{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T04:18:49Z","timestamp":1787545129994,"version":"build-2736575974"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T00:00:00Z","timestamp":1786492800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"vor","delay-in-days":12,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"the University Key Program of Natural Science"},{"name":"the Anhui Provincial Medical Imaging Discipline (Professional) Leader Cultivation Project from the Anhui Provincial Department of Education"},{"name":"the Special Project of Key Support and Cultivation Discipline Area (Quantum Medicine Project) of Bengbu Medical University"},{"name":"the Key Project of Natural Science Research for Universities in Anhui Province"},{"name":"the Scientific Research Project of Anhui Provincial Health Commission"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Imaging"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>This study aimed to develop artificial intelligence (AI) models based on mammography (MG) and digital breast tomosynthesis (DBT) for non-invasive preoperative differentiation of benign and malignant breast microcalcifications.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We retrospectively analyzed 190 patients with pathologically confirmed breast microcalcifications, who were divided into training and test sets at a ratio of 7:3. Radiomics features and deep learning scores extracted using ResNet-50 were derived from MG and DBT images. After feature selection procedures, single-modality models and an integrated model (MD model) were constructed.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The area under the curves (AUCs) of the BI-RADS model, DBT model, MG model, and MD model in the training set were 0.805, 0.879, 0.896, and 0.939. In the test set, the corresponding AUCs were 0.809, 0.768, 0.793, and 0.835, respectively. The MD model demonstrated significantly better diagnostic performance compared with the other models (DeLong test,\n                      <jats:italic>P<\/jats:italic>\n                      \u2009&lt;\u20090.05). SHapley Additive exPlanations (SHAP) analysis revealed that the deep learning scores (DL scores) from the MG craniocaudal (CC) view and radiomics features reflecting textural complexity and spatial heterogeneity were the most influential features in model prediction.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The MD model integrating radiomics and deep learning scores from MG and DBT improved the diagnostic accuracy for differentiating benign and malignant breast microcalcifications, outperforming traditional methods. It provided a valuable non-invasive preoperative tool with the potential to optimize clinical decision-making and reduce unnecessary invasive procedures.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12880-026-02673-w","type":"journal-article","created":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T04:13:37Z","timestamp":1786508017000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AI-based multimodal fusion for preoperative prediction of breast microcalcifications: combining mammography and tomosynthesis"],"prefix":"10.1186","volume":"26","author":[{"given":"Junting","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruixin","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingna","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengcheng","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongyu","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichuan","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhizhen","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,12]]},"reference":[{"issue":"3","key":"2673_CR1","first-page":"229","volume":"74","author":"F Bray","year":"2024","unstructured":"Bray F, Laversanne M, Sung H, Ferlay J, Siegel RL, Soerjomataram I, Jemal A. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2024;74(3):229\u201363.","journal-title":"CA Cancer J Clin"},{"issue":"3","key":"2673_CR2","doi-asserted-by":"publisher","first-page":"1960","DOI":"10.1002\/mp.17571","volume":"52","author":"MA Lago","year":"2025","unstructured":"Lago MA, Badano A. Longitudinal in silico imaging study comparing digital mammography and digital breast tomosynthesis systems. Med Phys. 2025;52(3):1960\u20138.","journal-title":"Med Phys"},{"issue":"2","key":"2673_CR3","doi-asserted-by":"publisher","first-page":"880","DOI":"10.1016\/j.fmre.2023.04.018","volume":"5","author":"Q Lin","year":"2023","unstructured":"Lin Q, Tan WM, Ge JY, Huang Y, Xiao Q, Xu YY, Jin YT, Shao ZM, Gu YJ, Yan B, et al. Artificial intelligence-based diagnosis of breast cancer by mammography microcalcification. Fundam Res. 2023;5(2):880\u20139.","journal-title":"Fundam Res"},{"issue":"8","key":"2673_CR4","doi-asserted-by":"publisher","first-page":"1709","DOI":"10.1016\/j.ultrasmedbio.2023.03.011","volume":"49","author":"Z Kou","year":"2023","unstructured":"Kou Z, Park TH, Miller RJ, Oelze ML. Detection of microcalcifications using nonlinear beamforming techniques. Ultrasound Med Biol. 2023;49(8):1709\u201318.","journal-title":"Ultrasound Med Biol"},{"key":"2673_CR5","doi-asserted-by":"publisher","first-page":"2023","DOI":"10.2147\/OTT.S187835","volume":"12","author":"L Zhang","year":"2019","unstructured":"Zhang L, Hao C, Wu Y, Zhu Y, Ren Y, Tong Z. Microcalcification and BMP-2 in breast cancer: correlation with clinicopathological features and outcomes. Onco Targets Ther. 2019;12:2023\u201333.","journal-title":"Onco Targets Ther"},{"issue":"4","key":"2673_CR6","first-page":"511","volume":"11","author":"L Nicosia","year":"2023","unstructured":"Nicosia L, Bozzini AC, Signorelli G, Palma S, Pesapane F, Frassoni S, Bagnardi V, Pizzamiglio M, Farina M, Trentin C, et al. Contrast-Enhanced Spectral Mammography in the Evaluation of Breast Microcalcifications: Controversies and Diagnostic Management. Healthc (Basel). 2023;11(4):511.","journal-title":"Healthc (Basel)"},{"issue":"13","key":"2673_CR7","doi-asserted-by":"publisher","first-page":"5865","DOI":"10.7150\/thno.43325","volume":"10","author":"KS Shin","year":"2020","unstructured":"Shin KS, Laohajaratsang M, Men S, Figueroa B, Dintzis SM, Fu D. Quantitative chemical imaging of breast calcifications in association with neoplastic processes. Theranostics. 2020;10(13):5865\u201378.","journal-title":"Theranostics"},{"key":"2673_CR8","doi-asserted-by":"publisher","first-page":"110795","DOI":"10.1016\/j.ejrad.2023.110795","volume":"162","author":"D Kim","year":"2023","unstructured":"Kim D, Kim J, Jung HK, Kim S. Assessment of malignant risk stratification for microcalcifications interpreted as amorphous morphology on mammography: A study based on the 5th edition of breast Imaging Reporting and Data System. Eur J Radiol. 2023;162:110795.","journal-title":"Eur J Radiol"},{"issue":"2","key":"2673_CR9","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1016\/j.acra.2023.09.033","volume":"31","author":"Y Chen","year":"2024","unstructured":"Chen Y, Jiang H, Li J, Zhang J, Wu P, Dai Z. A Mammography-Based Radiomic Nomogram for Predicting Malignancy in Breast Suspicious Microcalcifications. Acad Radiol. 2024;31(2):492\u2013502.","journal-title":"Acad Radiol"},{"issue":"4","key":"2673_CR10","doi-asserted-by":"publisher","first-page":"2134","DOI":"10.1007\/s10278-024-01347-9","volume":"38","author":"N Wang","year":"2025","unstructured":"Wang N, Xu W, Wang H, Wu S, Wang J, Ao W, Zhang C, Zhu Y, Xie Z, Mao G. Machine Learning Based on Digital Mammography to Reduce the Need for Invasive Biopsies of Benign Calcifications Classified in BI-RADS Category 4. J Imaging Inf Med. 2025;38(4):2134\u201345.","journal-title":"J Imaging Inf Med"},{"issue":"4","key":"2673_CR11","doi-asserted-by":"publisher","first-page":"1372","DOI":"10.3390\/jcm12041372","volume":"12","author":"F Pesapane","year":"2023","unstructured":"Pesapane F, De Marco P, Rapino A, Lombardo E, Nicosia L, Tantrige P, Rotili A, Bozzini AC, Penco S, Dominelli V, et al. How Radiomics Can Improve Breast Cancer Diagnosis and Treatment. J Clin Med. 2023;12(4):1372.","journal-title":"J Clin Med"},{"issue":"1","key":"2673_CR12","doi-asserted-by":"publisher","first-page":"e222830","DOI":"10.1148\/radiol.222830","volume":"308","author":"Z Shi","year":"2023","unstructured":"Shi Z, Huang X, Cheng Z, Xu Z, Lin H, Liu C, Chen X, Liu C, Liang C, Lu C, et al. MRI-based Quantification of Intratumoral Heterogeneity for Predicting Treatment Response to Neoadjuvant Chemotherapy in Breast Cancer. Radiology. 2023;308(1):e222830.","journal-title":"Radiology"},{"key":"2673_CR13","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1109\/RBME.2023.3269776","volume":"17","author":"Z Wang","year":"2024","unstructured":"Wang Z, Fang M, Zhang J, Tang L, Zhong L, Li H, Cao R, Zhao X, Liu S, Zhang R, et al. Radiomics and Deep Learning in Nasopharyngeal Carcinoma: A Review. IEEE Rev Biomed Eng. 2024;17:118\u201335.","journal-title":"IEEE Rev Biomed Eng"},{"issue":"8","key":"2673_CR14","doi-asserted-by":"publisher","first-page":"4474","DOI":"10.1007\/s00330-025-11406-6","volume":"35","author":"KA Abdullah","year":"2025","unstructured":"Abdullah KA, Marziali S, Nanaa M, Escudero S\u00e1nchez L, Payne NR, Gilbert FJ. Deep learning-based breast cancer diagnosis in breast MRI: systematic review and meta-analysis. Eur Radiol. 2025;35(8):4474\u201389.","journal-title":"Eur Radiol"},{"issue":"1","key":"2673_CR15","doi-asserted-by":"publisher","first-page":"30248","DOI":"10.1038\/s41598-025-16331-8","volume":"15","author":"Y Xu","year":"2025","unstructured":"Xu Y, Li B, Zou B, Fan B, Wang S, Yu J, Dong T, Wang L. Deep learning for survival prediction in triple-negative breast cancer: development and validation in real-world cohorts. Sci Rep. 2025;15(1):30248.","journal-title":"Sci Rep"},{"issue":"3","key":"2673_CR16","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1002\/cncr.34540","volume":"129","author":"J Gu","year":"2023","unstructured":"Gu J, Tong T, Xu D, Cheng F, Fang C, He C, Wang J, Wang B, Yang X, Wang K, et al. Deep learning radiomics of ultrasonography for comprehensively predicting tumor and axillary lymph node status after neoadjuvant chemotherapy in breast cancer patients: A multicenter study. Cancer. 2023;129(3):356\u201366.","journal-title":"Cancer"},{"issue":"9","key":"2673_CR17","doi-asserted-by":"publisher","first-page":"6132","DOI":"10.1007\/s00330-024-10641-7","volume":"34","author":"S Zheng","year":"2024","unstructured":"Zheng S, Yang Z, Du G, Zhang Y, Jiang C, Xu T, Li B, Wang D, Qiu Y, Lin D, et al. Discrimination between HER2-overexpressing, -low-expressing, and -zero-expressing statuses in breast cancer using multiparametric MRI-based radiomics. Eur Radiol. 2024;34(9):6132\u201344.","journal-title":"Eur Radiol"},{"key":"2673_CR18","volume-title":"ACR BI-RADS Atlas: Breast Imaging Reporting and Data System","author":"C D\u2019Orsi","year":"2013","unstructured":"D\u2019Orsi C, Sickles E, Mendelson E. ACR BI-RADS Atlas: Breast Imaging Reporting and Data System. 5th ed. Reston: American College of Radiology; 2013.","edition":"5"},{"key":"2673_CR19","doi-asserted-by":"publisher","first-page":"725922","DOI":"10.3389\/fonc.2021.725922","volume":"11","author":"S Niu","year":"2021","unstructured":"Niu S, Wang X, Zhao N, Liu G, Kan Y, Dong Y, Cui EN, Luo Y, Yu T, Jiang X. Radiomic Evaluations of the Diagnostic Performance of DM, DBT, DCE MRI, DWI, and Their Combination for the Diagnosis of Breast Cancer. Front Oncol. 2021;11:725922.","journal-title":"Front Oncol"},{"issue":"11","key":"2673_CR20","doi-asserted-by":"publisher","first-page":"3899","DOI":"10.1007\/s00330-016-4265-y","volume":"26","author":"K L\u00e5ng","year":"2016","unstructured":"L\u00e5ng K, Nerg\u00e5rden M, Andersson I, Rosso A, Zackrisson S. False positives in breast cancer screening with one-view breast tomosynthesis: An analysis of findings leading to recall, work-up and biopsy rates in the Malm\u00f6 Breast Tomosynthesis Screening Trial. Eur Radiol. 2016;26(11):3899\u2013907.","journal-title":"Eur Radiol"},{"issue":"12","key":"2673_CR21","doi-asserted-by":"publisher","first-page":"2161","DOI":"10.1016\/j.ejrad.2016.10.004","volume":"85","author":"P Clauser","year":"2016","unstructured":"Clauser P, Nagl G, Helbich TH, Pinker-Domenig K, Weber M, Kapetas P, Bernathova M, Baltzer PAT. Diagnostic performance of digital breast tomosynthesis with a wide scan angle compared to full-field digital mammography for the detection and characterization of microcalcifications. Eur J Radiol. 2016;85(12):2161\u20138.","journal-title":"Eur J Radiol"},{"issue":"8","key":"2673_CR22","doi-asserted-by":"publisher","first-page":"3435","DOI":"10.1002\/mp.14216","volume":"47","author":"Y Peng","year":"2020","unstructured":"Peng Y, Wu S, Yuan G, Wu Z, Du Q, Sun H, Yang X, Chen Q, Zheng J. A radiomics method to classify microcalcification clusters in digital breast tomosynthesis. Med Phys. 2020;47(8):3435\u201346.","journal-title":"Med Phys"},{"key":"2673_CR23","doi-asserted-by":"publisher","first-page":"105504","DOI":"10.1016\/j.compbiomed.2022.105504","volume":"146","author":"K Marathe","year":"2022","unstructured":"Marathe K, Marasinou C, Li B, Nakhaei N, Li B, Elmore JG, Shapiro L, Hsu W. Automated quantitative assessment of amorphous calcifications: Towards improved malignancy risk stratification. Comput Biol Med. 2022;146:105504.","journal-title":"Comput Biol Med"},{"key":"2673_CR24","doi-asserted-by":"publisher","first-page":"1482020","DOI":"10.3389\/fimmu.2024.1482020","volume":"15","author":"F Guo","year":"2024","unstructured":"Guo F, Sun S, Deng X, Wang Y, Yao W, Yue P, Wu S, Yan J, Zhang X, Zhang Y. Predicting axillary lymph node metastasis in breast cancer using a multimodal radiomics and deep learning model. Front Immunol. 2024;15:1482020.","journal-title":"Front Immunol"},{"issue":"3","key":"2673_CR25","doi-asserted-by":"publisher","first-page":"1652","DOI":"10.1007\/s00330-021-08271-4","volume":"32","author":"M Ma","year":"2022","unstructured":"Ma M, Liu R, Wen C, Xu W, Xu Z, Wang S, Wu J, Pan D, Zheng B, Qin G, et al. Predicting the molecular subtype of breast cancer and identifying interpretable imaging features using machine learning algorithms. Eur Radiol. 2022;32(3):1652\u201362.","journal-title":"Eur Radiol"},{"issue":"1","key":"2673_CR26","doi-asserted-by":"publisher","first-page":"2541316","DOI":"10.1080\/07853890.2025.2541316","volume":"57","author":"Q Yuan","year":"2025","unstructured":"Yuan Q, Ye R, Qian Y, Yu H, Zhou Y, Cui X, Liu F, Niu M. Machine learning and SHAP value interpretation for predicting the response to neoadjuvant chemotherapy and long-term clinical outcomes in Chinese female breast cancer. Ann Med. 2025;57(1):2541316.","journal-title":"Ann Med"},{"issue":"02","key":"2673_CR27","doi-asserted-by":"publisher","first-page":"43","DOI":"10.4236\/ojrad.2025.152005","volume":"15","author":"NN Nana","year":"2025","unstructured":"Nana NN, Takmou P, Eyidi SSM. Evaluation of the Quality of Screening Mammograms at the Radiology Department of the Douala General Hospital: Analysis of 100 Cases Using the PGMI System. Open J Radiol. 2025;15(02):43\u201351.","journal-title":"Open J Radiol"},{"issue":"1","key":"2673_CR28","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1186\/s40644-019-0229-1","volume":"19","author":"H Wang","year":"2019","unstructured":"Wang H, Lai J, Li J, Gu R, Liu F, Hu Y, Mei J, Jiang X, Shen S, Yu F, et al. Does establishing a preoperative nomogram including ultrasonographic findings help predict the likelihood of malignancy in patients with microcalcifications? Cancer Imaging. 2019;19(1):46.","journal-title":"Cancer Imaging"},{"issue":"11","key":"2673_CR29","doi-asserted-by":"publisher","first-page":"6612","DOI":"10.1016\/j.acra.2025.07.062","volume":"32","author":"W Xu","year":"2025","unstructured":"Xu W, Deng S, Mao G, Wang N, Huang Y, Zhang C, Sa G, Wu S, An Y. Differentiation of Suspicious Microcalcifications Using Deep Learning: DCIS or IDC. Acad Radiol. 2025;32(11):6612\u201322.","journal-title":"Acad Radiol"},{"key":"2673_CR30","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.clinimag.2021.11.034","volume":"83","author":"LH Portnow","year":"2022","unstructured":"Portnow LH, Georgian-Smith D, Haider I, Barrios M, Bay CP, Nelson KP, Raza S. Persistent inter-observer variability of breast density assessment using BI-RADS\u00ae 5th edition guidelines. Clin Imaging. 2022;83:21\u20137.","journal-title":"Clin Imaging"},{"issue":"1","key":"2673_CR31","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1186\/s13244-025-01983-x","volume":"16","author":"H Tan","year":"2025","unstructured":"Tan H, Wu Q, Wu Y, Zheng B, Wang B, Chen Y, Du L, Zhou J, Fu F, Guo H, et al. Mammography-based artificial intelligence for breast cancer detection, diagnosis, and BI-RADS categorization using multi-view and multi-level convolutional neural networks. Insights Imaging. 2025;16(1):109.","journal-title":"Insights Imaging"},{"issue":"6","key":"2673_CR32","doi-asserted-by":"publisher","first-page":"967","DOI":"10.1007\/s12282-022-01375-9","volume":"29","author":"LA Dang","year":"2022","unstructured":"Dang LA, Chazard E, Poncelet E, Serb T, Rusu A, Pauwels X, Parsy C, Poclet T, Cauliez H, Engelaere C, et al. Impact of artificial intelligence in breast cancer screening with mammography. Breast Cancer. 2022;29(6):967\u201377.","journal-title":"Breast Cancer"}],"container-title":["BMC Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12880-026-02673-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-026-02673-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-026-02673-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T03:31:13Z","timestamp":1787542273000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12880-026-02673-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,12]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2673"],"URL":"https:\/\/doi.org\/10.1186\/s12880-026-02673-w","relation":{},"ISSN":["1471-2342"],"issn-type":[{"value":"1471-2342","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,12]]},"assertion":[{"value":"20 May 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 August 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The retrospective study was approved by the Institutional Review Board of The First Affiliated Hospital of Bengbu Medical University (Approval Number:2025\u2009\u2212\u2009524). All research procedures of this study were performed in accordance with the principles of the Declaration of Helsinki and its subsequent amendments. The requirement for informed consent was waived by the ethics committee due to the retrospective nature of the study and the use of the de-identified patient data.","order":1,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"417"}}