); and Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, Md (R.M.S.).

Ronald M Summers (RM)

Department of Radiology, University of Wisconsin School of Medicine & Public Health, E3/311 Clinical Science Center, 600 Highland Ave, Madison, WI 53792-3252 (P.J.P., T.N., A.A.P., P.M.G., S.J., J.W.G.); and Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, Md (R.M.S.).

John W Garrett (JW)

Department of Radiology, University of Wisconsin School of Medicine & Public Health, E3/311 Clinical Science Center, 600 Highland Ave, Madison, WI 53792-3252 (P.J.P., T.N., A.A.P., P.M.G., S.J., J.W.G.); and Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, Md (R.M.S.).

Classifications MeSH