{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T18:07:29Z","timestamp":1784830049530,"version":"3.55.0"},"reference-count":33,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:00:00Z","timestamp":1784764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: The paper aimed to synthesize the diagnostic performance of artificial intelligence (AI) methods for classifying breast lesions on contrast-enhanced breast MRI and to estimate a pooled area under the receiver operating characteristic curve (AUC). Methods: This targeted evidence synthesis and meta-analysis was informed by PRISMA 2020 reporting principles where applicable. Eligible studies were drawn from an investigator-supplied corpus of 12 primary manuscripts and assessed against predefined criteria. MEDLINE\/PubMed, Embase, and Web of Science were consulted through October 2025 to contextualize the literature and verify bibliographic and study details; additional database records were not screened for eligibility. We included studies applying machine learning or deep learning to contrast-enhanced breast MRI for benign-versus-malignant lesion classification and reporting an AUC on an independent test set, external validation set, or patient-wise cross-validation. AUCs were pooled on the logit scale using an inverse-variance DerSimonian\u2013Laird random-effects model, and heterogeneity was quantified using I2. Results: Nine studies met the criteria for quantitative synthesis (evaluation-set sizes, 60\u20133936). The pooled random-effects AUC was 0.898 (95% CI, 0.875\u20130.918), with substantial heterogeneity (I2 = 88.1%) and a 95% prediction interval of 0.824\u20130.943, indicating that performance may vary meaningfully across settings. Conclusions: AI models showed promising discriminative performance within this targeted corpus, but substantial heterogeneity, differences in unit of analysis, approximated variance estimates, and limited external institutional validation temper confidence in generalizability. The pooled AUC should be interpreted descriptively, and future studies should prioritize rigorous multi-institutional external validation, transparent reporting, and prospective reader- or workflow-impact evaluation before routine clinical deployment.<\/jats:p>","DOI":"10.3390\/diagnostics16152316","type":"journal-article","created":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T17:13:17Z","timestamp":1784826797000},"page":"2316","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Artificial Intelligence for Breast MRI Lesion Classification: A Targeted Evidence Synthesis and Meta-Analysis of Discriminative Performance and Heterogeneity"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7134-6138","authenticated-orcid":false,"given":"Romuald","family":"Ferre","sequence":"first","affiliation":[{"name":"Division of Breast Imaging, Department of Radiology, UNC School of Medicine, Chapel Hill, NC 27599, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thad","family":"Benefield","sequence":"additional","affiliation":[{"name":"Carolina Mammography Registry, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5509-2948","authenticated-orcid":false,"given":"Cherie M.","family":"Kuzmiak","sequence":"additional","affiliation":[{"name":"Division of Breast Imaging, Department of Radiology, UNC School of Medicine, Chapel Hill, NC 27599, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"520","DOI":"10.1148\/radiol.2019182947","article-title":"Breast MRI: State of the Art","volume":"292","author":"Mann","year":"2019","journal-title":"Radiology"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2091","DOI":"10.1056\/NEJMoa1903986","article-title":"Supplemental MRI Screening for Women with Extremely Dense Breast Tissue","volume":"381","author":"Bakker","year":"2019","journal-title":"N. Engl. J. Med."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2304","DOI":"10.1200\/JCO.2013.52.5386","article-title":"Abbreviated breast magnetic resonance imaging (MRI): First postcontrast subtracted images and maximum-intensity projection-a novel approach to breast cancer screening with MRI","volume":"32","author":"Kuhl","year":"2014","journal-title":"J. Clin. Oncol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"746","DOI":"10.1001\/jama.2020.0572","article-title":"Comparison of Abbreviated Breast MRI vs Digital Breast Tomosynthesis for Breast Cancer Detection Among Women with Dense Breasts Undergoing Screening","volume":"323","author":"Comstock","year":"2020","journal-title":"JAMA"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1310","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":"ref_6","doi-asserted-by":"crossref","first-page":"584","DOI":"10.1053\/j.semnuclmed.2022.02.003","article-title":"Application of Deep Learning in Breast Cancer Imaging","volume":"52","author":"Balkenende","year":"2022","journal-title":"Semin. Nucl. Med."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"450","DOI":"10.1002\/jmri.29101","article-title":"A Survey of Publicly Available MRI Datasets for Potential Use in Artificial Intelligence Research","volume":"59","author":"Dishner","year":"2024","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1148\/radiol.2021203960","article-title":"Deep Learning for Automated Triaging of 4581 Breast MRI Examinations from the DENSE Trial","volume":"302","author":"Verburg","year":"2022","journal-title":"Radiology"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"8706","DOI":"10.1007\/s00330-022-08863-8","article-title":"Using deep learning to safely exclude lesions with only ultrafast breast MRI to shorten acquisition and reading time","volume":"32","author":"Jing","year":"2022","journal-title":"Eur. Radiol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"710","DOI":"10.1097\/RLI.0000000000000976","article-title":"Automated Triage of Screening Breast MRI Examinations in High-Risk Women Using an Ensemble Deep Learning Model","volume":"58","author":"Bhowmik","year":"2023","journal-title":"Investig. Radiol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2290","DOI":"10.1002\/jmri.29358","article-title":"AI Applications to Breast MRI: Today and Tomorrow","volume":"60","author":"Brunekreef","year":"2024","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"n71","DOI":"10.1136\/bmj.n71","article-title":"The PRISMA 2020 statement: An updated guideline for reporting systematic reviews","volume":"372","author":"Page","year":"2021","journal-title":"BMJ"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"h5527","DOI":"10.1136\/bmj.h5527","article-title":"STARD 2015: An updated list of essential items for reporting diagnostic accuracy studies","volume":"351","author":"Bossuyt","year":"2015","journal-title":"BMJ"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"e200029","DOI":"10.1148\/ryai.2020200029","article-title":"Checklist for Artificial Intelligence in Medical Imaging (CLAIM): A Guide for Authors and Reviewers","volume":"2","author":"Mongan","year":"2020","journal-title":"Radiol. Artif. Intell."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"51","DOI":"10.7326\/M18-1376","article-title":"PROBAST: A Tool to Assess the Risk of Bias and Applicability of Prediction Model Studies","volume":"170","author":"Wolff","year":"2019","journal-title":"Ann. Intern Med."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/0197-2456(86)90046-2","article-title":"Meta-analysis in clinical trials","volume":"7","author":"DerSimonian","year":"1986","journal-title":"Control Clin. Trials"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1539","DOI":"10.1002\/sim.1186","article-title":"Quantifying heterogeneity in a meta-analysis","volume":"21","author":"Higgins","year":"2002","journal-title":"Stat. Med."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"d549","DOI":"10.1136\/bmj.d549","article-title":"Interpretation of random effects meta-analyses","volume":"342","author":"Riley","year":"2011","journal-title":"BMJ"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"IntHout, J., Ioannidis, J.P.A., and Borm, G.F. (2014). The Hartung-Knapp-Sidik-Jonkman method for random effects meta-analysis is straightforward and considerably outperforms the standard DerSimonian-Laird method. BMC Med. Res. Methodol., 14.","DOI":"10.1186\/1471-2288-14-25"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"3786","DOI":"10.1007\/s00330-020-07684-x","article-title":"To buy or not to buy-evaluating commercial AI solutions in radiology (the ECLAIR guidelines)","volume":"31","author":"Omoumi","year":"2021","journal-title":"Eur. Radiol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"745","DOI":"10.1007\/s13244-018-0645-y","article-title":"Artificial intelligence as a medical device in radiology: Ethical and regulatory issues in Europe and the United States","volume":"9","author":"Pesapane","year":"2018","journal-title":"Insights Imaging"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"014503","DOI":"10.1117\/1.JMI.5.1.014503","article-title":"Use of clinical MRI maximum intensity projections for improved breast lesion classification with deep convolutional neural networks","volume":"5","author":"Antropova","year":"2018","journal-title":"J. Med. Imaging"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1097\/RLI.0000000000000544","article-title":"Artificial Intelligence-Based Classification of Breast Lesions Imaged with a Multiparametric Breast MRI Protocol with Ultrafast DCE-MRI, T2, and DWI","volume":"54","author":"Vreemann","year":"2019","journal-title":"Investig. Radiol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"290","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":"ref_25","doi-asserted-by":"crossref","unstructured":"Adachi, M., Fujioka, T., Mori, M., Kubota, K., Kikuchi, Y., Xiaotong, W., Oyama, J., Kimura, K., Oda, G., and Nakagawa, T. (2020). Detection and Diagnosis of Breast Cancer Using Artificial Intelligence Based assessment of Maximum Intensity Projection Dynamic Contrast-Enhanced Magnetic Resonance Images. Diagnostics, 10.","DOI":"10.3390\/diagnostics10050330"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.mri.2020.10.003","article-title":"Deep-learning approach with convolutional neural network for classification of maximum intensity projections of dynamic contrast-enhanced breast magnetic resonance imaging","volume":"75","author":"Fujioka","year":"2021","journal-title":"Magn. Reson. Imaging"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"e200159","DOI":"10.1148\/ryai.2021200159","article-title":"Improved Classification of Benign and Malignant Breast Lesions Using Deep Feature Maximum Intensity Projection MRI in Breast Cancer Diagnosis Using Dynamic Contrast-enhanced MRI","volume":"3","author":"Hu","year":"2021","journal-title":"Radiol. Artif. Intell."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"4857","DOI":"10.1007\/s00330-022-08553-5","article-title":"An artificial intelligence system using maximum intensity projection MR images facilitates classification of non-mass enhancement breast lesions","volume":"32","author":"Wang","year":"2022","journal-title":"Eur. Radiol."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Zhu, J., Geng, J., Shan, W., Zhang, B., Shen, H., Dong, X., Liu, M., Li, X., and Cheng, L. (2022). Development and validation of a deep learning model for breast lesion segmentation and characterization in multiparametric MRI. Front. Oncol., 12.","DOI":"10.3389\/fonc.2022.946580"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"eabo4802","DOI":"10.1126\/scitranslmed.abo4802","article-title":"Improving breast cancer diagnostics with deep learning for MRI","volume":"14","author":"Witowski","year":"2022","journal-title":"Sci. Transl. Med."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.diii.2019.02.008","article-title":"Detection and characterization of MRI breast lesions using deep learning","volume":"100","author":"Herent","year":"2019","journal-title":"Diagn. Interv. Imaging"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1144","DOI":"10.1002\/jmri.26721","article-title":"Weakly supervised 3D deep learning for breast cancer classification and localization of the lesions in MR images","volume":"50","author":"Zhou","year":"2019","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1002\/jmri.28713","article-title":"MRI-Based Breast Cancer Classification and Localization by Multiparametric Feature Extraction and Combination Using Deep Learning","volume":"59","author":"Cong","year":"2024","journal-title":"J. Magn. Reson. Imaging"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/15\/2316\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T17:24:52Z","timestamp":1784827492000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/15\/2316"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,23]]},"references-count":33,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["diagnostics16152316"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16152316","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,23]]}}}