{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:09:34Z","timestamp":1792022974013,"version":"4.4.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2023,4,18]],"date-time":"2023-04-18T00:00:00Z","timestamp":1681776000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,4,18]],"date-time":"2023-04-18T00:00:00Z","timestamp":1681776000000},"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":["Jpn J Radiol"],"published-print":{"date-parts":[[2023,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Purpose<\/jats:title>\n                <jats:p>To evaluate the diagnostic performance of deep learning using the Residual Networks 50 (ResNet50) neural network constructed from different segmentations for distinguishing malignant and benign non-mass enhancement (NME) on breast magnetic resonance imaging (MRI) and conduct a comparison with radiologists with various levels of experience.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Materials and methods<\/jats:title>\n                <jats:p>A total of 84 consecutive patients with 86 lesions (51 malignant, 35 benign) presenting NME on breast MRI were analyzed. Three radiologists with different levels of experience evaluated all examinations, based on the Breast Imaging-Reporting and Data System (BI-RADS) lexicon and categorization. For the deep learning method, one expert radiologist performed lesion annotation manually using the early phase of dynamic contrast-enhanced (DCE) MRI. Two segmentation methods were applied: a precise segmentation was carefully set to include only the enhancing area, and a rough segmentation covered the whole enhancing region, including the intervenient non-enhancing area. ResNet50 was implemented using the DCE MRI input. The diagnostic performance of the radiologists\u2019 readings and deep learning were then compared using receiver operating curve analysis.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>The ResNet50 model from precise segmentation achieved diagnostic accuracy equivalent [area under the curve (AUC)\u2009=\u20090.91, 95% confidence interval (CI) 0.90, 0.93] to that of a highly experienced radiologist (AUC\u2009=\u20090.89, 95% CI 0.81, 0.96; <jats:italic>p<\/jats:italic>\u2009=\u20090.45). Even the model from rough segmentation showed diagnostic performance equivalent to a board-certified radiologist (AUC\u2009=\u20090.80, 95% CI 0.78, 0.82 vs. AUC\u2009=\u20090.79, 95% CI 0.70, 0.89, respectively). Both ResNet50 models from the precise and rough segmentation exceeded the diagnostic accuracy of a radiology resident (AUC\u2009=\u20090.64, 95% CI 0.52, 0.76).<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusion<\/jats:title>\n                <jats:p>These findings suggest that the deep learning model from ResNet50 has the potential to ensure accuracy in the diagnosis of NME on breast MRI.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1007\/s11604-023-01435-w","type":"journal-article","created":{"date-parts":[[2023,4,18]],"date-time":"2023-04-18T05:31:57Z","timestamp":1681795917000},"page":"1094-1103","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Use of a deep learning algorithm for non-mass enhancement on breast MRI: comparison with radiologists\u2019 interpretations at various levels"],"prefix":"10.1007","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4161-3201","authenticated-orcid":false,"given":"Mariko","family":"Goto","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Koji","family":"Sakai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasuchiyo","family":"Toyama","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshitomo","family":"Nakai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kei","family":"Yamada","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,4,18]]},"reference":[{"key":"1435_CR1","doi-asserted-by":"publisher","first-page":"3669","DOI":"10.1007\/s00330-015-3807-z","volume":"25","author":"RM Mann","year":"2015","unstructured":"Mann RM, Balleyguier C, Baltzer PA, Bick U, Colin C, Cornford E, et al. Breast MRI: EUSOBI recommendations for women\u2019s information. Eur Radiol. 2015;25:3669\u201378.","journal-title":"Eur Radiol"},{"key":"1435_CR2","unstructured":"Radiology ACo. ACR practice parameter for the performance of contrast enhanced magnetic resonance imaging (MRI) of the breast. 2018:https:\/\/www.acr.org\/-\/media\/acr\/files\/practice-parameters\/mr-contrast-breast.pdf."},{"key":"1435_CR3","unstructured":"American College of Radiology Breast Imaging Reporting and Data System (BI-RADS), vol 2013, 5th edn. American College of Radiology. 2013."},{"key":"1435_CR4","doi-asserted-by":"publisher","first-page":"219","DOI":"10.2214\/AJR.14.12656","volume":"204","author":"T Chadashvili","year":"2015","unstructured":"Chadashvili T, Ghosh E, Fein-Zachary V, Mehta TS, Venkataraman S, Dialani V, et al. Nonmass enhancement on breast MRI: review of patterns with radiologic-pathologic correlation and discussion of management. AJR Am J Roentgenol. 2015;204:219\u201327.","journal-title":"AJR Am J Roentgenol"},{"key":"1435_CR5","doi-asserted-by":"crossref","unstructured":"Lunkiewicz M, Forte S, Freiwald B, Singer G, Leo C, Kubik-Huch RA. Interobserver variability and likelihood of malignancy for fifth edition BI-RADS MRI descriptors in non-mass breast lesions. Eur Radiol. 2020;30:77\u201386.","DOI":"10.1007\/s00330-019-06312-7"},{"key":"1435_CR6","doi-asserted-by":"publisher","first-page":"994","DOI":"10.2214\/AJR.08.1983","volume":"193","author":"RL Gutierrez","year":"2009","unstructured":"Gutierrez RL, DeMartini WB, Eby PR, Kurland BF, Peacock S, Lehman CD. BI-RADS lesion characteristics predict likelihood of malignancy in breast MRI for masses but not for nonmasslike enhancement. AJR Am J Roentgenol. 2009;193:994\u20131000.","journal-title":"AJR Am J Roentgenol"},{"key":"1435_CR7","doi-asserted-by":"publisher","first-page":"1658","DOI":"10.2214\/AJR.09.3486","volume":"194","author":"PA Baltzer","year":"2010","unstructured":"Baltzer PA, Benndorf M, Dietzel M, Gajda M, Runnebaum IB, Kaiser WA. False-positive findings at contrast-enhanced breast MRI: a BI-RADS descriptor study. AJR Am J Roentgenol. 2010;194:1658\u201363.","journal-title":"AJR Am J Roentgenol"},{"key":"1435_CR8","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1007\/s12282-021-01229-w","volume":"28","author":"M Tozaki","year":"2021","unstructured":"Tozaki M, Yabuuchi H, Goto M, Sasaki M, Kubota K, Nakahara H. Effects of gadobutrol on background parenchymal enhancement and differential diagnosis between benign and malignant lesions in dynamic magnetic resonance imaging of the breast. Breast Cancer. 2021;28:927\u201336.","journal-title":"Breast Cancer"},{"key":"1435_CR9","doi-asserted-by":"publisher","first-page":"558","DOI":"10.1111\/j.1524-4741.2010.00968.x","volume":"16","author":"C Moraes Pde","year":"2010","unstructured":"Moraes Pde C, Chala LF, Chang YS, Kim SJ, Endo E, de Barros N, et al. Observer variability in the application of morphologic and dynamic criteria according to the BI-RADS for MRI. Breast J. 2010;16:558\u201360.","journal-title":"Breast J"},{"key":"1435_CR10","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1016\/j.ejrad.2014.10.023","volume":"84","author":"PAT Baltzer","year":"2015","unstructured":"Baltzer PAT, Kaiser WA, Dietzel M. Lesion type and reader experience affect the diagnostic accuracy of breast MRI: a multiple reader ROC study. Eur J Radiol. 2015;84:86\u201391.","journal-title":"Eur J Radiol"},{"key":"1435_CR11","doi-asserted-by":"publisher","first-page":"998","DOI":"10.1002\/jmri.26852","volume":"52","author":"B Reig","year":"2020","unstructured":"Reig B, Heacock L, Geras KJ, Moy L. Machine learning in breast MRI. J Magn Reson Imaging. 2020;52:998\u20131018.","journal-title":"J Magn Reson Imaging"},{"key":"1435_CR12","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1148\/radiol.2018181352","volume":"290","author":"D Truhn","year":"2019","unstructured":"Truhn D, Schrading S, Haarburger C, Schneider H, Merhof D, Kuhl C. Radiomic versus convolutional neural networks analysis for classification of contrast-enhancing lesions at multiparametric breast MRI. Radiology. 2019;290:290\u20137.","journal-title":"Radiology"},{"key":"1435_CR13","doi-asserted-by":"publisher","first-page":"798","DOI":"10.1002\/jmri.26981","volume":"51","author":"J Zhou","year":"2020","unstructured":"Zhou J, Zhang Y, Chang KT, Lee KE, Wang O, Li J, et al. Diagnosis of benign and malignant breast lesions on DCE-MRI by using radiomics and deep learning with consideration of peritumor tissue. J Magn Reson Imaging. 2020;51:798\u2013809.","journal-title":"J Magn Reson Imaging"},{"key":"1435_CR14","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2021.728224","volume":"11","author":"J Zhou","year":"2021","unstructured":"Zhou J, Liu YL, Zhang Y, Chen JH, Combs FJ, Parajuli R, et al. BI-RADS reading of non-mass lesions on DCE-MRI and differential diagnosis performed by radiomics and deep learning. Front Oncol. 2021;11: 728224.","journal-title":"Front Oncol"},{"key":"1435_CR15","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1007\/s11604-017-0717-9","volume":"36","author":"T Asada","year":"2018","unstructured":"Asada T, Yamada T, Kanemaki Y, Fujiwara K, Okamoto S, Nakajima Y. Grading system to categorize breast MRI using BI-RADS 5th edition: a statistical study of non-mass enhancement descriptors in terms of probability of malignancy. Jpn J Radiol. 2018;36:200\u20138.","journal-title":"Jpn J Radiol"},{"key":"1435_CR16","doi-asserted-by":"publisher","first-page":"330","DOI":"10.2214\/AJR.05.0998","volume":"187","author":"M Tozaki","year":"2006","unstructured":"Tozaki M, Fukuda K. High-spatial-resolution MRI of non-masslike breast lesions: interpretation model based on BI-RADS MRI descriptors. AJR Am J Roentgenol. 2006;187:330\u20137.","journal-title":"AJR Am J Roentgenol"},{"key":"1435_CR17","doi-asserted-by":"publisher","first-page":"313","DOI":"10.2214\/AJR.05.0881","volume":"187","author":"M Tozaki","year":"2006","unstructured":"Tozaki M, Igarashi T, Fukuda K. Breast MRI using the VIBE sequence: clustered ring enhancement in the differential diagnosis of lesions showing non-masslike enhancement. AJR Am J Roentgenol. 2006;187:313\u201321.","journal-title":"AJR Am J Roentgenol"},{"key":"1435_CR18","doi-asserted-by":"crossref","unstructured":"Maltez de Almeida JR, Gomes AB, Barros TP, Fahel PE, de Seixas Rocha M. Subcategorization of Suspicious Breast Lesions (BI-RADS Category 4) According to MRI Criteria: Role of Dynamic Contrast-Enhanced and Diffusion-Weighted Imaging. AJR Am J Roentgenol. 2015;205:222\u201331.","DOI":"10.2214\/AJR.14.13834"},{"key":"1435_CR19","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. In: 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 2015, pp. 1026\u20131034.","DOI":"10.1109\/ICCV.2015.123"},{"key":"1435_CR20","doi-asserted-by":"publisher","first-page":"1382","DOI":"10.1002\/jmri.22567","volume":"33","author":"SA Jansen","year":"2011","unstructured":"Jansen SA, Shimauchi A, Zak L, Fan X, Karczmar GS, Newstead GM. The diverse pathology and kinetics of mass, nonmass, and focus enhancement on MR imaging of the breast. J Magn Reson Imaging. 2011;33:1382\u20139.","journal-title":"J Magn Reson Imaging"},{"key":"1435_CR21","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1007\/s11604-020-01029-w","volume":"39","author":"M Honda","year":"2021","unstructured":"Honda M, Kataoka M, Kawaguchi K, Iima M, Miyake KK, Kishimoto AO, et al. Subcategory classifications of Breast Imaging and Data System (BI-RADS) category 4 lesions on MRI. Jpn J Radiol. 2021;39:56\u201365.","journal-title":"Jpn J Radiol"},{"key":"1435_CR22","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1016\/j.pbiomolbio.2011.06.006","volume":"106","author":"Y Kim","year":"2011","unstructured":"Kim Y, Stolarska MA, Othmer HG. The role of the microenvironment in tumor growth and invasion. Prog Biophys Mol Biol. 2011;106:353\u201379.","journal-title":"Prog Biophys Mol Biol"},{"key":"1435_CR23","doi-asserted-by":"publisher","first-page":"991","DOI":"10.2217\/fon-2016-0501","volume":"13","author":"JS Wu","year":"2017","unstructured":"Wu JS, Sheng SR, Liang XH, Tang YL. The role of tumor microenvironment in collective tumor cell invasion. Future Oncol. 2017;13:991\u20131002.","journal-title":"Future Oncol"},{"key":"1435_CR24","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1148\/radiol.2017171157","volume":"287","author":"H Cheon","year":"2018","unstructured":"Cheon H, Kim HJ, Kim TH, Ryeom HK, Lee J, Kim GC, et al. Invasive breast cancer: prognostic value of peritumoral edema identified at preoperative MR imaging. Radiology. 2018;287:68\u201375.","journal-title":"Radiology"},{"key":"1435_CR25","doi-asserted-by":"publisher","first-page":"1004","DOI":"10.1016\/j.ejrad.2016.02.017","volume":"85","author":"HJ Shin","year":"2016","unstructured":"Shin HJ, Park JY, Shin KC, Kim HH, Cha JH, Chae EY, et al. Characterization of tumor and adjacent peritumoral stroma in patients with breast cancer using high-resolution diffusion-weighted imaging: correlation with pathologic biomarkers. Eur J Radiol. 2016;85:1004\u201311.","journal-title":"Eur J Radiol"},{"key":"1435_CR26","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/j.acra.2005.08.035","volume":"13","author":"W Chen","year":"2006","unstructured":"Chen W, Giger ML, Bick U. A fuzzy c-means (FCM)-based approach for computerized segmentation of breast lesions in dynamic contrast-enhanced MR images. Acad Radiol. 2006;13:63\u201372.","journal-title":"Acad Radiol"},{"key":"1435_CR27","doi-asserted-by":"publisher","DOI":"10.1155\/2015\/450531","volume":"2015","author":"Z Pang","year":"2015","unstructured":"Pang Z, Zhu D, Chen D, Li L, Shao Y. A computer-aided diagnosis system for dynamic contrast-enhanced MR images based on level set segmentation and ReliefF feature selection. Comput Math Methods Med. 2015;2015: 450531.","journal-title":"Comput Math Methods Med"},{"key":"1435_CR28","volume":"5","author":"MU Dalmis","year":"2018","unstructured":"Dalmis MU, Vreemann S, Kooi T, Mann RM, Karssemeijer N, Gubern-Merida A. Fully automated detection of breast cancer in screening MRI using convolutional neural networks. J Med Imaging (Bellingham). 2018;5: 014502.","journal-title":"J Med Imaging (Bellingham)."},{"key":"1435_CR29","doi-asserted-by":"publisher","first-page":"4857","DOI":"10.1007\/s00330-022-08553-5","volume":"32","author":"L Wang","year":"2022","unstructured":"Wang L, Chang L, Luo R, Cui X, Liu H, Wu H, et al. An artificial intelligence system using maximum intensity projection MR images facilitates classification of non-mass enhancement breast lesions. Eur Radiol. 2022;32:4857\u201367.","journal-title":"Eur Radiol"}],"container-title":["Japanese Journal of Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11604-023-01435-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11604-023-01435-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11604-023-01435-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,30]],"date-time":"2023-09-30T04:18:40Z","timestamp":1696047520000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11604-023-01435-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,18]]},"references-count":29,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["1435"],"URL":"https:\/\/doi.org\/10.1007\/s11604-023-01435-w","relation":{},"ISSN":["1867-1071","1867-108X"],"issn-type":[{"value":"1867-1071","type":"print"},{"value":"1867-108X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,18]]},"assertion":[{"value":"16 February 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 April 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 April 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Koji Sakai serves as an associate professor of a joint research laboratory supported by Doctor-NET Inc. Kei Yamada received research funding from Guerbet and GE Healthcare. Mariko Goto, Yasuchiyo Toyama, and Yoshitomo Nakai have no conflicts of interest to declare.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Approval was obtained from the institutional ethics committee of the Kyoto Prefectural University of Medicine (ERB-C-860\u20131).","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical statement"}}]}}