{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T04:06:42Z","timestamp":1778213202342,"version":"3.51.4"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,3,14]],"date-time":"2020-03-14T00:00:00Z","timestamp":1584144000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2020,3,14]],"date-time":"2020-03-14T00:00:00Z","timestamp":1584144000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000071","name":"National Institute of Child Health and Human Development","doi-asserted-by":"publisher","award":["K12 HD055884"],"award-info":[{"award-number":["K12 HD055884"]}],"id":[{"id":"10.13039\/100000071","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000069","name":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","doi-asserted-by":"publisher","award":["K23 AR059763"],"award-info":[{"award-number":["K23 AR059763"]}],"id":[{"id":"10.13039\/100000069","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000069","name":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","doi-asserted-by":"publisher","award":["T32 AR007611"],"award-info":[{"award-number":["T32 AR007611"]}],"id":[{"id":"10.13039\/100000069","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000069","name":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","doi-asserted-by":"publisher","award":["R21 AR068035"],"award-info":[{"award-number":["R21 AR068035"]}],"id":[{"id":"10.13039\/100000069","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000069","name":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","doi-asserted-by":"publisher","award":["R01 AR073270"],"award-info":[{"award-number":["R01 AR073270"]}],"id":[{"id":"10.13039\/100000069","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000092","name":"U.S. National Library of Medicine","doi-asserted-by":"publisher","award":["R21LM012615"],"award-info":[{"award-number":["R21LM012615"]}],"id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P30 AR072579"],"award-info":[{"award-number":["P30 AR072579"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NIH","award":["UL1 TR001422"],"award-info":[{"award-number":["UL1 TR001422"]}]},{"DOI":"10.13039\/100001845","name":"Scleroderma Research Foundation","doi-asserted-by":"publisher","award":["Hinchcliff"],"award-info":[{"award-number":["Hinchcliff"]}],"id":[{"id":"10.13039\/100001845","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Arthritis Res Ther"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Skin fibrosis is the clinical hallmark of systemic sclerosis (SSc), where collagen deposition and remodeling of the dermis occur over time. The most widely used outcome measure in SSc clinical trials is the modified Rodnan skin score (mRSS), which is a semi-quantitative assessment of skin stiffness at seventeen body sites. However, the mRSS is confounded by obesity, edema, and high inter-rater variability. In order to develop a new histopathological outcome measure for SSc, we applied a computer vision technology called a deep neural network (DNN) to stained sections of SSc skin. We tested the hypotheses that DNN analysis could reliably assess mRSS and discriminate SSc from normal skin.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>We analyzed biopsies from two independent (primary and secondary) cohorts. One investigator performed mRSS assessments and forearm biopsies, and trichrome-stained biopsy sections were photomicrographed. We used the AlexNet DNN to generate a numerical signature of 4096 quantitative image features (QIFs) for 100 randomly selected dermal image patches\/biopsy. In the primary cohort, we used principal components analysis (PCA) to summarize the QIFs into a <jats:italic>Biopsy Score<\/jats:italic> for comparison with mRSS. In the secondary cohort, using QIF signatures as the input, we fit a logistic regression model to discriminate between SSc vs. control biopsy, and a linear regression model to estimate mRSS, yielding <jats:italic>Diagnostic Scores<\/jats:italic> and <jats:italic>Fibrosis Scores,<\/jats:italic> respectively. We determined the correlation between Fibrosis Scores and the published Scleroderma Skin Severity Score (4S) and between Fibrosis Scores and longitudinal changes in mRSS on a per patient basis.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>In the primary cohort (<jats:italic>n<\/jats:italic>\u00a0=\u20096, 26 SSc biopsies), Biopsy Scores significantly correlated with mRSS (R\u2009=\u20090.55, <jats:italic>p<\/jats:italic>\u00a0=\u20090.01). In the secondary cohort (<jats:italic>n<\/jats:italic>\u00a0=\u200960 SSc and 16 controls, 164 biopsies; divided into 70% training and 30% test sets), the Diagnostic Score was significantly associated with SSc-status (misclassification rate\u2009=\u20091.9% [training], 6.6% [test]), and the Fibrosis Score significantly correlated with mRSS (R\u2009=\u20090.70 [training], 0.55 [test]). The DNN-derived Fibrosis Score significantly correlated with 4S (R\u2009=\u20090.69, <jats:italic>p<\/jats:italic>\u00a0=\u20093\u2009\u00d7\u200910<jats:sup>\u2212\u200917<\/jats:sup>).<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>DNN analysis of SSc biopsies is an unbiased, quantitative, and reproducible outcome that is associated with validated SSc outcomes.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s13075-020-2127-0","type":"journal-article","created":{"date-parts":[[2020,3,14]],"date-time":"2020-03-14T11:03:20Z","timestamp":1584183800000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["High-throughput quantitative histology in systemic sclerosis skin disease using computer vision"],"prefix":"10.1186","volume":"22","author":[{"given":"Chase","family":"Correia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seamus","family":"Mawe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shane","family":"Lofgren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roberta G.","family":"Marangoni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jungwha","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rana","family":"Saber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kathleen","family":"Aren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michelle","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shannon","family":"Teaw","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aileen","family":"Hoffmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Isaac","family":"Goldberg","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shawn E.","family":"Cowper","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Purvesh","family":"Khatri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8652-9890","authenticated-orcid":false,"given":"Monique","family":"Hinchcliff","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1425-5939","authenticated-orcid":false,"given":"J. Matthew","family":"Mahoney","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,3,14]]},"reference":[{"issue":"2","key":"2127_CR1","first-page":"202","volume":"15","author":"EC LeRoy","year":"1988","unstructured":"LeRoy EC, Black C, Fleischmajer R, Jablonska S, Krieg T, Medsger TA Jr, et al. Scleroderma (systemic sclerosis): classification, subsets and pathogenesis. J Rheumatol. 1988;15(2):202\u20135.","journal-title":"J Rheumatol"},{"issue":"7","key":"2127_CR2","first-page":"1271","volume":"22","author":"JE Pope","year":"1995","unstructured":"Pope JE, Baron M, Bellamy N, Campbell J, Carette S, Chalmers I, et al. Variability of skin scores and clinical measurements in scleroderma. J Rheumatol. 1995;22(7):1271\u20136.","journal-title":"J Rheumatol"},{"issue":"2","key":"2127_CR3","first-page":"79","volume":"14","author":"Sclerosis TGGftSoS","year":"1999","unstructured":"Sclerosis TGGftSoS. Clinical evaluation of systemic sclerosis: a comprehensive panel of diagnostic tests to assess skin, microvascular and visceral involvement. The Genoese Group for the Study of systemic sclerosis. An Ital Med Int. 1999;14(2):79\u201385.","journal-title":"An Ital Med Int"},{"issue":"4","key":"2127_CR4","first-page":"233","volume":"16","author":"M Basso","year":"2001","unstructured":"Basso M, Filaci G, Cutolo M, Murdaca G, Derchi L, Gianrossi R, et al. Long-term treatment of patients affected by systemic sclerosis with cyclosporin a. Ann Ital Med Int. 2001;16(4):233\u20139.","journal-title":"Ann Ital Med Int"},{"issue":"4","key":"2127_CR5","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1002\/art.22093","volume":"55","author":"EY Kissin","year":"2006","unstructured":"Kissin EY, Schiller AM, Gelbard RB, Anderson JJ, Falanga V, Simms RW, et al. Durometry for the assessment of skin disease in systemic sclerosis. Arthritis Rheum. 2006;55(4):603\u20139.","journal-title":"Arthritis Rheum"},{"issue":"1","key":"2127_CR6","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1186\/s13075-018-1686-9","volume":"20","author":"H Li","year":"2018","unstructured":"Li H, Furst DE, Jin H, Sun C, Wang X, Yang L, et al. High-frequency ultrasound of the skin in systemic sclerosis: an exploratory study to examine correlation with disease activity and to define the minimally detectable difference. Arthritis Res Ther. 2018;20(1):181.","journal-title":"Arthritis Res Ther"},{"issue":"1","key":"2127_CR7","first-page":"84","volume":"25","author":"DE Furst","year":"1998","unstructured":"Furst DE, Clements PJ, Steen VD, Medsger TA Jr, Masi AT, D'Angelo WA, et al. The modified Rodnan skin score is an accurate reflection of skin biopsy thickness in systemic sclerosis. J Rheumatol. 1998;25(1):84\u20138.","journal-title":"J Rheumatol"},{"issue":"3","key":"2127_CR8","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1136\/ard.2007.086850","volume":"68","author":"G Farina","year":"2009","unstructured":"Farina G, Lemaire R, Pancari P, Bayle J, Widom RL, Lafyatis R. Cartilage oligomeric matrix protein expression in systemic sclerosis reveals heterogeneity of dermal fibroblast responses to transforming growth factor beta. Ann Rheum Dis. 2009;68(3):435\u201341.","journal-title":"Ann Rheum Dis"},{"issue":"2","key":"2127_CR9","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1002\/art.27220","volume":"62","author":"G Farina","year":"2010","unstructured":"Farina G, Lafyatis D, Lemaire R, Lafyatis R. A four-gene biomarker predicts skin disease in patients with diffuse cutaneous systemic sclerosis. Arthritis Rheum. 2010;62(2):580\u20138.","journal-title":"Arthritis Rheum"},{"issue":"1","key":"2127_CR10","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.jid.2016.08.027","volume":"137","author":"LM Rice","year":"2017","unstructured":"Rice LM, Mantero JC, Stifano G, Ziemek J, Simms RW, Gordon J, et al. A proteome-derived longitudinal Pharmacodynamic biomarker for diffuse systemic sclerosis skin. J Invest Dermatol. 2017;137(1):62\u201370.","journal-title":"J Invest Dermatol"},{"issue":"21","key":"2127_CR11","doi-asserted-by":"publisher","first-page":"e89073","DOI":"10.1172\/jci.insight.89073","volume":"1","author":"S Lofgren","year":"2016","unstructured":"Lofgren S, Hinchcliff M, Carns M, Wood T, Aren K, Arroyo E, et al. Integrated, multicohort analysis of systemic sclerosis identifies robust transcriptional signature of disease severity. JCI insight. 2016;1(21):e89073.","journal-title":"JCI insight"},{"issue":"7639","key":"2127_CR12","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","volume":"542","author":"A Esteva","year":"2017","unstructured":"Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542(7639):115\u20138.","journal-title":"Nature."},{"key":"2127_CR13","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.cmpb.2018.01.027","volume":"159","author":"A Pal","year":"2018","unstructured":"Pal A, Garain U, Chandra A, Chatterjee R, Senapati S. Psoriasis skin biopsy image segmentation using deep convolutional neural network. Comput Methods Prog Biomed. 2018;159:59\u201369.","journal-title":"Comput Methods Prog Biomed"},{"key":"2127_CR14","doi-asserted-by":"publisher","first-page":"32","DOI":"10.4103\/jpi.jpi_31_18","volume":"9","author":"TG Olsen","year":"2018","unstructured":"Olsen TG, Jackson BH, Feeser TA, Kent MN, Moad JC, Krishnamurthy S, et al. Diagnostic performance of deep learning algorithms applied to three common diagnoses in Dermatopathology. J Pathol Inform. 2018;9:32.","journal-title":"J Pathol Inform"},{"key":"2127_CR15","unstructured":"Krizhevsky A, Sutskever I, Hinton G. ImageNet Classification with Deep Convolutional Neural Networks. In: Pereira F, Burges C, Bottou L, Weinberger K, editors. Advances in Neural Information Processing Systems. New York: Curran Associates, Inc; 2012. p. 1097\u2013105."},{"key":"2127_CR16","volume-title":"Adaptive computation and machine learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A. Deep learning. In: Dietterich T, editor. Adaptive computation and machine learning. Cambridge: The MIT Press; 2016."},{"issue":"8","key":"2127_CR17","doi-asserted-by":"publisher","first-page":"1979","DOI":"10.1038\/jid.2013.130","volume":"133","author":"M Hinchcliff","year":"2013","unstructured":"Hinchcliff M, Huang CC, Wood TA, Matthew Mahoney J, Martyanov V, Bhattacharyya S, et al. Molecular signatures in skin associated with clinical improvement during mycophenolate treatment in systemic sclerosis. J Invest Dermatol. 2013;133(8):1979\u201389.","journal-title":"J Invest Dermatol."},{"issue":"6","key":"2127_CR18","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1016\/j.jid.2018.01.006","volume":"138","author":"M Hinchcliff","year":"2018","unstructured":"Hinchcliff M, Toledo DM, Taroni JN, Wood TA, Franks JM, Ball MS, et al. Mycophenolate Mofetil treatment of systemic sclerosis reduces myeloid cell numbers and attenuates the inflammatory gene signature in skin. J Invest Dermatol. 2018;138(6):1301\u201310.","journal-title":"J Invest Dermatol."},{"issue":"11","key":"2127_CR19","doi-asserted-by":"publisher","first-page":"2737","DOI":"10.1002\/art.38098","volume":"65","author":"F van den Hoogen","year":"2013","unstructured":"van den Hoogen F, Khanna D, Fransen J, Johnson SR, Baron M, Tyndall A, et al. 2013 classification criteria for systemic sclerosis: an American College of Rheumatology\/European league against rheumatism collaborative initiative. Arthritis Rheum. 2013;65(11):2737\u201347.","journal-title":"Arthritis Rheum"},{"key":"2127_CR20","doi-asserted-by":"crossref","unstructured":"Sheehan S, Mawe S, Cianciolo RE, Korstanje R, Mahoney JM. Detection and Classification of Novel Renal Histologic Phenotypes Using Deep Neural Networks. Am J Pathol. 2019;189:1786\u201396.","DOI":"10.1016\/j.ajpath.2019.05.019"},{"key":"2127_CR21","unstructured":"Jolliffe I. Principal component analysis, second edition. Second ed. Bickel P, Diggle P, Fienberg S, Gather U, Zeger S, editors. New York: Springer; 2002."},{"key":"2127_CR22","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1007\/978-0-387-21606-5","volume-title":"The elements of statistical learning: data mining, inference, and prediction","author":"T Hastie","year":"2001","unstructured":"Hastie T, Tibshirani R, Friedman J. The elements of statistical learning: data mining, inference, and prediction, vol. 2001. 1st ed. New York: Springer-Verlag; 2001. p. 533.","edition":"1"},{"key":"2127_CR23","doi-asserted-by":"crossref","unstructured":"Strutz T. Weights and Outliers. Data Fitting and Uncertainty (A practical introduction to weighted least squares and beyond). 2nd ed. Wiesbaden: Springer Vieweg; 2016.","DOI":"10.1007\/978-3-658-11456-5_3"},{"key":"2127_CR24","unstructured":"Clements P, Lachenbruch P, Siebold J, White B, Weiner S, Martin R, et al. Inter and intraobserver variability of total skin thickness score (modified Rodnan TSS) in systemic sclerosis. J Rheumatol. 1995;22(7):1281\u20135."},{"key":"2127_CR25","doi-asserted-by":"crossref","unstructured":"Brennan P, Silman A, Black C, Bernstein R, Coppock J, Maddison P, et al. Reliability of skin involvement measures in scleroderma. The UK scleroderma study group. Br J Rheumatol. 1992;31(7):457\u201360.","DOI":"10.1093\/rheumatology\/31.7.457"},{"key":"2127_CR26","doi-asserted-by":"crossref","unstructured":"Sobanski V, Jonathan Giovannelli J, Y A, Riemekasten G, P A, S V, et al. Phenotypes determined by cluster analysis and their survival in the prospective EUSTAR cohort of patients with systemic sclerosis. Arthritis Rheumatol. 2019;71:1553\u201370.","DOI":"10.1002\/art.40906"},{"key":"2127_CR27","doi-asserted-by":"crossref","unstructured":"Hinchcliff M, Mahoney J. High-throughput Quantitative Histology in Systemic Sclerosis Skin Disease Using Computer Vision. Nat Rev Rheumatol. 2019;15:456\u20137.","DOI":"10.1038\/s41584-019-0257-z"}],"container-title":["Arthritis Research &amp; Therapy"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13075-020-2127-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13075-020-2127-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13075-020-2127-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,14]],"date-time":"2021-03-14T00:13:32Z","timestamp":1615680812000},"score":1,"resource":{"primary":{"URL":"https:\/\/arthritis-research.biomedcentral.com\/articles\/10.1186\/s13075-020-2127-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,14]]},"references-count":27,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["2127"],"URL":"https:\/\/doi.org\/10.1186\/s13075-020-2127-0","relation":{},"ISSN":["1478-6362"],"issn-type":[{"value":"1478-6362","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3,14]]},"assertion":[{"value":"4 September 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 March 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Research partners provided written informed consent in accordance with the Declaration of Helsinki Protocols and Northwestern University Institutional Review Board guidelines (STU00004428).","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Monique Hinchcliff has received grant support from an NIH Small Business Innovative Research grant for her work identifying genomic SSc biomarkers.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"48"}}