{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T00:04:08Z","timestamp":1793318648280,"version":"4.5.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T00:00:00Z","timestamp":1690934400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T00:00:00Z","timestamp":1690934400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"National Science and Technology Council, Taiwan","award":["NSTC 112-2628-E-038-001-MY3"],"award-info":[{"award-number":["NSTC 112-2628-E-038-001-MY3"]}]},{"name":"Ministry of Education (MOE), Taiwan"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Gout is a common metabolic disorder characterized by deposits of monosodium urate monohydrate crystals (tophi) in soft tissue, triggering intense and acute arthritis with intolerable pain as well as articular and periarticular inflammation. Tophi can also promote chronic inflammatory and erosive arthritis. 2015 ACR\/EULAR Gout Classification criteria include clinical, laboratory, and imaging findings, where cases of gout are indicated by a threshold score of\u2009\u2265\u20098. Some imaging-related findings, such as a double contour sign in ultrasound, urate in dual-energy computed tomography, or radiographic gout-related erosion, generate a score of up to 4. Clearly, the diagnosis of gout is largely assisted by imaging findings; however, dual-energy computed tomography is expensive and exposes the patient to high levels of radiation. Although musculoskeletal ultrasound is non-invasive and inexpensive, the reliability of the results depends on expert experience. In the current study, we applied transfer learning to train a convolutional neural network for the identification of tophi in ultrasound images. The accuracy of predictions varied with the convolutional neural network model, as follows: InceptionV3 (0.871\u2009\u00b1\u20090.020), ResNet101 (0.913\u2009\u00b1\u20090.015), and VGG19 (0.918\u2009\u00b1\u20090.020). The sensitivity was as follows: InceptionV3 (0.507\u2009\u00b1\u20090.060), ResNet101 (0.680\u2009\u00b1\u20090.056), and VGG19 (0.747\u2009\u00b1\u20090.056). The precision was as follows: InceptionV3 (0.767\u2009\u00b1\u20090.091), ResNet101 (0.863\u2009\u00b1\u20090.098), and VGG19 (0.825\u2009\u00b1\u20090.062). Our results demonstrate that it is possible to retrain deep convolutional neural networks to identify the patterns of tophi in ultrasound images with a high degree of accuracy.<\/jats:p>","DOI":"10.1038\/s41598-023-39508-5","type":"journal-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T10:02:11Z","timestamp":1690970531000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Identification of tophi in ultrasound imaging based on transfer learning and clinical practice"],"prefix":"10.1038","volume":"13","author":[{"given":"Tzu-Min","family":"Lin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hsiang-Yen","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ching-Kuei","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke-Hung","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi-Ching","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing-Fei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Syu-Jyun","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,8,2]]},"reference":[{"issue":"Suppl 5","key":"39508_CR1","doi-asserted-by":"publisher","first-page":"S5","DOI":"10.3949\/ccjm.75.Suppl_5.S5","volume":"75","author":"BF Mandell","year":"2008","unstructured":"Mandell, B. F. Clinical manifestations of hyperuricemia and gout. Clevel. Clin. J. Med. 75(Suppl 5), S5-8 (2008).","journal-title":"Clevel. Clin. J. Med."},{"key":"39508_CR2","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1038\/s41584-020-0441-1","volume":"16","author":"M Dehlin","year":"2020","unstructured":"Dehlin, M., Jacobsson, L. & Roddy, E. Global epidemiology of gout: Prevalence, incidence, treatment patterns and risk factors. Nat. Rev. Rheumatol. 16, 380\u2013390 (2020).","journal-title":"Nat. Rev. Rheumatol."},{"key":"39508_CR3","doi-asserted-by":"publisher","first-page":"1071","DOI":"10.2169\/internalmedicine.56.7923","volume":"56","author":"RD Hayashi","year":"2017","unstructured":"Hayashi, R. D. et al. Multiple gouty tophi with bone erosion and destruction: A report of an early-onset case in an obese patient. Intern. Med. 56, 1071\u20131077 (2017).","journal-title":"Intern. Med."},{"key":"39508_CR4","doi-asserted-by":"publisher","first-page":"27","DOI":"10.7326\/M16-0462","volume":"166","author":"SJ Newberry","year":"2017","unstructured":"Newberry, S. J. et al. Diagnosis of gout: A systematic review in support of an American college of physicians clinical practice guideline. Ann. Intern. Med. 166, 27\u201336 (2017).","journal-title":"Ann. Intern. Med."},{"key":"39508_CR5","doi-asserted-by":"publisher","first-page":"1339","DOI":"10.1007\/s00296-018-4033-1","volume":"38","author":"HW Garner","year":"2018","unstructured":"Garner, H. W. & Wessell, D. E. Current status of ultrasound and dual-energy computed tomography in the evaluation of gout. Rheumatol. Int. 38, 1339\u20131344 (2018).","journal-title":"Rheumatol. Int."},{"key":"39508_CR6","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1136\/annrheumdis-2015-208237","volume":"74","author":"T Neogi","year":"2015","unstructured":"Neogi, T. et al. 2015 Gout classification criteria: An American College of Rheumatology\/European League Against Rheumatism collaborative initiative. Ann. Rheum. Dis. 74, 1789\u20131798 (2015).","journal-title":"Ann. Rheum. Dis."},{"key":"39508_CR7","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.jbspin.2014.03.011","volume":"82","author":"S Ottaviani","year":"2015","unstructured":"Ottaviani, S. et al. Ultrasound in gout: A useful tool for following urate-lowering therapy. Jt. Bone Spine 82, 42\u201344 (2015).","journal-title":"Jt. Bone Spine"},{"key":"39508_CR8","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1007\/s00296-009-1002-8","volume":"30","author":"RG Thiele","year":"2010","unstructured":"Thiele, R. G. & Schlesinger, N. Ultrasonography shows disappearance of monosodium urate crystal deposition on hyaline cartilage after sustained normouricemia is achieved. Rheumatol. Int. 30, 495\u2013503 (2010).","journal-title":"Rheumatol. Int."},{"key":"39508_CR9","doi-asserted-by":"publisher","first-page":"2460","DOI":"10.3899\/jrheum.141164","volume":"42","author":"R Grainger","year":"2015","unstructured":"Grainger, R. et al. Imaging as an outcome measure in gout studies: Report from the OMERACT gout working group. J. Rheumatol. 42, 2460\u20132464 (2015).","journal-title":"J. Rheumatol."},{"key":"39508_CR10","doi-asserted-by":"publisher","first-page":"i27","DOI":"10.1093\/rheumatology\/kex445","volume":"57","author":"N Dalbeth","year":"2018","unstructured":"Dalbeth, N. & Doyle, A. J. Imaging tools to measure treatment response in gout. Rheumatology (Oxford) 57, i27\u2013i34 (2018).","journal-title":"Rheumatology (Oxford)"},{"key":"39508_CR11","doi-asserted-by":"publisher","first-page":"1500","DOI":"10.1136\/annrheumdis-2020-217392","volume":"79","author":"HB Hammer","year":"2020","unstructured":"Hammer, H. B. et al. Ultrasound shows rapid reduction of crystal depositions during a treat-to-target approach in gout patients: 12-month results from the NOR-Gout study. Ann. Rheum. Dis. 79, 1500\u20131505 (2020).","journal-title":"Ann. Rheum. Dis."},{"key":"39508_CR12","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1016\/j.jbspin.2020.09.014","volume":"87","author":"E Ebstein","year":"2020","unstructured":"Ebstein, E. et al. UltraSound evaluation in follow-up of urate-lowering therapy in gout phase 2 (USEFUL-2): Duration of flare prophylaxis. Jt. Bone Spine 87, 647\u2013651 (2020).","journal-title":"Jt. Bone Spine"},{"key":"39508_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13075-021-02568-x","volume":"23","author":"E Cipolletta","year":"2021","unstructured":"Cipolletta, E. et al. Sonographic estimation of monosodium urate burden predicts the fulfillment of the 2016 remission criteria for gout: A 12-month study. Arthritis Res. Ther. 23, 1\u201310 (2021) https:\/\/doi.org\/10.1186\/s13075-021-02568-x.","journal-title":"Arthritis Res. Ther."},{"key":"39508_CR14","doi-asserted-by":"publisher","first-page":"410","DOI":"10.1093\/rheumatology\/key303","volume":"58","author":"E Ebstein","year":"2019","unstructured":"Ebstein, E. et al. Ultrasound evaluation in follow-up of urate-lowering therapy in gout: The USEFUL study. Rheumatology (Oxford) 58, 410\u2013417 (2019).","journal-title":"Rheumatology (Oxford)"},{"key":"39508_CR15","doi-asserted-by":"publisher","first-page":"1108","DOI":"10.1093\/rheumatology\/keac367","volume":"62","author":"E Cipolletta","year":"2023","unstructured":"Cipolletta, E., Abhishek, A., Di Battista, J., Grassi, W. & Filippucci, E. Ultrasonography in the prediction of gout flares: A 12-month prospective observational study. Rheumatology (Oxford) 62, 1108\u20131116 (2023).","journal-title":"Rheumatology (Oxford)"},{"key":"39508_CR16","doi-asserted-by":"publisher","first-page":"1609","DOI":"10.1136\/ard.2008.099713","volume":"68","author":"HK Choi","year":"2009","unstructured":"Choi, H. K. et al. Dual energy computed tomography in tophaceous gout. Ann. Rheum. Dis. 68, 1609\u20131612 (2009).","journal-title":"Ann. Rheum. Dis."},{"key":"39508_CR17","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1177\/1941738116664326","volume":"8","author":"OK Nwawka","year":"2016","unstructured":"Nwawka, O. K. Update in musculoskeletal ultrasound research. Sports Health 8, 429\u2013437 (2016).","journal-title":"Sports Health"},{"key":"39508_CR18","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1016\/j.semarthrit.2017.09.012","volume":"47","author":"YH Lee","year":"2018","unstructured":"Lee, Y. H. & Song, G. G. Diagnostic accuracy of ultrasound in patients with gout: A meta-analysis. Semin. Arthritis Rheum. 47, 703\u2013709 (2018).","journal-title":"Semin. Arthritis Rheum."},{"key":"39508_CR19","doi-asserted-by":"publisher","first-page":"30","DOI":"10.14366\/usg.20080","volume":"40","author":"Y Shin","year":"2021","unstructured":"Shin, Y., Yang, J., Lee, Y. H. & Kim, S. Artificial intelligence in musculoskeletal ultrasound imaging. Ultrasonography 40, 30\u201344 (2021).","journal-title":"Ultrasonography"},{"key":"39508_CR20","doi-asserted-by":"publisher","first-page":"e0184059","DOI":"10.1371\/journal.pone.0184059","volume":"12","author":"P Burlina","year":"2017","unstructured":"Burlina, P., Billings, S., Joshi, N. & Albayda, J. Automated diagnosis of myositis from muscle ultrasound: Exploring the use of machine learning and deep learning methods. PLoS ONE 12, e0184059 (2017).","journal-title":"PLoS ONE"},{"key":"39508_CR21","doi-asserted-by":"publisher","first-page":"1252","DOI":"10.1016\/j.ultrasmedbio.2017.01.012","volume":"43","author":"N Quader","year":"2017","unstructured":"Quader, N., Hodgson, A. J., Mulpuri, K., Schaeffer, E. & Abugharbieh, R. Automatic evaluation of scan adequacy and dysplasia metrics in 2-D ultrasound images of the neonatal hip. Ultrasound Med. Biol. 43, 1252\u20131262 (2017).","journal-title":"Ultrasound Med. Biol."},{"key":"39508_CR22","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1016\/j.ultrasmedbio.2017.10.005","volume":"44","author":"P Mielnik","year":"2018","unstructured":"Mielnik, P., Fojcik, M., Segen, J. & Kulbacki, M. A novel method of synovitis stratification in ultrasound using machine learning algorithms: Results from clinical validation of the MEDUSA project. Ultrasound Med. Biol. 44, 489\u2013494 (2018).","journal-title":"Ultrasound Med. Biol."},{"key":"39508_CR23","doi-asserted-by":"publisher","first-page":"2677","DOI":"10.1016\/j.ultrasmedbio.2015.05.015","volume":"41","author":"S Yu","year":"2015","unstructured":"Yu, S., Tan, K. K., Sng, B. L., Li, S. & Sia, A. T. H. Lumbar ultrasound image feature extraction and classification with support vector machine. Ultrasound Med. Biol. 41, 2677\u20132689 (2015).","journal-title":"Ultrasound Med. Biol."},{"key":"39508_CR24","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.imu.2016.06.003","volume":"3","author":"O Hadjerci","year":"2016","unstructured":"Hadjerci, O. et al. Computer-aided detection system for nerve identification using ultrasound images: A comparative study. Inform. Med. Unlocked 3, 29\u201343 (2016).","journal-title":"Inform. Med. Unlocked"},{"key":"39508_CR25","volume-title":"Nerve Localization by Machine Learning Framework with New Feature Selection Algorithm (Image Analysis and Processing\u2014ICIAP 20","author":"O Hadjerci","year":"2015","unstructured":"Hadjerci, O. et al. Nerve Localization by Machine Learning Framework with New Feature Selection Algorithm (Image Analysis and Processing\u2014ICIAP 20 (Springer International Publishing, 2015)."},{"key":"39508_CR26","doi-asserted-by":"publisher","first-page":"638","DOI":"10.1136\/annrheumdis-2012-202301","volume":"72","author":"PV Chowalloor","year":"2013","unstructured":"Chowalloor, P. V. & Keen, H. I. A systematic review of ultrasonography in gout and asymptomatic hyperuricaemia. Ann. Rheum. Dis. 72, 638\u2013645 (2013).","journal-title":"Ann. Rheum. Dis."},{"key":"39508_CR27","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun, Y., Bottou, L., Bengio, Y. & Haffner, P. Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278\u20132324 (1998).","journal-title":"Proc. IEEE"},{"key":"39508_CR28","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1007\/s13244-018-0639-9","volume":"9","author":"R Yamashita","year":"2018","unstructured":"Yamashita, R., Nishio, M., Do, R. K. G. & Togashi, K. Convolutional neural networks: An overview and application in radiology. Insights Imaging 9, 611\u2013629 (2018).","journal-title":"Insights Imaging"},{"key":"39508_CR29","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1016\/j.eng.2018.11.020","volume":"5","author":"S Liu","year":"2019","unstructured":"Liu, S. et al. Deep learning in medical ultrasound analysis: A review. Engineering 5, 261\u2013275 (2019).","journal-title":"Engineering"},{"key":"39508_CR30","doi-asserted-by":"publisher","first-page":"105117","DOI":"10.1016\/j.compbiomed.2021.105117","volume":"141","author":"MC Fiorentino","year":"2022","unstructured":"Fiorentino, M. C. et al. A deep-learning framework for metacarpal-head cartilage-thickness estimation in ultrasound rheumatological images. Comput. Biol. Med. 141, 105117 (2022).","journal-title":"Comput. Biol. Med."},{"key":"39508_CR31","doi-asserted-by":"publisher","first-page":"589197","DOI":"10.3389\/fmed.2021.589197","volume":"8","author":"E Cipolletta","year":"2021","unstructured":"Cipolletta, E. et al. Artificial intelligence for ultrasound informative image selection of metacarpal head cartilage. A pilot study. Front. Med. (Lausanne) 8, 589197 (2021).","journal-title":"Front. Med. (Lausanne)"},{"key":"39508_CR32","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1016\/j.semarthrit.2010.09.003","volume":"40","author":"LK Stamp","year":"2011","unstructured":"Stamp, L. K. et al. Serum urate as a soluble biomarker in chronic gout-evidence that serum urate fulfills the OMERACT validation criteria for soluble biomarkers. Semin. Arthritis Rheum. 40, 483\u2013500 (2011).","journal-title":"Semin. Arthritis Rheum."},{"key":"39508_CR33","first-page":"1888","volume":"34","author":"F Perez-Ruiz","year":"2007","unstructured":"Perez-Ruiz, F., Martin, I. & Canteli, B. Ultrasonographic measurement of tophi as an outcome measure for chronic gout. J. Rheumatol. 34, 1888\u20131893 (2007).","journal-title":"J. Rheumatol."},{"key":"39508_CR34","doi-asserted-by":"publisher","first-page":"1318","DOI":"10.1016\/j.jacr.2019.06.004","volume":"16","author":"Z Akkus","year":"2019","unstructured":"Akkus, Z. et al. A survey of deep-learning applications in ultrasound: Artificial intelligence-powered ultrasound for improving clinical workflow. J. Am. Coll. Radiol. 16, 1318\u20131328 (2019).","journal-title":"J. Am. Coll. Radiol."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-39508-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-39508-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-39508-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T10:09:19Z","timestamp":1690970959000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-39508-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,2]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["39508"],"URL":"https:\/\/doi.org\/10.1038\/s41598-023-39508-5","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,2]]},"assertion":[{"value":"16 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"12507"}}