{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:04:21Z","timestamp":1782846261315,"version":"3.54.5"},"reference-count":48,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec sec-type=\"background\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Axillary lymph node metastasis (ALNM) is an important factor in detecting breast cancer (BC). However, the noninvasive diagnosis of ALNM remains challenging. While some deep learning (DL) models have been developed for preoperative ALNM assessment, their performance lacks systematic evaluation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"objective\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aims to evaluate the effectiveness of DL in detecting ALNM, providing evidence to support clinical diagnostic tools.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"methods\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Embase, Web of Science, PubMed, and Cochrane Library were searched from their inception through January 26, 2026. The Quality Assessment of Diagnostic Accuracy Studies was used to assess the risk of bias in the included studies. A bivariate mixed effects model was applied for analysis, and subgroup analyses were conducted based on different imaging modalities.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"results\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>This meta-analysis included 28 independent studies and pooled data from 20,811 patients with BC. Among them, 7123 cases had confirmed ALNM. The overall diagnostic performance of the DL model (bivariate mixed effects) for detecting ALNM in BC was as follows: sensitivity 0.80 (95% CI 0.76\u20100.84), specificity 0.85 (95% CI 0.80\u20100.88), diagnostic odds ratio (DOR) 22 (95% CI 16\u201030), and area under the summary receiver operating characteristic curve (AUC) 0.89 (95% CI 0.86\u20100.92). The positive likelihood ratio (LR+) was 5.2 (95% CI 4.1\u20106.5), and the negative likelihood ratio (LR\u2212) was 0.24 (95% CI 0.19\u20100.29). For ultrasound-based DL models targeting ALNM detection, the pooled sensitivity and specificity were 0.79 (95% CI 0.72\u20100.84) and 0.86 (95% CI 0.79\u20100.91), respectively. Diagnostic performance metrics showed an LR+ of 5.5 (95% CI 3.8\u20108.1), an LR\u2212 of 0.25 (95% CI 0.19\u20100.32), a DOR of 22 (95% CI 15\u201033), and an AUC of 0.89 (95% CI 0.86\u20100.91). Regarding magnetic resonance imaging\u2013based DL models for detecting ALNM, the pooled sensitivity was 0.78 (95% CI 0.71\u20100.83) and the pooled specificity was 0.82 (95% CI 0.76\u20100.87). Corresponding metrics included an LR+ of 4.4 (95% CI 3.3\u20105.9), an LR\u2212 of 0.27 (95% CI 0.21\u20100.35), a DOR of 16 (95% CI 11\u201025), and an AUC of 0.87 (95% CI 0.84\u20100.90). For computed tomography (CT)\u2013based models, the sensitivity was 0.90 (95% CI 0.78\u20100.96), the specificity was 0.88 (95% CI 0.84\u20100.92), and the AUC was as high as 0.91 (95% CI 0.89\u20100.94).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"conclusions\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Current DL methods for detecting ALNM in BC primarily utilize ultrasound, magnetic resonance imaging, and CT. DL models based on all 3 modalities demonstrated good diagnostic performance. CT had the highest sensitivity and AUC, while its specificity was comparable to that of ultrasound. These findings provide supportive evidence for the development or optimization of clinical diagnostic models.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/77593","type":"journal-article","created":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T16:19:51Z","timestamp":1776356391000},"page":"e77593-e77593","source":"Crossref","is-referenced-by-count":0,"title":["Accuracy of Deep Learning for Detecting Axillary Lymph Node Metastasis in Breast Cancer: Systematic Review and Meta-Analysis"],"prefix":"10.2196","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6438-7775","authenticated-orcid":false,"given":"Xueying","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1181-1781","authenticated-orcid":false,"given":"Tiantian","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2111-9601","authenticated-orcid":false,"given":"Xiaohang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6877-6864","authenticated-orcid":false,"given":"Deyuan","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,4,16]]},"reference":[{"issue":"4","key":"R1","doi-asserted-by":"publisher","first-page":"1154","DOI":"10.1038\/s41591-025-03502-3","article-title":"Global patterns and trends in breast cancer incidence and mortality across 185 countries","volume":"31","author":"Kim","journal-title":"Nat Med"},{"issue":"1","key":"R2","doi-asserted-by":"publisher","first-page":"12","DOI":"10.3322\/caac.21820","article-title":"Cancer statistics, 2024","volume":"74","author":"Siegel","journal-title":"CA Cancer J Clin"},{"issue":"3","key":"R3","doi-asserted-by":"publisher","first-page":"209","DOI":"10.3322\/caac.21660","article-title":"Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"71","author":"Sung","journal-title":"CA Cancer J Clin"},{"issue":"21","key":"R4","doi-asserted-by":"publisher","first-page":"1981","DOI":"10.1056\/NEJMoa2409932","article-title":"Overall survival with pembrolizumab in early-stage triple-negative breast cancer","volume":"391","author":"Schmid","journal-title":"N Engl J Med"},{"issue":"3","key":"R5","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1016\/S1470-2045(23)00018-9","article-title":"Accelerated partial breast irradiation using sole interstitial multicatheter brachytherapy compared with whole-breast irradiation with boost for early breast cancer: 10-year results of a GEC-ESTRO randomised, phase 3, non-inferiority trial","volume":"24","author":"Strnad","journal-title":"Lancet Oncol"},{"issue":"1","key":"R6","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/S1470-2045(24)00581-3","article-title":"De-escalated neoadjuvant weekly nab-paclitaxel with trastuzumab and pertuzumab versus docetaxel, carboplatin, trastuzumab, and pertuzumab in patients with HER2-positive early breast cancer (HELEN-006): a multicentre, randomised, phase 3 trial","volume":"26","author":"Chen","journal-title":"Lancet Oncol"},{"issue":"3","key":"R7","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1148\/radiol.2020192534","article-title":"Axillary nodal evaluation in breast cancer: state of the art","volume":"295","author":"Chang","journal-title":"Radiology"},{"issue":"1","key":"R8","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1038\/s41580-021-00407-0","article-title":"A guide to machine learning for biologists","volume":"23","author":"Greener","journal-title":"Nat Rev Mol Cell Biol"},{"issue":"12","key":"R9","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1038\/s41568-021-00399-1","article-title":"Artificial intelligence in cancer research, diagnosis and therapy","volume":"21","author":"Elemento","journal-title":"Nat Rev Cancer"},{"issue":"8","key":"R10","doi-asserted-by":"publisher","first-page":"1772","DOI":"10.1016\/j.cell.2023.01.035","article-title":"From patterns to patients: advances in clinical machine learning for cancer diagnosis, prognosis, and treatment","volume":"186","author":"Swanson","journal-title":"Cell"},{"issue":"26","key":"R11","doi-asserted-by":"publisher","first-page":"5365","DOI":"10.1002\/sim.9564","article-title":"DL 101: basic introduction to deep learning with its application in biomedical related fields","volume":"41","author":"Zhan","journal-title":"Stat Med"},{"issue":"1","key":"R12","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-40890-x","article-title":"Biology-guided deep learning predicts prognosis and cancer immunotherapy response","volume":"14","author":"Jiang","journal-title":"Nat Commun"},{"issue":"1","key":"R13","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-42811-4","article-title":"PET\/CT based cross-modal deep learning signature to predict occult nodal metastasis in lung cancer","volume":"14","author":"Zhong","journal-title":"Nat Commun"},{"issue":"4","key":"R14","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.3390\/curroncol31040169","article-title":"Deep learning prediction of axillary lymph node metastasis in breast cancer patients using clinical implication-applied preprocessed ct images","volume":"31","author":"Park","journal-title":"Curr Oncol"},{"issue":"4","key":"R15","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1007\/s10278-023-00818-9","article-title":"Deep learning radiomics of preoperative breast MRI for prediction of axillary lymph node metastasis in breast cancer","volume":"36","author":"Chen","journal-title":"J Digit Imaging"},{"key":"R16","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1219838","article-title":"Prediction of axillary lymph node metastasis in early breast cancer patients with ultrasonic videos based deep learning","volume":"13","author":"Li","journal-title":"Front Oncol"},{"issue":"8","key":"R17","doi-asserted-by":"publisher","first-page":"529","DOI":"10.7326\/0003-4819-155-8-201110180-00009","article-title":"QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies","volume":"155","author":"Whiting","journal-title":"Ann Intern Med"},{"key":"R18","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2024.102472","article-title":"Computer-assisted diagnosis for axillary lymph node metastasis of early breast cancer based on transformer with dual-modal adaptive mid-term fusion using ultrasound elastography","volume":"119","author":"Gong","journal-title":"Comput Med Imaging Graph"},{"issue":"1","key":"R19","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-13086-0","article-title":"Ultrasound derived deep learning features for predicting axillary lymph node metastasis in breast cancer using graph convolutional networks in a multicenter study","volume":"15","author":"Agyekum","journal-title":"Sci Rep"},{"issue":"1","key":"R20","doi-asserted-by":"publisher","DOI":"10.1038\/s41698-025-00971-0","article-title":"Applying a multi-task and multi-instance framework to predict axillary lymph node metastases in breast cancer","volume":"9","author":"Li","journal-title":"NPJ Precis Oncol"},{"issue":"11","key":"R21","doi-asserted-by":"publisher","first-page":"2288","DOI":"10.21037\/gs-2025-365","article-title":"Preoperative prediction of axillary lymph node metastasis in breast invasive ductal carcinoma patients using a deep learning model based on dynamic contrast-enhanced magnetic resonance imaging: a multicenter study","volume":"14","author":"Gu","journal-title":"Gland Surg"},{"issue":"1","key":"R22","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-025-01988-4","article-title":"Predicting axillary lymph node metastasis in breast cancer patients using CNN-GCN on DCE-MRI: a multicenter study","volume":"25","author":"Dai","journal-title":"BMC Med Imaging"},{"issue":"1","key":"R23","doi-asserted-by":"publisher","first-page":"91","DOI":"10.17305\/bb.2025.12010","article-title":"A deep learning model based on chest CT to predict benign and malignant breast masses and axillary lymph node metastasis","volume":"26","author":"Sun","journal-title":"Biomol Biomed"},{"issue":"1","key":"R24","doi-asserted-by":"publisher","DOI":"10.1186\/s12885-024-12619-6","article-title":"Artificial intelligence assisted ultrasound for the non-invasive prediction of axillary lymph node metastasis in breast cancer","volume":"24","author":"Wang","journal-title":"BMC Cancer"},{"issue":"3","key":"R25","doi-asserted-by":"publisher","DOI":"10.1148\/rycan.230107","article-title":"Machine learning prediction of lymph node metastasis in breast cancer: performance of a multi-institutional MRI-based 4D convolutional neural network","volume":"6","author":"Polat","journal-title":"Radiol Imaging Cancer"},{"issue":"5","key":"R26","doi-asserted-by":"publisher","first-page":"1710","DOI":"10.1002\/jmri.28913","article-title":"Multitask deep learning-based whole-process system for automatic diagnosis of breast lesions and axillary lymph node metastasis discrimination from dynamic contrast-enhanced-MRI: a multicenter study","volume":"59","author":"Zhou","journal-title":"J Magn Reson Imaging"},{"issue":"1","key":"R27","doi-asserted-by":"publisher","DOI":"10.1038\/s41523-024-00628-4","article-title":"Deep learning radiomics based prediction of axillary lymph node metastasis in breast cancer","volume":"10","author":"Liu","journal-title":"NPJ Breast Cancer"},{"issue":"4","key":"R28","doi-asserted-by":"publisher","first-page":"1352","DOI":"10.1002\/jmri.29225","article-title":"MRI-based kinetic heterogeneity evaluation in the accurate access of axillary lymph node status in breast cancer using a hybrid CNN-RNN model","volume":"60","author":"Guo","journal-title":"J Magn Reson Imaging"},{"issue":"8","key":"R29","doi-asserted-by":"publisher","first-page":"4995","DOI":"10.21037\/qims-22-1257","article-title":"Deep learning radiomics for prediction of axillary lymph node metastasis in patients with clinical stage T1-2 breast cancer","volume":"13","author":"Wei","journal-title":"Quant Imaging Med Surg"},{"issue":"6","key":"R30","doi-asserted-by":"publisher","first-page":"1842","DOI":"10.1002\/jmri.28464","article-title":"Attention-based deep learning for the preoperative differentiation of axillary lymph node metastasis in breast cancer on DCE-MRI","volume":"57","author":"Gao","journal-title":"J Magn Reson Imaging"},{"key":"R31","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.1069733","article-title":"Predicting of axillary lymph node metastasis in invasive breast cancer using multiparametric MRI dataset based on CNN model","volume":"12","author":"Zhang","journal-title":"Front Oncol"},{"key":"R32","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.944569","article-title":"A machine learning model based on ultrasound image features to assess the risk of sentinel lymph node metastasis in breast cancer patients:applications of scikit-learn and SHAP","volume":"12","author":"Zhang","journal-title":"Front Oncol"},{"issue":"3","key":"R33","doi-asserted-by":"publisher","first-page":"700","DOI":"10.1002\/jmri.28082","article-title":"Preoperative prediction of axillary lymph node metastasis in breast cancer using CNN based on multiparametric MRI","volume":"56","author":"Wang","journal-title":"J Magn Reson Imaging"},{"key":"R34","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105250","article-title":"Deep learning prediction of axillary lymph node status using ultrasound images","volume":"143","author":"Sun","journal-title":"Comput Biol Med"},{"issue":"19","key":"R35","doi-asserted-by":"publisher","DOI":"10.3390\/cancers14194574","article-title":"CNN-based approaches with different tumor bounding options for lymph node status prediction in breast DCE-MRI","volume":"14","author":"Santucci","journal-title":"Cancers (Basel)"},{"key":"R36","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2022.882648","article-title":"A convolutional neural network based on ultrasound images of primary breast masses: prediction of lymph-node metastasis in collaboration with classification of benign and malignant tumors","volume":"13","author":"Li","journal-title":"Front Physiol"},{"issue":"1","key":"R37","doi-asserted-by":"publisher","DOI":"10.1186\/s42492-022-00104-5","article-title":"Preoperative prediction of lymph node metastasis using deep learning-based features","volume":"5","author":"Cattell","journal-title":"Vis Comput Ind Biomed Art"},{"issue":"7","key":"R38","doi-asserted-by":"publisher","first-page":"3679","DOI":"10.1002\/mp.14876","article-title":"Decoupling convolution network for characterizing the metastatic lymph nodes of breast cancer patients","volume":"48","author":"Zeng","journal-title":"Med Phys"},{"key":"R39","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104715","article-title":"Axillary lymph node metastasis prediction by contrast-enhanced computed tomography images for breast cancer patients based on deep learning","volume":"136","author":"Liu","journal-title":"Comput Biol Med"},{"issue":"1","key":"R40","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1148\/radiol.2019190372","article-title":"Lymph node metastasis prediction from primary breast cancer US images using deep learning","volume":"294","author":"Zhou","journal-title":"Radiology"},{"issue":"1","key":"R41","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-15027-z","article-title":"Deep learning radiomics can predict axillary lymph node status in early-stage breast cancer","volume":"11","author":"Zheng","journal-title":"Nat Commun"},{"issue":"53","key":"R42","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2020.00053","article-title":"Deep learning vs. radiomics for predicting axillary lymph node metastasis of breast cancer using ultrasound images: don\u2019t forget the peritumoral region","volume":"10","author":"Sun","journal-title":"Front Oncol"},{"key":"R43","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2020.103018","article-title":"Deep learning radiomics of ultrasonography: identifying the risk of axillary non-sentinel lymph node involvement in primary breast cancer","volume":"60","author":"Guo","journal-title":"EBioMedicine"},{"key":"R44","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.799209","article-title":"The diagnostic performance of machine learning-based radiomics of DCE-MRI in predicting axillary lymph node metastasis in breast cancer: a meta-analysis","volume":"12","author":"Zhang","journal-title":"Front Oncol"},{"issue":"1","key":"R45","doi-asserted-by":"publisher","DOI":"10.1186\/s13244-021-01034-1","article-title":"A meta-analysis of the diagnostic performance of machine learning-based MRI in the prediction of axillary lymph node metastasis in breast cancer patients","volume":"12","author":"Chen","journal-title":"Insights Imaging"},{"issue":"6","key":"R46","doi-asserted-by":"publisher","first-page":"564","DOI":"10.2174\/1573405618666220822093226","article-title":"Radiomics and artificial intelligence in predicting axillary lymph node metastasis in breast cancer: a systematic review","volume":"19","author":"Eldaly","journal-title":"Curr Med Imaging"},{"issue":"1","key":"R47","doi-asserted-by":"publisher","DOI":"10.1186\/s12885-023-11638-z","article-title":"Application of CT and MRI images based on an artificial intelligence algorithm for predicting lymph node metastasis in breast cancer patients: a meta-analysis","volume":"23","author":"Liu","journal-title":"BMC Cancer"},{"key":"R48","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.1046005","article-title":"Diagnostic performance of radiomics in predicting axillary lymph node metastasis in breast cancer: a systematic review and meta-analysis","volume":"12","author":"Gong","journal-title":"Front Oncol"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2026\/1\/e77593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:09:51Z","timestamp":1782842991000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2026\/1\/e77593"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,16]]},"references-count":48,"URL":"https:\/\/doi.org\/10.2196\/77593","relation":{},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,16]]},"article-number":"v28i4e77593"}}