{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:41:38Z","timestamp":1790728898762,"version":"4.1.0"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>A wide variety of benign and malignant processes can manifest as non-mass enhancement (NME) in breast MRI. Compared to mass lesions, there are no distinct features that can be used for differential diagnosis. The purpose is to use the BI-RADS descriptors and models developed using radiomics and deep learning to distinguish benign from malignant NME lesions.<\/jats:p><\/jats:sec><jats:sec><jats:title>Materials and Methods<\/jats:title><jats:p>A total of 150 patients with 104 malignant and 46 benign NME were analyzed. Three radiologists performed reading for morphological distribution and internal enhancement using the 5th BI-RADS lexicon. For each case, the 3D tumor mask was generated using Fuzzy-C-Means segmentation. Three DCE parametric maps related to wash-in, maximum, and wash-out were generated, and PyRadiomics was applied to extract features. The radiomics model was built using five machine learning algorithms. ResNet50 was implemented using three parametric maps as input. Approximately 70% of earlier cases were used for training, and 30% of later cases were held out for testing.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The diagnostic BI-RADS in the original MRI report showed that 104\/104 malignant and 36\/46 benign lesions had a BI-RADS score of 4A\u20135. For category reading, the kappa coefficient was 0.83 for morphological distribution (excellent) and 0.52 for internal enhancement (moderate). Segmental and Regional distribution were the most prominent for the malignant group, and focal distribution for the benign group. Eight radiomics features were selected by support vector machine (SVM). Among the five machine learning algorithms, SVM yielded the highest accuracy of 80.4% in training and 77.5% in testing datasets. ResNet50 had a better diagnostic performance, 91.5% in training and 83.3% in testing datasets.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Diagnosis of NME was challenging, and the BI-RADS scores and descriptors showed a substantial overlap. Radiomics and deep learning may provide a useful CAD tool to aid in diagnosis.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fonc.2021.728224","type":"journal-article","created":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T06:33:08Z","timestamp":1635748388000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["BI-RADS Reading of Non-Mass Lesions on DCE-MRI and Differential Diagnosis Performed by Radiomics and Deep Learning"],"prefix":"10.3389","volume":"11","author":[{"given":"Jiejie","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan-Lin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeon-Hor","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Freddie J.","family":"Combs","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ritesh","family":"Parajuli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rita S.","family":"Mehta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiru","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongwei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youfan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhifang","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meihao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Risheng","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min-Ying","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2021,11,1]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-015-3807-z","article-title":"Breast MRI: EUSOBI Recommendations for Women\u2019s Information","volume":"25","author":"Mann","year":"2015","journal-title":"Eur Radiol"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.mri.2017.10.012","article-title":"Is Breast MRI a Helpful Additional Diagnostic Test in Suspicious Mammographic Microcalcifications","volume":"46","author":"Baltzer","year":"2018","journal-title":"Magn Reson Imaging"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2019182947","article-title":"Breast MRI: State of the Art","volume":"3","author":"Mann","year":"2019","journal-title":"Radiology"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20160715","article-title":"The Potential of Multiparametric MRI of the Breast","volume":"90","author":"Pinker","year":"2019","journal-title":"Br J Radiol"},{"key":"B5","volume-title":"ACR BI-RADS\u00ae Atlas, Breast Imaging Reporting and Data System. 5th Edn","author":"D\u2019Orsi","year":"2013"},{"key":"B6","doi-asserted-by":"publisher","first-page":"686","DOI":"10.1002\/jmri.27332","article-title":"AI-Enhanced Diagnosis of Challenging Lesions in Breast MRI: A Methodology and Application Primer","volume":"54","author":"Meyer-Base","year":"2021","journal-title":"J Magn Reson Imaging"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.11.8394","article-title":"Accuracy and Interpretation Time of Computer-Aided Detection Among Novice and Experienced Breast MRI Readers","volume":"200","author":"Lehman","year":"2020","journal-title":"AJR Am J Roentgenol."},{"key":"B8","doi-asserted-by":"publisher","first-page":"e30909","DOI":"10.5812\/iranjradiol.30909","article-title":"Significance of Additional Non-Mass Enhancement in Patients With Breast Cancer on Preoperative 3T Dynamic Contrast Enhanced MRI of the Breast","volume":"13","author":"Cho","year":"2016","journal-title":"Iran J Radiol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.17.18086","article-title":"Revisiting Nonmass Enhancement in Breast MRI: Analysis of Outcomes and Follow-Up Using the Updated BI-RADS Atlas","volume":"209","author":"Chikarmane","year":"2017","journal-title":"AJR Am J Roentgenol"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1007\/s11604-017-0717-9","article-title":"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","volume":"36","author":"Asada","year":"2018","journal-title":"Jpn J Radiol"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20180464","article-title":"The MRI Characteristics of Non-Mass Enhancement Lesions of the Breast: Associations With Malignancy","volume":"92","author":"Aydin","year":"2019","journal-title":"Br J Radiol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/s00330-019-06312-7","article-title":"Interobserver Variability and Likelihood of Malignancy for Fifth Edition BI-RADS MRI Descriptors in Non-Mass Breast Lesions","volume":"30","author":"Lunkiewicz","year":"2020","journal-title":"Eur Radiol"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-009-1616-y","article-title":"Selection of Diagnostic Features on Breast MRI to Differentiate Between Malignant and Benign Lesions Using Computer-Aided Diagnosis: Differences in Lesions Presenting as Mass and Non-Mass-Like Enhancement","volume":"20","author":"Newell","year":"2010","journal-title":"Eur Radiol"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2015150241","article-title":"Improving the Accuracy of Computer-Aided Diagnosis for Breast MR Imaging by Differentiating Between Mass and Nonmass Lesions","volume":"278","author":"Gallego-Ortiz","year":"2016","journal-title":"Radiology"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1186\/s40644-019-0252-2","article-title":"Independent Validation of Machine Learning in Diagnosing Breast Cancer on Magnetic Resonance Imaging Within a Single Institution","volume":"19","author":"Ji","year":"2019","journal-title":"Cancer Imaging"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2018181352","article-title":"Radiomic Versus Convolutional Neural Networks Analysis for Classification of Contrast-Enhancing Lesions at Multiparametric Breast MRI","volume":"290","author":"Truhn","year":"2019","journal-title":"Radiology"},{"key":"B17","doi-asserted-by":"publisher","first-page":"798","DOI":"10.1002\/jmri.26981","article-title":"Diagnosis of Benign and Malignant Breast Lesions on DCE-MRI by Using Radiomics and Deep Learning With Consideration of Peritumor Tissue","volume":"51","author":"Zhou","year":"2020","journal-title":"J Magn Reson Imaging"},{"key":"B18","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1007\/978-1-4757-0450-1_3","volume-title":"Objective Function Clustering in Pattern Recognition With Fuzzy Objective Function Algorithms","author":"Bezdek","year":"1981"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1158\/0008-5472.CAN-17-0339","article-title":"Computational Radiomics System to Decode the Radiographic Phenotype","volume":"77","author":"van Griethuysen","year":"2017","journal-title":"Cancer Res"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1063\/1.106515","article-title":"An Introduction to Variable and Feature Selection","volume":"3","author":"Guyon","year":"2003","journal-title":"J Mach Learn Res"},{"key":"B21","doi-asserted-by":"publisher","first-page":"049901","DOI":"10.1117\/1.2819119","article-title":"Pattern Recognition and Machine Learning","volume":"16","author":"Nasrabadi","year":"2007","journal-title":"J Electron Imaging."},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1007\/s40846-016-0163-7","article-title":"Pattern Recognition Approaches for Breast Cancer DCE-MRI Classification: A Systematic Review","volume":"36","author":"Fusco","year":"2016","journal-title":"J Med Biol Eng"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1097\/RLI.0000000000000518","article-title":"Impact of Machine Learning With Multiparametric Magnetic Resonance Imaging of the Breast for Early Prediction of Response to Neoadjuvant Chemotherapy and Survival Outcomes in Breast Cancer Patients","volume":"54","author":"Tahmassebi","year":"2019","journal-title":"Invest Radiol"},{"key":"B24","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2015.123","article-title":"Delving Deep Into Rectifiers: Surpassing Human-Level Performance on Imagenet Classification","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"He","year":"2015"},{"key":"B25","volume-title":"Adam: A Method for Stochastic Optimization","author":"Kingma","year":"2014"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/j.anndiagpath.2020.151563","article-title":"MRI-Guided Core Needle Biopsy of the Breast: Radiology-Pathology Correlation and Impact on Clinical Management","volume":"48","author":"Lilly","year":"2020","journal-title":"Ann Diagn Pathol"},{"key":"B27","doi-asserted-by":"publisher","first-page":"10536","DOI":"10.1038\/s41598-020-67441-4","article-title":"A Deep Learning Methodology for Improved Breast Cancer Diagnosis Using Multiparametric MRI","volume":"10","author":"Hu","year":"2020","journal-title":"Sci Rep"},{"key":"B28","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/j.mri.2019.02.013","article-title":"Differentiation of Spinal Metastases Originated From Lung and Other Cancers Using Radiomics and Deep Learning Based on DCE-MRI","volume":"64","author":"Lang","year":"2019","journal-title":"Magn Reson Imaging."},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1158\/1078-0432.CCR-19-0374","article-title":"Deep Learning to Distinguish Benign From Malignant Renal Lesions Based on Routine MR Imaging","volume":"26","author":"Xi","year":"2020","journal-title":"Clin Cancer Res"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1093\/annonc\/mdx034","article-title":"Promises and Challenges for the Implementation of Computational Medical Imaging (Radiomics) in Oncology","volume":"28","author":"Limkin","year":"2017","journal-title":"Ann Oncol"},{"key":"B31","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1080\/23808993.2019.1585805","article-title":"Deep Learning and Radiomics in Precision Medicine","volume":"4","author":"Parekh","year":"2019","journal-title":"Expert Rev Precis Med Drug Dev"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.26878","article-title":"Artificial Intelligence in the Interpretation of Breast Cancer on MRI","volume":"51","author":"Sheth","year":"2020","journal-title":"J Magn Reson Imaging"},{"key":"B33","doi-asserted-by":"publisher","first-page":"998","DOI":"10.1002\/jmri.26852","article-title":"Machine Learning in Breast MRI","volume":"52","author":"Reig","year":"2020","journal-title":"J Magn Reson Imaging"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1515\/raon-2017-0016","article-title":"Breast Dynamic Contrast Enhanced MRI: Fibrocystic Changes Presenting as a Non-Mass Enhancement Mimicking Malignancy","volume":"51","author":"Milosevic","year":"2017","journal-title":"Radiol Oncol"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-020-07274-x","article-title":"Prediction of Breast Cancer Molecular Subtypes on DCE-MRI Using Convolutional Neural Network With Transfer Learning Between Two Centers","volume":"31","author":"Zhang","year":"2021","journal-title":"Eur Radiol"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2021.728224\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T06:33:15Z","timestamp":1635748395000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2021.728224\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,1]]},"references-count":35,"alternative-id":["10.3389\/fonc.2021.728224"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2021.728224","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,1]]},"article-number":"728224"}}