{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T01:35:48Z","timestamp":1792805748925,"version":"4.5.0"},"reference-count":52,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T00:00:00Z","timestamp":1768694400000},"content-version":"vor","delay-in-days":17,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["J Applied Clin Med Phys"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Deep learning has advanced breast tumor prediction research, but traditional single\u2010modality models limit feature diversity and accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To develop and validate a multimodal deep learning approach that combines mammography and ultrasound imaging for improved breast tumor classification and enhanced clinical decision\u2010making.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective study analyzed 663 female patients with breast lesions from 2018 to 2021, including 384 benign and 279 malignant cases. The two\u2010stage prediction model employed improved modality\u2010specific attention mechanisms: efficient channel attention (ECA\u2010Net) for ultrasound and convolutional block attention module (CBAM) for mammography. The fused features were input into a stacking ensemble module with logistic regression (LR), support vector machine (SVM), random forest (RF), and Extra\u2010Trees (ET) as base learners, and multilayer perceptron (MLP) neural network as meta\u2010learner. Data was divided into training (464), validation (133), and test (66) sets with a 7:2:1 ratio.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed multimodal prediction model\u2014mammography ultrasound (MPM\u2010MU) achieved superior performance with an area under the receiver operating characteristic (ROC) Curve (AUC) of 87.9\u00a0\u00b1\u00a00.21%, representing improvements of 13.4% and 15.6% over attention\u2010enhanced mammography (74.5%) and ultrasound (72.3%) models, respectively. Ablation studies confirmed the effectiveness of both multimodal feature fusion and attention mechanisms in enhancing diagnostic performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The multimodal prediction model\u2014mammography ultrasound (MPM\u2010MU) with modality\u2010specific attention mechanisms demonstrated superior performance in distinguishing between benign and malignant breast tumors compared to single\u2010modality approaches. This approach assists radiologists in improving breast lesion classification accuracy and enhancing clinical decision\u2010making, potentially reducing unnecessary biopsies and improving diagnostic consistency.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/acm2.70464","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T07:48:23Z","timestamp":1768808903000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Multimodal deep learning for breast tumor classification: Integrating mammography and ultrasound for enhanced diagnostic accuracy"],"prefix":"10.1002","volume":"27","author":[{"given":"Yu","family":"Yan","sequence":"first","affiliation":[{"name":"Department of Medical Equipment Jiangsu Province Hospital of Chinese Medicine Affiliated Hospital of Nanjing University of Chinese Medicine Nanjing Jiangsu China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichen","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Information Technology Nanjing University of Chinese Medicine Nanjing Jiangsu China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ge","family":"Fang","sequence":"additional","affiliation":[{"name":"Department of Medical Equipment Jiangsu Province Hospital of Chinese Medicine Affiliated Hospital of Nanjing University of Chinese Medicine Nanjing Jiangsu China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6983-9379","authenticated-orcid":false,"given":"Xu","family":"He","sequence":"additional","affiliation":[{"name":"Department of Medical Equipment Jiangsu Province Hospital of Chinese Medicine Affiliated Hospital of Nanjing University of Chinese Medicine Nanjing Jiangsu China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifei","family":"Qian","sequence":"additional","affiliation":[{"name":"Department of Medical Equipment Jiangsu Province Hospital of Chinese Medicine Affiliated Hospital of Nanjing University of Chinese Medicine Nanjing Jiangsu China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenwen","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Information Technology Nanjing University of Chinese Medicine Nanjing Jiangsu China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,1,18]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1177\/0284185118770917"},{"key":"e_1_2_11_3_1","doi-asserted-by":"crossref","unstructured":"CalistoFM NunesN NascimentoJC. BreastScreening: on the use of multi\u2010modality in medical imaging diagnosis.2020:1\u20105.","DOI":"10.1145\/3399715.3399744"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21834"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21763"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591\u2010025\u201003502\u20103"},{"key":"e_1_2_11_7_1","unstructured":"WildCP WeiderpassE StewartBW. World cancer report.2020."},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106073"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.3390\/app112210753"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.5306\/wjco.v5.i3.465"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1038\/bjc.2013.177"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-13969-8_8"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12885\u2010020\u201006992\u20101"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2021.109878"},{"key":"e_1_2_11_15_1","first-page":"584","volume-title":"Application of Deep Learning in Breast Cancer Imaging","author":"Balkenende L","year":"2022"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/aa82ec"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13361"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67434-6_14"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20170576"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultrasmedbio.2022.07.006"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3236693"},{"key":"e_1_2_11_22_1","first-page":"112","article-title":"Data augmentation based on conditional generative adversarial networks for lesion classification in ultrasound images","volume":"17","author":"Cai L","year":"2024","journal-title":"J Biotech Res"},{"key":"e_1_2_11_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/JCSSE53117.2021.9493840"},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.104919"},{"key":"e_1_2_11_25_1","doi-asserted-by":"publisher","DOI":"10.4103\/jcrt.jcrt_1796_23"},{"key":"e_1_2_11_26_1","doi-asserted-by":"publisher","DOI":"10.3390\/app11041965"},{"key":"e_1_2_11_27_1","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/2964829"},{"key":"e_1_2_11_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107660"},{"issue":"1","key":"e_1_2_11_29_1","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava N","year":"2014","journal-title":"J Mach Learn Res"},{"key":"e_1_2_11_30_1","doi-asserted-by":"crossref","unstructured":"ShangW ChiuJ SohnK.Exploring normalization in deep residual networks with concatenated rectified linear units. In:Exploring Normalization in Deep Residual Networks with Concatenated Rectified Linear Units;2017: doi:10.1609\/aaai.v31i1.10759","DOI":"10.1609\/aaai.v31i1.10759"},{"key":"e_1_2_11_31_1","doi-asserted-by":"crossref","unstructured":"HuJ ShenL SunG. Squeeze\u2010and\u2010excitation networks.2018:7132\u20107141.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1002\/ima.22628"},{"key":"e_1_2_11_33_1","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2025.1589356"},{"issue":"3","key":"e_1_2_11_34_1","first-page":"206","article-title":"Breast cancer detection and classification with digital breast tomosynthesis: a two\u2010stage deep learning approach","volume":"31","author":"Alashban Y","year":"2025","journal-title":"Diagn Interv Radiol"},{"key":"e_1_2_11_35_1","doi-asserted-by":"publisher","DOI":"10.3390\/tomography8050200"},{"key":"e_1_2_11_36_1","doi-asserted-by":"crossref","unstructured":"WangQ WuB ZhuP LiP ZuoW HuQ.ECA\u2010Net: efficient channel attention for deep convolutional neural networks. In:2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Seattle WA USA;2020:11534\u201011542. doi:10.1109\/CVPR42600.2020.01155","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"e_1_2_11_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"e_1_2_11_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00477\u2010024\u201002760\u2010w"},{"key":"e_1_2_11_39_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1004369"},{"key":"e_1_2_11_40_1","doi-asserted-by":"publisher","DOI":"10.3390\/cancers15072112"},{"issue":"1","key":"e_1_2_11_41_1","first-page":"1","article-title":"Screening mammography for women aged 40 to 49 years at average risk for breast cancer: an evidence\u2010based analysis","volume":"7","author":"Secretariat MA","year":"2007","journal-title":"Ont Health Techn Assess Ser"},{"key":"e_1_2_11_42_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13058\u2010019\u20101203\u20103"},{"key":"e_1_2_11_43_1","doi-asserted-by":"publisher","DOI":"10.1186\/s43055\u2010020\u201000175\u20105"},{"key":"e_1_2_11_44_1","doi-asserted-by":"publisher","DOI":"10.1148\/rg.344130066"},{"key":"e_1_2_11_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330\u2010022\u201008617\u20106"},{"key":"e_1_2_11_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacr.2023.04.002"},{"key":"e_1_2_11_47_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.594"},{"key":"e_1_2_11_48_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:MACH.0000015881.36452.6e"},{"key":"e_1_2_11_49_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41523\u2010023\u201000517\u20102"},{"key":"e_1_2_11_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3102622"},{"key":"e_1_2_11_51_1","doi-asserted-by":"publisher","DOI":"10.25046\/aj050220"},{"key":"e_1_2_11_52_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13058\u2010025\u201002033\u20106"},{"key":"e_1_2_11_53_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103730"}],"container-title":["Journal of Applied Clinical Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acm2.70464","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/acm2.70464","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acm2.70464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T13:09:14Z","timestamp":1771333754000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/acm2.70464"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":52,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1002\/acm2.70464"],"URL":"https:\/\/doi.org\/10.1002\/acm2.70464","archive":["Portico"],"relation":{},"ISSN":["1526-9914","1526-9914"],"issn-type":[{"value":"1526-9914","type":"print"},{"value":"1526-9914","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-09-26","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-18","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70464"}}