{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T22:32:17Z","timestamp":1792794737166,"version":"4.5.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2022,2,2]],"date-time":"2022-02-02T00:00:00Z","timestamp":1643760000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,2,2]],"date-time":"2022-02-02T00:00:00Z","timestamp":1643760000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100006095","name":"helse s\u00f8r-\u00f8st rhf","doi-asserted-by":"publisher","award":["2018033"],"award-info":[{"award-number":["2018033"]}],"id":[{"id":"10.13039\/501100006095","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005366","name":"University of Oslo","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005366","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Pediatr Radiol"],"published-print":{"date-parts":[[2022,5]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Manual assessment of bone marrow signal is time-consuming and requires meticulous standardisation to secure adequate precision of findings.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Objective<\/jats:title>\n                <jats:p>We examined the feasibility of using deep learning for automated segmentation of bone marrow signal in children and adolescents.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Materials and methods<\/jats:title>\n                <jats:p>We selected knee images from 95 whole-body MRI examinations of healthy individuals and of children with chronic non-bacterial osteomyelitis, ages 6\u201318\u00a0years, in a longitudinal prospective multi-centre study cohort. Bone marrow signal on T2-weighted Dixon water-only images was divided into three color-coded intensity-levels: 1\u2009=\u2009slightly increased; 2\u2009=\u2009mildly increased; 3\u2009=\u2009moderately to highly increased, up to fluid-like signal. We trained a convolutional neural network on 85 examinations to perform bone marrow segmentation. Four readers manually segmented a test set of 10 examinations and calculated ground truth using simultaneous truth and performance level estimation (STAPLE). We evaluated model and rater performance through Dice similarity coefficient and in consensus.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>Consensus score of model performance showed acceptable results for all but one examination. Model performance and reader agreement had highest scores for level-1 signal (median Dice 0.68) and lowest scores for level-3 signal (median Dice 0.40), particularly in examinations where this signal was sparse.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusion<\/jats:title>\n                <jats:p>It is feasible to develop a deep-learning-based model for automated segmentation of bone marrow signal in children and adolescents. Our model performed poorest for the highest signal intensity in examinations where this signal was sparse. Further improvement requires training on larger and more balanced datasets and validation against ground truth, which should be established by radiologists from several institutions in consensus.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1007\/s00247-021-05270-x","type":"journal-article","created":{"date-parts":[[2022,2,2]],"date-time":"2022-02-02T06:25:48Z","timestamp":1643783148000},"page":"1104-1114","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Automated segmentation of magnetic resonance bone marrow signal: a feasibility study"],"prefix":"10.1007","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5136-3835","authenticated-orcid":false,"given":"Elisabeth","family":"von Brandis","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8624-1152","authenticated-orcid":false,"given":"H\u00e5vard B.","family":"Jenssen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4279-7540","authenticated-orcid":false,"given":"Derk F. M.","family":"Avenarius","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3486-3141","authenticated-orcid":false,"given":"Atle","family":"Bj\u00f8rnerud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5207-9182","authenticated-orcid":false,"given":"Berit","family":"Flat\u00f8","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anders H.","family":"Tomterstad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vibke","family":"Lilleby","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0135-2169","authenticated-orcid":false,"given":"Karen","family":"Rosendahl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5954-7586","authenticated-orcid":false,"given":"Tomas","family":"Sakinis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8487-7843","authenticated-orcid":false,"given":"Pia K. K.","family":"Zadig","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6529-4984","authenticated-orcid":false,"given":"Lil-Sofie Ording","family":"M\u00fcller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,2,2]]},"reference":[{"key":"5270_CR1","doi-asserted-by":"publisher","first-page":"1224","DOI":"10.3899\/jrheum.160821","volume":"44","author":"R Hemke","year":"2017","unstructured":"Hemke R, Tzaribachev N, Nusman CM et al (2017) Magnetic resonance imaging (MRI) of the knee as an outcome measure in juvenile idiopathic arthritis: an OMERACT reliability study on MRI scales. J Rheumatol 44:1224\u20131230","journal-title":"J Rheumatol"},{"key":"5270_CR2","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1186\/s12969-017-0159-z","volume":"15","author":"N Herregods","year":"2017","unstructured":"Herregods N, Dehoorne J, Van den Bosch F et al (2017) ASAS definition for sacroiliitis on MRI in SpA: applicable to children? Pediatr Rheumatol Online J 15:24","journal-title":"Pediatr Rheumatol Online J"},{"key":"5270_CR3","doi-asserted-by":"publisher","first-page":"714","DOI":"10.1007\/s00247-012-2345-y","volume":"42","author":"L Tanturri de Horatio","year":"2012","unstructured":"Tanturri de Horatio L, Damasio MB, Barbuti D et al (2012) MRI assessment of bone marrow in children with juvenile idiopathic arthritis: intra- and inter-observer variability. Pediatr Radiol 42:714\u2013720","journal-title":"Pediatr Radiol"},{"key":"5270_CR4","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1186\/s13075-018-1543-x","volume":"20","author":"PF Weiss","year":"2018","unstructured":"Weiss PF, Maksymowych WP, Lambert RG et al (2018) Feasibility and reliability of the Spondyloarthritis Research Consortium of Canada sacroiliac joint inflammation score in children. Arthritis Res Ther 20:56","journal-title":"Arthritis Res Ther"},{"key":"5270_CR5","doi-asserted-by":"publisher","first-page":"739","DOI":"10.3899\/jrheum.190186","volume":"47","author":"Y Zhao","year":"2019","unstructured":"Zhao Y, Sato TS, Nielsen SM et al (2019) Development of CROMRIS (chronic nonbacterial osteomyelitis MRI scoring) tool and evaluation of its interrater reliability. J Rheumatol 47:739\u2013747","journal-title":"J Rheumatol"},{"key":"5270_CR6","doi-asserted-by":"publisher","first-page":"636","DOI":"10.3899\/jrheum.180222","volume":"46","author":"J Panwar","year":"2019","unstructured":"Panwar J, Tse SML, Lim L et al (2019) Spondyloarthritis Research Consortium of Canada scoring system for sacroiliitis in juvenile spondyloarthritis\/enthesitis-related arthritis: a reliability, validity, and responsiveness study. J Rheumatol 46:636\u2013644","journal-title":"J Rheumatol"},{"key":"5270_CR7","first-page":"1385","volume":"30","author":"M Ostergaard","year":"2003","unstructured":"Ostergaard M, Peterfy C, Conaghan P et al (2003) OMERACT rheumatoid arthritis magnetic resonance imaging studies. Core set of MRI acquisitions, joint pathology definitions, and the OMERACT RA-MRI scoring system. J Rheumatol 30:1385\u20131386","journal-title":"J Rheumatol"},{"key":"5270_CR8","doi-asserted-by":"publisher","first-page":"1118","DOI":"10.1002\/art.22496","volume":"56","author":"E Jimenez-Boj","year":"2007","unstructured":"Jimenez-Boj E, Nobauer-Huhmann I, Hanslik-Schnabel B et al (2007) Bone erosions and bone marrow edema as defined by magnetic resonance imaging reflect true bone marrow inflammation in rheumatoid arthritis. Arthritis Rheum 56:1118\u20131124","journal-title":"Arthritis Rheum"},{"key":"5270_CR9","first-page":"5","volume":"8","author":"FM McQueen","year":"2006","unstructured":"McQueen FM, Ostendorf B (2006) What is MRI bone oedema in rheumatoid arthritis and why does it matter? Arthritis Res Ther 8:5","journal-title":"Arthritis Res Ther"},{"key":"5270_CR10","doi-asserted-by":"publisher","first-page":"1352","DOI":"10.2214\/AJR.16.17263","volume":"208","author":"DFM Avenarius","year":"2017","unstructured":"Avenarius DFM, Ording Muller LS, Rosendahl K (2017) Joint fluid, bone marrow edemalike changes, and ganglion cysts in the pediatric wrist: features that may mimic pathologic abnormalities \u2014 follow-up of a healthy cohort. AJR Am J Roentgenol 208:1352\u20131357","journal-title":"AJR Am J Roentgenol"},{"key":"5270_CR11","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1136\/ard.2010.135244","volume":"70","author":"LS Ording Muller","year":"2011","unstructured":"Ording Muller LS, Avenarius D, Damasio B et al (2011) The paediatric wrist revisited: redefining MR findings in healthy children. Ann Rheum Dis 70:605\u2013610","journal-title":"Ann Rheum Dis"},{"key":"5270_CR12","doi-asserted-by":"publisher","first-page":"670","DOI":"10.1007\/s00247-006-0129-y","volume":"36","author":"N Shabshin","year":"2006","unstructured":"Shabshin N, Schweitzer ME, Morrison WB et al (2006) High-signal T2 changes of the bone marrow of the foot and ankle in children: red marrow or traumatic changes? Pediatr Radiol 36:670\u2013676","journal-title":"Pediatr Radiol"},{"key":"5270_CR13","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1007\/s00256-020-03632-4","volume":"50","author":"D Maraghelli","year":"2021","unstructured":"Maraghelli D, Brandi ML, Matucci Cerinic M et al (2021) Edema-like marrow signal intensity: a narrative review with a pictorial essay. Skeletal Radiol 50:645\u2013663","journal-title":"Skeletal Radiol"},{"key":"5270_CR14","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1037\/h0060230","volume":"45","author":"AL Diamon","year":"1953","unstructured":"Diamon AL (1953) Foveal simultaneous brightness contrast as a function of inducing, and test-field luminances. J Exp Psychol 45:304\u2013314","journal-title":"J Exp Psychol"},{"key":"5270_CR15","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1037\/h0062595","volume":"46","author":"H Leibowitz","year":"1953","unstructured":"Leibowitz H, Mote FA, Thurlow WR (1953) Simultaneous contrast as a function of separation between test and inducing fields. J Exp Psychol 46:453\u2013456","journal-title":"J Exp Psychol"},{"key":"5270_CR16","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.visres.2020.04.012","volume":"173","author":"P Sinha","year":"2020","unstructured":"Sinha P, Crucilla S, Gandhi T et al (2020) Mechanisms underlying simultaneous brightness contrast: early and innate. Vision Res 173:41\u201349","journal-title":"Vision Res"},{"key":"5270_CR17","doi-asserted-by":"publisher","first-page":"1072","DOI":"10.1002\/(SICI)1522-2594(199912)42:6<1072::AID-MRM11>3.0.CO;2-M","volume":"42","author":"LG Ny\u00fal","year":"1999","unstructured":"Ny\u00fal LG, Udupa JK (1999) On standardizing the MR image intensity scale. Magn Reson Med 42:1072\u20131081","journal-title":"Magn Reson Med"},{"key":"5270_CR18","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/s13244-016-0534-1","volume":"8","author":"AP Brady","year":"2017","unstructured":"Brady AP (2017) Error and discrepancy in radiology: inevitable or avoidable? Insights Imaging 8:171\u2013182","journal-title":"Insights Imaging"},{"key":"5270_CR19","doi-asserted-by":"publisher","first-page":"939","DOI":"10.1002\/jmri.26534","volume":"49","author":"MA Mazurowski","year":"2019","unstructured":"Mazurowski MA, Buda M, Saha A, Bashir MR (2019) Deep learning in radiology: an overview of the concepts and a survey of the state of the art with focus on MRI. J Magn Reson Imaging 49:939\u2013954","journal-title":"J Magn Reson Imaging"},{"key":"5270_CR20","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1038\/s41568-018-0016-5","volume":"18","author":"A Hosny","year":"2018","unstructured":"Hosny A, Parmar C, Quackenbush J et al (2018) Artificial intelligence in radiology. Nat Rev Cancer 18:500\u2013510","journal-title":"Nat Rev Cancer"},{"key":"5270_CR21","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1016\/j.bbe.2021.05.005","volume":"41","author":"K Rzecki","year":"2021","unstructured":"Rzecki K, Kucyba\u0142a I, Gut D et al (2021) Fully automated algorithm for the detection of bone marrow oedema lesions in patients with axial spondyloarthritis \u2014 feasibility study. Biocybern Biomed Eng 41:833\u2013853","journal-title":"Biocybern Biomed Eng"},{"key":"5270_CR22","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1186\/s12969-020-00442-9","volume":"18","author":"CS Bhat","year":"2020","unstructured":"Bhat CS, Chopra M, Andronikou S et al (2020) Artificial intelligence for interpretation of segments of whole body MRI in CNO: pilot study comparing radiologists versus machine learning algorithm. Pediatr Rheumatol Online J 18:47","journal-title":"Pediatr Rheumatol Online J"},{"key":"5270_CR23","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1186\/s13244-019-0832-5","volume":"11","author":"E Montagnon","year":"2020","unstructured":"Montagnon E, Cerny M, Cadrin-Chenevert A et al (2020) Deep learning workflow in radiology: a primer. Insights Imaging 11:22","journal-title":"Insights Imaging"},{"key":"5270_CR24","unstructured":"Tardi C (2020) 80\u201320 rule. Investopedia. https:\/\/www.investopedia.com\/terms\/p\/paretoprinciple.asp. Accessed 24 Oct 2021"},{"key":"5270_CR25","unstructured":"No authors listed (2021) MedSeg website. https:\/\/www.medseg.ai. Accessed 22 Nov 2021"},{"key":"5270_CR26","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells W, Frangi A (eds) Medical image computing and computer-assisted intervention \u2014 MICCAI 2015. Springer, Cham","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"5270_CR27","doi-asserted-by":"crossref","unstructured":"Schneidmuller D, Roder C, Kraus R et al (2011) Development and validation of a paediatric long-bone fracture classification. A prospective multicentre study in 13 European paediatric trauma centres. BMC Musculoskelet Disord 12:89","DOI":"10.1186\/1471-2474-12-89"},{"key":"5270_CR28","doi-asserted-by":"publisher","first-page":"903","DOI":"10.1109\/TMI.2004.828354","volume":"23","author":"SK Warfield","year":"2004","unstructured":"Warfield SK, Zou KH, Wells WM (2004) Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation. IEEE Trans Med Imaging 23:903\u2013921","journal-title":"IEEE Trans Med Imaging"},{"key":"5270_CR29","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1097\/00002508-200003000-00005","volume":"16","author":"EK Breivik","year":"2000","unstructured":"Breivik EK, Bj\u00f6rnsson GA, Skovlund E (2000) A comparison of pain rating scales by sampling from clinical trial data. Clin J Pain 16:22\u201328","journal-title":"Clin J Pain"},{"key":"5270_CR30","doi-asserted-by":"publisher","first-page":"1567","DOI":"10.1007\/s00247-018-4187-8","volume":"48","author":"KR Suther","year":"2018","unstructured":"Suther KR, Hopp E, Smevik B et al (2018) Can visual analogue scale be used in radiologic subjective image quality assessment? Pediatr Radiol 48:1567\u20131575","journal-title":"Pediatr Radiol"},{"key":"5270_CR31","doi-asserted-by":"publisher","first-page":"297","DOI":"10.2307\/1932409","volume":"26","author":"RL Dice","year":"1945","unstructured":"Dice RL (1945) Measures of the amount of ecologic association between species. Ecology 26:297\u2013302","journal-title":"Ecology"},{"key":"5270_CR32","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/s10462-020-09854-1","volume":"54","author":"S Asgari Taghanaki","year":"2020","unstructured":"Asgari Taghanaki S, Abhishek K, Cohen JP et al (2020) Deep semantic segmentation of natural and medical images: a review. Artif Intell Rev 54:137\u2013178","journal-title":"Artif Intell Rev"},{"key":"5270_CR33","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1148\/radiol.10100252","volume":"257","author":"AA Bankier","year":"2010","unstructured":"Bankier AA, Levine D, Halpern EF, Kressel HY (2010) Consensus interpretation in imaging research: is there a better way? Radiology 257:14\u201317","journal-title":"Radiology"},{"key":"5270_CR34","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1148\/radiology.175.1.2315484","volume":"175","author":"SG Moore","year":"1990","unstructured":"Moore SG, Dawson KL (1990) Red and yellow marrow age-related changes at MR imaging. Radiology 175:219\u2013223","journal-title":"Radiology"},{"key":"5270_CR35","doi-asserted-by":"publisher","first-page":"783","DOI":"10.1016\/j.pcl.2018.04.003","volume":"65","author":"Y Zhao","year":"2018","unstructured":"Zhao Y, Ferguson PJ (2018) Chronic nonbacterial osteomyelitis and chronic recurrent multifocal osteomyelitis in children. Pediatr Clin North Am 65:783\u2013800","journal-title":"Pediatr Clin North Am"},{"key":"5270_CR36","doi-asserted-by":"publisher","first-page":"2742","DOI":"10.1007\/s00259-020-04800-3","volume":"47","author":"X Tang","year":"2020","unstructured":"Tang X, Jafargholi Rangraz E, Coudyzer W et al (2020) Whole liver segmentation based on deep learning and manual adjustment for clinical use in SIRT. Eur J Nucl Med Mol Imaging 47:2742\u20132752","journal-title":"Eur J Nucl Med Mol Imaging"}],"updated-by":[{"DOI":"10.1007\/s00247-022-05315-9","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T00:00:00Z","timestamp":1645488000000}}],"container-title":["Pediatric Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00247-021-05270-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00247-021-05270-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00247-021-05270-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,14]],"date-time":"2022-05-14T04:11:35Z","timestamp":1652501495000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00247-021-05270-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,2]]},"references-count":36,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["5270"],"URL":"https:\/\/doi.org\/10.1007\/s00247-021-05270-x","relation":{"correction":[{"id-type":"doi","id":"10.1007\/s00247-022-05315-9","asserted-by":"object"}]},"ISSN":["0301-0449","1432-1998"],"issn-type":[{"value":"0301-0449","type":"print"},{"value":"1432-1998","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,2]]},"assertion":[{"value":"21 June 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 November 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 December 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 February 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 February 2022","order":5,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":6,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1007\/s00247-022-05315-9","URL":"https:\/\/doi.org\/10.1007\/s00247-022-05315-9","order":8,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The 2nd and 9th authors are co-owners of Artificial Intelligence AS, which develops MedSeg, the tool used for annotation in this article. This study was funded by a national grant from the regional health provider Helse S\u00f8r-\u00d8st (number 2018033).","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}