{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,11]],"date-time":"2026-11-11T21:48:32Z","timestamp":1794433712755,"version":"4.9.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,8,12]],"date-time":"2020-08-12T00:00:00Z","timestamp":1597190400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,8,12]],"date-time":"2020-08-12T00:00:00Z","timestamp":1597190400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"The Bio"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Colposcopy is widely used to detect cervical cancers, but experienced physicians who are needed for an accurate diagnosis are lacking in developing countries. Artificial intelligence (AI) has been recently used in computer-aided diagnosis showing remarkable promise. In this study, we developed and validated deep learning models to automatically classify cervical neoplasms on colposcopic photographs. Pre-trained convolutional neural networks were fine-tuned for two grading systems: the cervical intraepithelial neoplasia (CIN) system and the lower anogenital squamous terminology (LAST) system. The multi-class classification accuracies of the networks for the CIN system in the test dataset were 48.6\u2009\u00b1\u20091.3% by Inception-Resnet-v2 and 51.7\u2009\u00b1\u20095.2% by Resnet-152. The accuracies for the LAST system were 71.8\u2009\u00b1\u20091.8% and 74.7\u2009\u00b1\u20091.8%, respectively. The area under the curve (AUC) for discriminating high-risk lesions from low-risk lesions by Resnet-152 was 0.781\u2009\u00b1\u20090.020 for the CIN system and 0.708\u2009\u00b1\u20090.024 for the LAST system. The lesions requiring biopsy were also detected efficiently (AUC, 0.947\u2009\u00b1\u20090.030 by Resnet-152), and presented meaningfully on attention maps. These results may indicate the potential of the application of AI for automated reading of colposcopic photographs.<\/jats:p>","DOI":"10.1038\/s41598-020-70490-4","type":"journal-article","created":{"date-parts":[[2020,8,12]],"date-time":"2020-08-12T06:06:55Z","timestamp":1597212415000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":87,"title":["Classification of cervical neoplasms on colposcopic photography using deep learning"],"prefix":"10.1038","volume":"10","author":[{"given":"Bum-Joo","family":"Cho","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youn Jin","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Myung-Je","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ju Han","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ga-Hyun","family":"Son","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sung-Ho","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong-Bae","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yeon-Ji","family":"Joo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hye-Yon","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min Sun","family":"Kyung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Young-Han","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Byung Soo","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soo Young","family":"Hur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanha","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sung Taek","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,8,12]]},"reference":[{"key":"70490_CR1","doi-asserted-by":"publisher","first-page":"87","DOI":"10.3322\/caac.21262","volume":"65","author":"L Torre","year":"2015","unstructured":"Torre, L. et al. Global cancer statistics, 2012. CA Cancer J Clin65, 87\u2013108 (2015).","journal-title":"CA Cancer J Clin"},{"key":"70490_CR2","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1097\/lgt.0000000000000322","volume":"21","author":"N Wentzensen","year":"2017","unstructured":"Wentzensen, N. et al. Evidence-based consensus recommendations for colposcopy practice for cervical cancer prevention in the United States. J Low Genit Tract Dis21, 216\u2013222. https:\/\/doi.org\/10.1097\/lgt.0000000000000322 (2017).","journal-title":"J Low Genit Tract Dis"},{"issue":"Suppl 1","key":"70490_CR3","doi-asserted-by":"publisher","first-page":"S49","DOI":"10.1016\/j.jcv.2015.11.015","volume":"76","author":"N Wentzensen","year":"2016","unstructured":"Wentzensen, N., Schiffman, M., Palmer, T. & Arbyn, M. Triage of HPV positive women in cervical cancer screening. J Clin Virol76(Suppl 1), S49\u2013S55. https:\/\/doi.org\/10.1016\/j.jcv.2015.11.015 (2016).","journal-title":"J Clin Virol"},{"key":"70490_CR4","doi-asserted-by":"publisher","first-page":"147","DOI":"10.3322\/caac.21139","volume":"62","author":"D Saslow","year":"2012","unstructured":"Saslow, D. et al. American Cancer Society, American Society for Colposcopy and Cervical Pathology, and American Society for Clinical Pathology screening guidelines for the prevention and early detection of cervical cancer. CA Cancer J Clin62, 147\u2013172. https:\/\/doi.org\/10.3322\/caac.21139 (2012).","journal-title":"CA Cancer J Clin"},{"key":"70490_CR5","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1016\/j.aogh.2014.09.014","volume":"80","author":"R Sankaranarayanan","year":"2014","unstructured":"Sankaranarayanan, R. Screening for cancer in low- and middle-income countries. Ann Glob Health80, 412\u2013417 (2014).","journal-title":"Ann Glob Health"},{"key":"70490_CR6","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1158\/1055-9965.EPI-16-0858","volume":"26","author":"L Torre","year":"2017","unstructured":"Torre, L., Islami, F., Siegel, R., Ward, E. & Jemal, A. Global cancer in women: burden and trends. Cancer Epidemiol Biomark Prev (CEBP)26, 444\u2013457 (2017).","journal-title":"Cancer Epidemiol Biomark Prev (CEBP)"},{"key":"70490_CR7","doi-asserted-by":"publisher","first-page":"1144","DOI":"10.1109\/42.896790","volume":"19","author":"Q Ji","year":"2000","unstructured":"Ji, Q., Engel, J. & Craine, E. Texture analysis for classification of cervix lesions. IEEE Trans Med Imaging19, 1144\u20131149 (2000).","journal-title":"IEEE Trans Med Imaging"},{"key":"70490_CR8","doi-asserted-by":"publisher","first-page":"e0126573","DOI":"10.1371\/journal.pone.0126573","volume":"10","author":"KR Davies","year":"2015","unstructured":"Davies, K. R., Cantor, S. B., Cox, D. D. & Follen, M. An alternative approach for estimating the accuracy of colposcopy in detecting cervical precancer. PLoS ONE10, e0126573. https:\/\/doi.org\/10.1371\/journal.pone.0126573 (2015).","journal-title":"PLoS ONE"},{"key":"70490_CR9","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1097\/LGT.0b013e31819308d4","volume":"13","author":"LS Massad","year":"2009","unstructured":"Massad, L. S., Jeronimo, J., Katki, H. A. & Schiffman, M. The accuracy of colposcopic grading for detection of high-grade cervical intraepithelial neoplasia. J Low Genit Tract Dis13, 137\u2013144. https:\/\/doi.org\/10.1097\/LGT.0b013e31819308d4 (2009).","journal-title":"J Low Genit Tract Dis"},{"key":"70490_CR10","doi-asserted-by":"publisher","first-page":"468","DOI":"10.3109\/00016349709047830","volume":"76","author":"JJ Baldauf","year":"1997","unstructured":"Baldauf, J. J., Dreyfus, M., Ritter, J. & Philippe, E. An analysis of the factors involved in the diagnostic accuracy of colposcopically directed biopsy. Acta Obstet Gynecol Scand76, 468\u2013473 (1997).","journal-title":"Acta Obstet Gynecol Scand"},{"key":"70490_CR11","doi-asserted-by":"publisher","first-page":"648","DOI":"10.3109\/00016349409013460","volume":"73","author":"O Kierkegaard","year":"1994","unstructured":"Kierkegaard, O., Byrjalsen, C., Frandsen, K. H., Hansen, K. C. & Frydenberg, M. Diagnostic accuracy of cytology and colposcopy in cervical squamous intraepithelial lesions. Acta Obstet Gynecol Scand73, 648\u2013651 (1994).","journal-title":"Acta Obstet Gynecol Scand"},{"key":"70490_CR12","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1007\/s00404-018-4953-8","volume":"299","author":"FA Stuebs","year":"2019","unstructured":"Stuebs, F. A. et al. Accuracy of colposcopy-directed biopsy in detecting early cervical neoplasia: a retrospective study. Arch Gynecol Obstet299, 525\u2013532. https:\/\/doi.org\/10.1007\/s00404-018-4953-8 (2019).","journal-title":"Arch Gynecol Obstet"},{"key":"70490_CR13","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1200\/JCO.2014.55.9948","volume":"33","author":"N Wentzensen","year":"2015","unstructured":"Wentzensen, N. et al. Multiple biopsies and detection of cervical cancer precursors at colposcopy. J. Clin. Oncol.33, 83\u201389 (2015).","journal-title":"J. Clin. Oncol."},{"key":"70490_CR14","doi-asserted-by":"publisher","first-page":"127","DOI":"10.3322\/caac.21552","volume":"69","author":"WL Bi","year":"2019","unstructured":"Bi, W. L. et al. Artificial intelligence in cancer imaging: clinical challenges and applications. CA Cancer J Clin69, 127\u2013157. https:\/\/doi.org\/10.3322\/caac.21552 (2019).","journal-title":"CA Cancer J Clin"},{"key":"70490_CR15","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., Schwartz, L. & Aerts, H. J. W. L. Artificial intelligence in radiology. Nat Rev Cancer18, 500\u2013510 (2018).","journal-title":"Nat Rev Cancer"},{"key":"70490_CR16","doi-asserted-by":"publisher","first-page":"2402","DOI":"10.1001\/jama.2016.17216","volume":"316","author":"V Gulshan","year":"2016","unstructured":"Gulshan, V. et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA316, 2402\u20132410. https:\/\/doi.org\/10.1001\/jama.2016.17216 (2016).","journal-title":"JAMA"},{"key":"70490_CR17","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","volume":"542","author":"A Esteva","year":"2017","unstructured":"Esteva, A. et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature542, 115\u2013118. https:\/\/doi.org\/10.1038\/nature21056 (2017).","journal-title":"Nature"},{"key":"70490_CR18","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1016\/j.crad.2018.12.015","volume":"74","author":"K Kallianos","year":"2019","unstructured":"Kallianos, K. et al. How far have we come? Artificial intelligence for chest radiograph interpretation. Clin Radiol74, 338\u2013345. https:\/\/doi.org\/10.1016\/j.crad.2018.12.015 (2019).","journal-title":"Clin Radiol"},{"key":"70490_CR19","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/s11936-019-0728-1","volume":"21","author":"K Seetharam","year":"2019","unstructured":"Seetharam, K., Shrestha, S. & Sengupta, P. P. Artificial intelligence in cardiovascular medicine. Curr Treat Opt Cardiovasc Med21, 25. https:\/\/doi.org\/10.1007\/s11936-019-0728-1 (2019).","journal-title":"Curr Treat Opt Cardiovasc Med"},{"key":"70490_CR20","doi-asserted-by":"publisher","DOI":"10.1055\/a-0981-6133","author":"BJ Cho","year":"2019","unstructured":"Cho, B. J. et al. Automated classification of gastric neoplasms in endoscopic images using a convolutional neural network. Endoscopy\nhttps:\/\/doi.org\/10.1055\/a-0981-6133 (2019).","journal-title":"Endoscopy"},{"key":"70490_CR21","doi-asserted-by":"publisher","DOI":"10.1530\/rep-18-0523","author":"R Wang","year":"2019","unstructured":"Wang, R. et al. Artificial intelligence in reproductive medicine. Reproduction (Cambridge, Engand)\nhttps:\/\/doi.org\/10.1530\/rep-18-0523 (2019).","journal-title":"Reproduction (Cambridge, Engand)"},{"key":"70490_CR22","doi-asserted-by":"publisher","first-page":"3518","DOI":"10.3892\/ol.2018.7762","volume":"15","author":"M Sato","year":"2018","unstructured":"Sato, M. et al. Application of deep learning to the classification of images from colposcopy. Oncol Lett15, 3518\u20133523. https:\/\/doi.org\/10.3892\/ol.2018.7762 (2018).","journal-title":"Oncol Lett"},{"key":"70490_CR23","doi-asserted-by":"publisher","first-page":"119","DOI":"10.4137\/cin.s17948","volume":"13","author":"PW Simoes","year":"2014","unstructured":"Simoes, P. W. et al. Classification of images acquired with colposcopy using artificial neural networks. Cancer Inform13, 119\u2013124. https:\/\/doi.org\/10.4137\/cin.s17948 (2014).","journal-title":"Cancer Inform"},{"key":"70490_CR24","doi-asserted-by":"publisher","first-page":"1465","DOI":"10.1097\/AOG.0b013e31827001d5","volume":"120","author":"AG Waxman","year":"2012","unstructured":"Waxman, A. G., Chelmow, D., Darragh, T. M., Lawson, H. & Moscicki, A. B. Revised terminology for cervical histopathology and its implications for management of high-grade squamous intraepithelial lesions of the cervix. Obstet Gynecol120, 1465\u20131471. https:\/\/doi.org\/10.1097\/AOG.0b013e31827001d5 (2012).","journal-title":"Obstet Gynecol"},{"key":"70490_CR25","doi-asserted-by":"publisher","first-page":"1266","DOI":"10.5858\/arpa.LGT200570","volume":"136","author":"TM Darragh","year":"2012","unstructured":"Darragh, T. M. et al. The lower anogenital squamous terminology standardization project for HPV-associated lesions: background and consensus recommendations from the College of American Pathologists and the American Society for colposcopy and cervical pathology. Arch Pathol Lab Med136, 1266\u20131297. https:\/\/doi.org\/10.5858\/arpa.LGT200570 (2012).","journal-title":"Arch Pathol Lab Med"},{"key":"70490_CR26","unstructured":"Huang, G. et al. Snapshot Ensembles: Train 1, get M for free. arXiv e-prints\nhttps:\/\/ui.adsabs.harvard.edu\/abs\/2017arXiv170400109H (2017)."},{"key":"70490_CR27","doi-asserted-by":"crossref","unstructured":"Simth, L. N. Cyclical learning rates for training neural networks. in 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), 464\u2013472 (2016).","DOI":"10.1109\/WACV.2017.58"},{"key":"70490_CR28","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A. & Torralba, A. learning deep features for discriminative localization. arXiv e-prints\nhttps:\/\/ui.adsabs.harvard.edu\/abs\/2015arXiv151204150Z (2015).","DOI":"10.1109\/CVPR.2016.319"},{"key":"70490_CR29","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1056\/NEJMra1814259","volume":"380","author":"A Rajkomar","year":"2019","unstructured":"Rajkomar, A., Dean, J. & Kohane, I. Machine learning in medicine. N Engl J Med380, 1347\u20131358. https:\/\/doi.org\/10.1056\/NEJMra1814259 (2019).","journal-title":"N Engl J Med"},{"key":"70490_CR30","first-page":"626","volume":"91","author":"MF Mitchell","year":"1998","unstructured":"Mitchell, M. F., Schottenfeld, D., Tortolero-Luna, G., Cantor, S. B. & Richards-Kortum, R. Colposcopy for the diagnosis of squamous intraepithelial lesions: a meta-analysis. Obstet Gynecol91, 626\u2013631 (1998).","journal-title":"Obstet Gynecol"},{"key":"70490_CR31","doi-asserted-by":"publisher","first-page":"923","DOI":"10.1093\/jnci\/djy225","volume":"111","author":"L Hu","year":"2019","unstructured":"Hu, L. et al. An observational study of deep learning and automated evaluation of cervical images for cancer screening. J Natl Cancer Inst111, 923\u2013932. https:\/\/doi.org\/10.1093\/jnci\/djy225 (2019).","journal-title":"J Natl Cancer Inst"},{"key":"70490_CR32","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1097\/LGT.0b013e318159408b","volume":"11","author":"TC Wright Jr","year":"2007","unstructured":"Wright, T. C. Jr. et al. 2006 consensus guidelines for the management of women with cervical intraepithelial neoplasia or adenocarcinoma in situ. J Low Genit Tract Dis11, 223\u2013239. https:\/\/doi.org\/10.1097\/LGT.0b013e318159408b (2007).","journal-title":"J Low Genit Tract Dis"},{"key":"70490_CR33","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1016\/s1470-2045(08)70103-7","volume":"9","author":"MR McCredie","year":"2008","unstructured":"McCredie, M. R. et al. Natural history of cervical neoplasia and risk of invasive cancer in women with cervical intraepithelial neoplasia 3: a retrospective cohort study. Lancet Oncol9, 425\u2013434. https:\/\/doi.org\/10.1016\/s1470-2045(08)70103-7 (2008).","journal-title":"Lancet Oncol"},{"key":"70490_CR34","first-page":"426","volume":"5","author":"AM Vasudha","year":"2018","unstructured":"Vasudha, A. M. & Juneja, M. Cervix cancer classification using colposcopy images by deep learning method. Int J Eng Technol Sci Res5, 426\u2013432 (2018).","journal-title":"Int J Eng Technol Sci Res"},{"key":"70490_CR35","doi-asserted-by":"publisher","first-page":"2306","DOI":"10.1109\/TBME.2018.2887208","volume":"66","author":"MN Asiedu","year":"2019","unstructured":"Asiedu, M. N. et al. Development of algorithms for automated detection of cervical pre-cancers with a low-cost, point-of-care, pocket colposcope. IEEE Trans Bio-Med Eng66, 2306\u20132318. https:\/\/doi.org\/10.1109\/TBME.2018.2887208 (2019).","journal-title":"IEEE Trans Bio-Med Eng"},{"key":"70490_CR36","first-page":"199","volume":"01","author":"F Rouhbakhsh","year":"2012","unstructured":"Rouhbakhsh, F., Farokhi, F. & Kangarloo, K. Effective Feature Selection for Pre-Cancerous Cervix Lesions Using Artificial Neural Networks. Int J Smart Electr Eng01, 199\u2013204 (2012).","journal-title":"Int J Smart Electr Eng"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-020-70490-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-020-70490-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-020-70490-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T10:33:33Z","timestamp":1670322813000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-020-70490-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,12]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2020,12]]}},"alternative-id":["70490"],"URL":"https:\/\/doi.org\/10.1038\/s41598-020-70490-4","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8,12]]},"assertion":[{"value":"3 February 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 August 2020","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 of interest"}}],"article-number":"13652"}}