{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T01:37:59Z","timestamp":1793065079205,"version":"4.5.0"},"reference-count":42,"publisher":"IOP Publishing","issue":"23","license":[{"start":{"date-parts":[[2019,12,5]],"date-time":"2019-12-05T00:00:00Z","timestamp":1575504000000},"content-version":"vor","delay-in-days":4,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2019,12,5]],"date-time":"2019-12-05T00:00:00Z","timestamp":1575504000000},"content-version":"tdm","delay-in-days":4,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2019,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The purpose of this study was to develop a computer-aided diagnosis (CAD) system for the classification of malignant and benign masses in the breast using ultrasonography based on a convolutional neural network (CNN), a state-of-the-art deep learning technique. We explored the regions for the correct classification by generating a heat map that presented the important regions used by the CNN for human malignancy\/benign classification. Clinical data was obtained from a large-scale clinical trial previously conducted by the Japan Association of Breast and Thyroid Sonology. Images of 1536 breast masses (897 malignant and 639 benign) confirmed by pathological examinations were collected, with each breast mass captured from various angles using an ultrasound (US) imaging probe. We constructed an ensemble network by combining two CNN models (VGG19 and ResNet152) fine-tuned on balanced training data with augmentation and used the mass-level classification method to enable the CNN to classify a given mass using all views. For an independent test set consisting of 154 masses (77 malignant and 77 benign), our network showed outstanding classification performance with a sensitivity of 90.9% (95% confidence interval 84.5\u201397.3), a specificity of 87.0% (79.5\u201394.5), and area under the curve (AUC) of 0.951 (0.916\u20130.987) compared to that of the two CNN models. In addition, our study indicated that the breast masses themselves were not detected by the CNN as important regions for correct mass classification. Collectively, this CNN-based CAD system is expected to assist doctors by improving the diagnosis of breast cancer in clinical practice.<\/jats:p>","DOI":"10.1088\/1361-6560\/ab5093","type":"journal-article","created":{"date-parts":[[2019,10,23]],"date-time":"2019-10-23T19:00:39Z","timestamp":1571857239000},"page":"235013","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":117,"title":["Computer-aided diagnosis system for breast ultrasound images using deep learning"],"prefix":"10.1088","volume":"64","author":[{"given":"Hiroki","family":"Tanaka","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shih-Wei","family":"Chiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takanori","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Setsuko","family":"Kaoku","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takuhiro","family":"Yamaguchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2019,12,5]]},"reference":[{"key":"pmbab5093bib001","doi-asserted-by":"publisher","first-page":"1621","DOI":"10.2214\/ajr.172.6.10350302","type":"journal-article","article-title":"Sonography of solid breast lesions: observer variability of lesion description and assessment","volume":"172","author":"Baker","year":"1999","journal-title":"Am. J. Roentgenol."},{"key":"pmbab5093bib002","doi-asserted-by":"publisher","first-page":"2151","DOI":"10.1001\/jama.299.18.2151","type":"journal-article","article-title":"Combined screening with ultrasound and mammography versus mammography alone in women at elevated risk of breast cancer","volume":"299","author":"Berg","year":"2008","journal-title":"JAMA"},{"key":"pmbab5093bib003","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1002\/mp.13361","type":"journal-article","article-title":"Breast mass classification in sonography with transfer learning using a deep convolutional neural network and color conversion","volume":"46","author":"Byra","year":"2019","journal-title":"Med. Phys."},{"key":"pmbab5093bib004","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1016\/j.acra.2011.10.023","type":"journal-article","article-title":"Evaluation of the accuracy of a computer-aided diagnosis (CAD) system in breast ultrasound according to the radiologist\u2019s experience","volume":"19","author":"Chabi","year":"2012","journal-title":"Acad. Radiol."},{"key":"pmbab5093bib005","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1016\/j.patcog.2009.05.012","type":"journal-article","article-title":"Automated breast cancer detection and classification using ultrasound images: a survey","volume":"43","author":"Cheng","year":"2010","journal-title":"Pattern Recogn."},{"key":"pmbab5093bib006","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1002\/jum.14332","type":"journal-article","article-title":"Application of computer-aided diagnosis on breast ultrasonography: evaluation of diagnostic performances and agreement of radiologists according to different levels of experience","volume":"37","author":"Cho","year":"2018","journal-title":"J. Ultrasound. Med."},{"key":"pmbab5093bib007","doi-asserted-by":"publisher","first-page":"177","DOI":"10.2214\/ajr.181.1.1810177","type":"journal-article","article-title":"Using sonography to screen women with mammographically dense breasts","volume":"181","author":"Crystal","year":"2003","journal-title":"Am. J. Roentgenol."},{"key":"pmbab5093bib008","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","type":"other","article-title":"ImageNet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"pmbab5093bib009","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1007\/s10278-012-9499-x","type":"journal-article","article-title":"Breast ultrasound image classification based on multiple-instance learning","volume":"25","author":"Ding","year":"2012","journal-title":"J. Digit. Imaging"},{"key":"pmbab5093bib010","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","type":"journal-article","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"pmbab5093bib011","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1007\/s11604-019-00831-5","type":"journal-article","article-title":"Distinction between benign and malignant breast masses at breast ultrasound using deep learning method with convolutional neural network","volume":"6","author":"Fujioka","year":"2019","journal-title":"Japan. J. Radiol."},{"key":"pmbab5093bib012","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1148\/rg.352140106","type":"journal-article","article-title":"Mammographic breast density: impact on breast cancer risk and implications for screening","volume":"35","author":"Freer","year":"2015","journal-title":"Radiographics"},{"key":"pmbab5093bib013","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1146\/annurev-bioeng-071812-152416","type":"journal-article","article-title":"Breast image analysis for risk assessment, detection, diagnosis, and treatment of cancer","volume":"15","author":"Giger","year":"2013","journal-title":"Annu. Rev. Biomed. Eng."},{"key":"pmbab5093bib014","doi-asserted-by":"publisher","first-page":"2402","DOI":"10.1001\/jama.2016.17216","type":"journal-article","article-title":"Development and validation of a Deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs","volume":"316","author":"Gulshan","year":"2016","journal-title":"JAMA"},{"key":"pmbab5093bib015","doi-asserted-by":"publisher","first-page":"7714","DOI":"10.1088\/1361-6560\/aa82ec","type":"journal-article","article-title":"A deep learning framework for supporting the classification of breast lesions in ultrasound Images","volume":"62","author":"Han","year":"2017","journal-title":"Phys. Med. Biol."},{"key":"pmbab5093bib016","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1148\/radiology.143.1.7063747","type":"journal-article","article-title":"The meaning and use of the area under a receiver operating characteristic (ROC) curve","volume":"143","author":"Hanley","year":"1982","journal-title":"Radiology"},{"key":"pmbab5093bib017","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","type":"other","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"pmbab5093bib018","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/s12938-019-0626-5","type":"journal-article","article-title":"Two-stage CNNs for computerized BI-RADS categorization in breast ultrasound images","volume":"18","author":"Huang","year":"2019","journal-title":"Biomed. Eng. Online"},{"key":"pmbab5093bib019","first-page":"979","type":"other","article-title":"Differential data augmentation techniques for medical imaging classification tasks","volume":"vol 2017","author":"Hussain","year":"2017"},{"key":"pmbab5093bib020","first-page":"448","type":"other","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"vol 37","author":"Ioffe","year":"2015"},{"key":"pmbab5093bib021","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2016\/6212684","type":"journal-article","article-title":"Ensemble Deep learning for biomedical time series classification","volume":"45","author":"Jin","year":"2016","journal-title":"Comput. Intell. Neurosci."},{"key":"pmbab5093bib022","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2015","type":"other"},{"key":"pmbab5093bib023","doi-asserted-by":"publisher","first-page":"1017","DOI":"10.1002\/mp.12110","type":"journal-article","article-title":"Discriminating solitary cysts from soft tissue lesions in mammography using a pretrained deep convolutional neural network","volume":"44","author":"Kooi","year":"2017","journal-title":"Med. Phys."},{"key":"pmbab5093bib024","first-page":"25","type":"journal-article","article-title":"Handling imbalanced datasets: a review","volume":"30","author":"Kotsiantis","year":"2006","journal-title":"GESTS Int. Trans. Comput. Sci. Eng."},{"key":"pmbab5093bib025","first-page":"1097","type":"journal-article","article-title":"Imagenet classification with deep convolutional neural networks","volume":"1","author":"Krizhevsky","year":"2012","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"pmbab5093bib026","doi-asserted-by":"publisher","first-page":"5356","DOI":"10.1016\/j.eswa.2015.02.005","type":"journal-article","article-title":"Image based computer aided diagnosis system for cancer detection","volume":"42","author":"Lee","year":"2015","journal-title":"Expert Syst. Appl."},{"key":"pmbab5093bib027","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1016\/j.ultras.2016.09.011","type":"journal-article","article-title":"A pre-trained convolutional neural network based method for thyroid nodule diagnosis","volume":"73","author":"Ma","year":"2017","journal-title":"Ultrasonics"},{"key":"pmbab5093bib028","doi-asserted-by":"publisher","first-page":"1236","DOI":"10.1093\/bib\/bbx044","type":"journal-article","article-title":"Deep learning for healthcare: review, opportunities and challenges","volume":"19","author":"Miotto","year":"2018","journal-title":"Brief. Bioinform."},{"key":"pmbab5093bib029","doi-asserted-by":"publisher","first-page":"987","DOI":"10.1109\/TMI.2006.877092","type":"journal-article","article-title":"Ultrasound Image segmentation: a survey","volume":"25","author":"Noble","year":"2006","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbab5093bib030","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1016\/S0140-6736(15)00774-6","type":"journal-article","article-title":"Sensitivity and specificity of mammography and adjunctive ultrasonography to screen for breast cancer in the Japan Strategic Anti-cancer Randomized Trial (J-START): a randomised controlled trial","volume":"387","author":"Ohuchi","year":"2016","journal-title":"Lancet"},{"key":"pmbab5093bib031","doi-asserted-by":"publisher","first-page":"2241","DOI":"10.1088\/0031-9155\/50\/10\/004","type":"journal-article","article-title":"Application of the compound probability density function for characterization of breast masses in ultrasound B scans","volume":"50","author":"Shankar","year":"2005","journal-title":"Phys. Med. Biol."},{"key":"pmbab5093bib032","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.ebiom.2017.10.014","type":"journal-article","article-title":"Application of convolutional neural networks in the diagnosis of helicobacter pylori infection based on endoscopic images","volume":"25","author":"Shinchijo","year":"2017","journal-title":"EBioMedicine"},{"key":"pmbab5093bib033","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","type":"other"},{"key":"pmbab5093bib034","author":"Smith","year":"2017","type":"book"},{"key":"pmbab5093bib035","first-page":"1929","type":"journal-article","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"pmbab5093bib036","doi-asserted-by":"publisher","first-page":"2264","DOI":"10.1111\/j.1349-7006.2008.00926.x","type":"journal-article","article-title":"Age-specific interval breast cancers in Japan: estimation of the proper sensitivity of screening using a population-based cancer registry","volume":"99","author":"Suzuki","year":"2008","journal-title":"Cancer Sci."},{"key":"pmbab5093bib037","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/s12194-017-0406-5","type":"journal-article","article-title":"Overview of deep learning in medical imaging","volume":"10","author":"Suzuki","year":"2017","journal-title":"Radiol. Phys. Technol."},{"key":"pmbab5093bib038","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.ijmedinf.2017.02.004","type":"journal-article","article-title":"Computer-aided diagnosis: a survey with bibliometric analysis","volume":"101","author":"Takahashi","year":"2017","journal-title":"Int. J. Med. Inform."},{"key":"pmbab5093bib039","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1007\/s12282-016-0707-2","type":"journal-article","article-title":"The need for supplemental breast cancer screening modalities: a perspective of population-based breast cancer screening programs in Japan","volume":"24","author":"Uematsu","year":"2016","journal-title":"Breast Cancer"},{"key":"pmbab5093bib040","doi-asserted-by":"publisher","first-page":"3193","DOI":"10.1002\/jum.15020","type":"journal-article","article-title":"Computer-aided diagnosis of solid breast lesions with ultrasound: factors associated with false-negative and false-positive results","volume":"38","author":"Wu","year":"2019","journal-title":"J. Ultrasound. Med."},{"key":"pmbab5093bib041","doi-asserted-by":"publisher","first-page":"4605191","DOI":"10.1155\/2018\/4605191","type":"journal-article","article-title":"Comparison of transferred deep neural networks in ultrasonic breast masses discrimination","volume":"2018","author":"Xiao","year":"2018","journal-title":"Biomed. Res. Int."},{"key":"pmbab5093bib042","first-page":"818","type":"other","article-title":"Visualizing and understanding convolutional networks","author":"Zeiler","year":"2014"}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"http:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ab5093","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"http:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ab5093\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ab5093\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ab5093","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ab5093","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ab5093\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ab5093\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ab5093\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ab5093\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ab5093\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ab5093","content-type":"text\/html","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ab5093\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T12:39:38Z","timestamp":1770467978000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ab5093"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,1]]},"references-count":42,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2019,12,5]]},"published-print":{"date-parts":[[2019,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/ab5093","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,12,1]]},"assertion":[{"value":"Computer-aided diagnosis system for breast ultrasound images using deep learning","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2019 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2019-05-16","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2019-10-23","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2019-12-05","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}