{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T16:11:02Z","timestamp":1792080662445,"version":"4.4.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,11,9]],"date-time":"2020-11-09T00:00:00Z","timestamp":1604880000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,11,9]],"date-time":"2020-11-09T00:00:00Z","timestamp":1604880000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>We hypothesized that, in discrimination between benign and malignant parotid gland tumors, high diagnostic accuracy could be obtained with a small amount of imbalanced data when anomaly detection (AD) was combined with deep leaning (DL) model and the L<jats:sub>2<\/jats:sub>-constrained softmax loss. The purpose of this study was to evaluate whether the proposed method was more accurate than other commonly used DL or AD methods. Magnetic resonance (MR) images of 245 parotid tumors (22.5% malignant) were retrospectively collected. We evaluated the diagnostic accuracy of the proposed method (VGG16-based DL and AD) and that of classification models using conventional DL and AD methods. A radiologist also evaluated the MR images. ROC and precision-recall (PR) analyses were performed, and the area under the curve (AUC) was calculated. In terms of diagnostic performance, the VGG16-based model with the L<jats:sub>2<\/jats:sub>-constrained softmax loss and AD (local outlier factor) outperformed conventional DL and AD methods and a radiologist (ROC-AUC\u2009=\u20090.86 and PR-ROC\u2009=\u20090.77). The proposed method could discriminate between benign and malignant parotid tumors in MR images even when only a small amount of data with imbalanced distribution is available.<\/jats:p>","DOI":"10.1038\/s41598-020-76389-4","type":"journal-article","created":{"date-parts":[[2020,11,9]],"date-time":"2020-11-09T11:05:02Z","timestamp":1604919902000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":43,"title":["Diagnostic accuracy of deep-learning with anomaly detection for a small amount of imbalanced data: discriminating malignant parotid tumors in MRI"],"prefix":"10.1038","volume":"10","author":[{"given":"Hidetoshi","family":"Matsuo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mizuho","family":"Nishio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomonori","family":"Kanda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasuyuki","family":"Kojita","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atsushi K.","family":"Kono","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masatoshi","family":"Hori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masanori","family":"Teshima","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naoki","family":"Otsuki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ken-ichi","family":"Nibu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takamichi","family":"Murakami","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,9]]},"reference":[{"key":"76389_CR1","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1148\/radiology.185.3.1438746","volume":"185","author":"NJM Freling","year":"1992","unstructured":"Freling, N. J. M. et al. Malignant parotid tumors: clinical use of MR imaging and histologic correlation. Radiology 185, 691\u2013696 (1992).","journal-title":"Radiology"},{"key":"76389_CR2","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1259\/dmfr\/15047967","volume":"39","author":"H Yerli","year":"2010","unstructured":"Yerli, H. et al. Diagnosing common parotid tumours with magnetic resonance imaging including diffusion-weighted imaging vs fine-needle aspiration cytology: a comparative study. Dentomaxillofacial Radiol. 39, 349\u2013355 (2010).","journal-title":"Dentomaxillofacial Radiol."},{"key":"76389_CR3","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1097\/MLG.0b013e318158f718","volume":"118","author":"M Supriya","year":"2008","unstructured":"Supriya, M., Denholm, S. & Palmer, T. Seeding of tumor cells after fine needle aspiration cytology in benign parotid tumor: a case report and literature review. Laryngoscope 118, 263\u2013265 (2008).","journal-title":"Laryngoscope"},{"key":"76389_CR4","doi-asserted-by":"publisher","first-page":"e0195875","DOI":"10.1371\/journal.pone.0195875","volume":"13","author":"M Nishio","year":"2018","unstructured":"Nishio, M. et al. Computer-aided diagnosis of lung nodule using gradient tree boosting and Bayesian optimization. PLoS ONE 13, e0195875 (2018).","journal-title":"PLoS ONE"},{"key":"76389_CR5","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. Nature 542, 115\u2013118 (2017).","journal-title":"Nature"},{"key":"76389_CR6","doi-asserted-by":"publisher","DOI":"10.1038\/s41374-020-0442-3","author":"H Miyoshi","year":"2020","unstructured":"Miyoshi, H. et al. Deep learning shows the capability of high-level computer-aided diagnosis in malignant lymphoma. Lab. Invest. https:\/\/doi.org\/10.1038\/s41374-020-0442-3 (2020).","journal-title":"Lab. Invest."},{"key":"76389_CR7","doi-asserted-by":"publisher","first-page":"101198","DOI":"10.1016\/j.techsoc.2019.101198","volume":"60","author":"M Coccia","year":"2020","unstructured":"Coccia, M. Deep learning technology for improving cancer care in society: new directions in cancer imaging driven by artificial intelligence. Technol. Soc. 60, 101198 (2020).","journal-title":"Technol. Soc."},{"key":"76389_CR8","doi-asserted-by":"publisher","DOI":"10.1364\/boe.381257","author":"M Halicek","year":"2020","unstructured":"Halicek, M., Dormer, J. D., Little, J. V., Chen, A. Y. & Fei, B. Tumor detection of the thyroid and salivary glands using hyperspectral imaging and deep learning. Biomed. Opt. Express https:\/\/doi.org\/10.1364\/boe.381257 (2020).","journal-title":"Biomed. Opt. Express"},{"key":"76389_CR9","doi-asserted-by":"crossref","unstructured":"Fruehwald-Pallamar, J. et al. Texture-based and diffusion-weighted discrimination of parotid gland lesions on MR images at 3.0 Tesla. NMR Biomed. 26, 1372\u20131379 (2013).","DOI":"10.1002\/nbm.2962"},{"key":"76389_CR10","doi-asserted-by":"publisher","first-page":"1525","DOI":"10.1016\/j.ultrasmedbio.2010.06.009","volume":"36","author":"S Siebers","year":"2010","unstructured":"Siebers, S. et al. Computer aided diagnosis of parotid gland lesions using ultrasonic multi-feature tissue characterization. Ultrasound Med. Biol. 36, 1525\u20131534 (2010).","journal-title":"Ultrasound Med. Biol."},{"key":"76389_CR11","unstructured":"Fornaciali, M., Carvalho, M., Bittencourt, F. V., Avila, S. & Valle, E. Towards Automated Melanoma Screening: Proper Computer Vision & Reliable Results. arXiv Prepr. arXiv:1609.01228 (2016)."},{"key":"76389_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-018-0162-3","volume":"6","author":"JM Johnson","year":"2019","unstructured":"Johnson, J. M. & Khoshgoftaar, T. M. Survey on deep learning with class imbalance. J. Big Data 6, 1\u201354 (2019).","journal-title":"J. Big Data"},{"key":"76389_CR13","unstructured":"Simonyan, K. & Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv Prepr. arXiv1409.1556 (2014)."},{"key":"76389_CR14","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":"76389_CR15","doi-asserted-by":"publisher","unstructured":"Breunig, M. M., Kriegel, H.-P., Ng, R. T. & Sander, J. LOF: identifying density-based local outliers. in Proceedings of the 2000 ACM SIGMOD international conference on Management of data - SIGMOD \u201900 93\u2013104 (ACM Press, 2000). doi:https:\/\/doi.org\/10.1145\/342009.335388.","DOI":"10.1145\/342009.335388"},{"key":"76389_CR16","unstructured":"Kingma, D. P. & Ba, J. L. Adam: A method for stochastic optimization. in 3rd International Conference on Learning Representations, ICLR 2015\u2014Conference Track Proceedings (International Conference on Learning Representations, ICLR, 2015)."},{"key":"76389_CR17","unstructured":"Ranjan, R., Castillo, C. D. & Chellappa, R. L2-constrained softmax loss for discriminative face verification. arXiv Prepr. arXiv1703.09507 (2017)."},{"key":"76389_CR18","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F. et al. Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011).","journal-title":"J. Mach. Learn. Res."},{"key":"76389_CR19","unstructured":"Dana, K., Ginneken, B. Van, Nayar, S. & Koenderink, J. Columbia-utrecht reflectance and texture database. (1997)."},{"key":"76389_CR20","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S. & Yang, Y. Random erasing data augmentation. arXiv Prepr. arXiv1708.04896 (2017)."},{"key":"76389_CR21","unstructured":"Zhang, H., Cisse, M., Dauphin, Y. N. & Lopez-Paz, D. mixup: Beyond empirical risk minimization. arXiv Prepr. arXiv1710.09412 (2017)."},{"key":"76389_CR22","first-page":"3581","volume":"4","author":"DP Kingma","year":"2014","unstructured":"Kingma, D. P., Rezende, D. J., Mohamed, S. & Welling, M. Semi-supervised learning with deep generative models. Adv. Neural Inf. Process. Syst. 4, 3581\u20133589 (2014).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"76389_CR23","unstructured":"Howard, A. G. et al. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv Prepr arXiv:1704.04861 (2017)."},{"key":"76389_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition vols 2016-December 770\u2013778 (IEEE Computer Society, 2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"76389_CR25","doi-asserted-by":"publisher","first-page":"1443","DOI":"10.1162\/089976601750264965","volume":"13","author":"B Sch\u00f6lkopf","year":"2001","unstructured":"Sch\u00f6lkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J. & Williamson, R. C. Estimating the support of a high-dimensional distribution. Neural Comput. 13, 1443\u20131471 (2001).","journal-title":"Neural Comput."},{"key":"76389_CR26","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten, L. & Hinton, G. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579\u20132605 (2008).","journal-title":"J. Mach. Learn. Res."},{"key":"76389_CR27","unstructured":"Applications - Keras Documentation. https:\/\/keras.io\/applications\/."},{"key":"76389_CR28","doi-asserted-by":"publisher","first-page":"1462","DOI":"10.1007\/s003300050576","volume":"8","author":"S Schick","year":"1998","unstructured":"Schick, S. et al. Differentiation of benign and malignant tumors of the parotid gland: value of pulsed Doppler and color Doppler sonography. Eur. Radiol. 8, 1462\u20131467 (1998).","journal-title":"Eur. Radiol."},{"key":"76389_CR29","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1148\/radiol.2262011486","volume":"226","author":"H Yabuuchi","year":"2003","unstructured":"Yabuuchi, H. et al. Salivary gland tumors: Diagnostic value of gadolinium-enhanced dynamic MR imaging with histopathologic correlation. Radiology 226, 345\u2013354 (2003).","journal-title":"Radiology"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-020-76389-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-020-76389-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-020-76389-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T22:56:10Z","timestamp":1670367370000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-020-76389-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,9]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2020,12]]}},"alternative-id":["76389"],"URL":"https:\/\/doi.org\/10.1038\/s41598-020-76389-4","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,9]]},"assertion":[{"value":"19 June 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 October 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 November 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 interests"}}],"article-number":"19388"}}