{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T07:15:40Z","timestamp":1788419740040,"version":"build-2803163510"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T00:00:00Z","timestamp":1788393600000},"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. Cell Dev. Biol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Accurate discrimination between benign and malignant breast masses is essential for biopsy decisions and individualized management. This study aimed to develop an interpretable machine-learning model integrating artificial intelligence (AI)-structured digital breast tomosynthesis (DBT) mass features with peripheral blood immune-inflammatory indices.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective study included 382 patients with 401 pathologically confirmed breast mass lesions (299 benign and 102 malignant) who underwent DBT before pathological examination. AI-structured DBT descriptors, clinical variables, and hematologic inflammatory indices were collected. Lesions were divided into training and testing cohorts using stratified random sampling at a 7:3 ratio. Least absolute shrinkage and selection operator (LASSO) logistic regression was used for feature selection, and five machine-learning models were trained. Model performance was evaluated using the area under the receiver operating characteristic curve (AUROC), calibration, decision curve analysis, Brier score, and confusion matrix. SHapley Additive exPlanations (SHAP) analysis was used to interpret the final model, and predicted probabilities were used for descriptive risk stratification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Logistic LASSO regression selected nine predictors: suspicious calcifications, irregular mass shape, age, long-axis diameter, neutrophil-to-lymphocyte ratio (NLR), short-axis diameter, oval mass shape, absence of calcifications, and obscured margin. In the testing cohort, the logistic regression model achieved the highest AUROC (0.884, 95% CI: 0.807\u20130.950), with an accuracy of 0.860, sensitivity of 0.806, specificity of 0.878, and negative predictive value of 0.929. SHAP analysis results indicate that suspicious calcifications, advanced age, irregular morphology, elevated NLR, and larger lesion size may be the primary factors contributing to the prediction of malignancy. The malignancy rate observed in this study ranged from 2.5% in the low-risk group to 67.6% in the high-risk group.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The logistic regression (LR) model integrating AI-derived structured DBT features, clinical variables, and peripheral blood immune-inflammatory biomarkers demonstrated favorable performance for breast mass classification and malignancy risk stratification, with a test-set AUROC of 0.884. Prospective multicentre external validation is required.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fcell.2026.1917987","type":"journal-article","created":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T06:40:23Z","timestamp":1788417623000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Explainable machine learning for breast mass characterization and malignancy risk stratification: multimodal integration of AI-derived structured digital breast tomosynthesis features and peripheral blood immune-inflammatory biomarkers"],"prefix":"10.3389","volume":"14","author":[{"given":"Lu","family":"Nie","sequence":"first","affiliation":[{"name":"Department of Radiology, Changzhou Maternal and Child Health Care Hospital, Changzhou Medical Center, Nanjing Medical University","place":["Changzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Radiology, Changzhou Maternal and Child Health Care Hospital, Changzhou Medical Center, Nanjing Medical University","place":["Changzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Radiology, Changzhou Maternal and Child Health Care Hospital, Changzhou Medical Center, Nanjing Medical University","place":["Changzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yizi","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Radiology, Changzhou Maternal and Child Health Care Hospital, Changzhou Medical Center, Nanjing Medical University","place":["Changzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,3]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"101976","DOI":"10.1016\/j.tranon.2024.101976","article-title":"Breast imaging reporting and data system for sonography: positive and negative predictive values of sonographic features in kumasi, Ghana","volume":"45","author":"Badu-Peprah","year":"2024","journal-title":"Transl. Oncol."},{"key":"B2","doi-asserted-by":"publisher","first-page":"2199","DOI":"10.1001\/jama.2017.14585","article-title":"Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer","volume":"318","author":"Bejnordi","year":"2017","journal-title":"JAMA"},{"key":"B3","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1002\/cpt.1951","article-title":"Artificial intelligence and mechanistic modeling for clinical decision making in oncology","volume":"108","author":"Benzekry","year":"2020","journal-title":"Clin. Pharmacol. Ther."},{"key":"B4","doi-asserted-by":"publisher","first-page":"229","DOI":"10.3322\/caac.21834","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA Cancer J. Clin."},{"key":"B5","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1148\/radiol.2422052130","article-title":"Use of microcalcification descriptors in BI-RADS 4th edition to stratify risk of malignancy","volume":"242","author":"Burnside","year":"2007","journal-title":"Radiology"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1397","DOI":"10.2147\/OTT.S227171","article-title":"The research progress on the prognostic value of the common hematological parameters in peripheral venous blood in breast cancer","volume":"13","author":"Chen","year":"2020","journal-title":"Onco Targets Ther."},{"key":"B7","doi-asserted-by":"publisher","first-page":"60","DOI":"10.3892\/mco.2024.2758","article-title":"Age-integrated breast imaging reporting and data system assessment model to improve the accuracy of breast cancer diagnosis","volume":"21","author":"Deng, J.","year":"2024","journal-title":"Mol. Clin. Oncol."},{"key":"B8","doi-asserted-by":"publisher","first-page":"e19","DOI":"10.1002\/imo2.19","article-title":"A glimpse into the future: integrating artificial intelligence for precision HER2-positive breast cancer management","volume":"1","author":"Deng","year":"","journal-title":"iMetaOmics"},{"key":"B9","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1007\/s11427-023-2491-7","article-title":"The burgeoning importance of PIWI-interacting RNAs in cancer progression","volume":"67","author":"Deng","year":"","journal-title":"Sci. China Life Sci."},{"key":"B10","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1016\/j.cancergen.2025.07.010","article-title":"Unraveling prognostic biomarkers in oral squamous cell carcinoma: an approach based on explainable artificial intelligence","author":"Dogra","year":"2025","journal-title":"Cancer Genet."},{"key":"B11","volume-title":"ACR BI-RADS Atlas: Breast Imaging Reporting and Data System","author":"D\u2019Orsi","year":"2013"},{"key":"B12","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1038\/nrclinonc.2017.101","article-title":"The immune contexture in cancer prognosis and treatment","volume":"14","author":"Fridman","year":"2017","journal-title":"Nat. Rev. Clin. Oncol."},{"key":"B13","doi-asserted-by":"publisher","first-page":"2499","DOI":"10.1001\/jama.2014.6095","article-title":"Breast cancer screening using tomosynthesis in combination with digital mammography","volume":"311","author":"Friedewald","year":"2014","journal-title":"JAMA"},{"key":"B14","doi-asserted-by":"publisher","first-page":"13203","DOI":"10.1038\/s41598-020-70077-z","article-title":"Neutrophil to lymphocyte ratio and breast cancer risk: analysis by subtype and potential interactions","volume":"10","author":"Gago-Dominguez","year":"2020","journal-title":"Sci. Rep."},{"key":"B15","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.immuni.2019.12.011","article-title":"Top 10 challenges in cancer immunotherapy","volume":"52","author":"Hegde","year":"2020","journal-title":"Immunity"},{"key":"B16","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1055\/s-0045-1809161","article-title":"Malignancy risk stratification of suspicious breast microcalcifications detected on mammograms using morphological and distribution characteristics based on the fifth edition of BI-RADS","volume":"36","author":"Hegde","year":"2025","journal-title":"Indian J. Radiol. Imaging"},{"key":"B17","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1258\/ar.2011.100357","article-title":"Mammographic morphology and distribution of calcifications in ductal carcinoma in situ diagnosed in organized screening","volume":"52","author":"Hofvind","year":"2011","journal-title":"Acta Radiol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"1260","DOI":"10.2214\/ajr.184.4.01841260","article-title":"BI-RADS for sonography: positive and negative predictive values of sonographic features","volume":"184","author":"Hong","year":"2005","journal-title":"AJR Am. J. Roentgenol."},{"key":"B19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cancergen.2025.08.003","article-title":"The impact of extracellular vesicles on breast cancer metastasis and therapeutics: genetic considerations","author":"Jahangiri","year":"2025","journal-title":"Cancer Genet."},{"key":"B20","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1016\/j.cancergen.2025.02.004","article-title":"Integrating radiomics and gene expression by mapping on the image with improved DeepInsight for clear cell renal cell carcinoma","author":"Kawahara","year":"2025","journal-title":"Cancer Genet."},{"key":"B21","doi-asserted-by":"publisher","first-page":"25","DOI":"10.4174\/astr.2021.100.1.25","article-title":"Prognostic implication of systemic inflammatory markers in young patients with resectable colorectal cancer","volume":"100","author":"Lee","year":"2021","journal-title":"Ann. Surg. Treat. Res."},{"key":"B22","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1038\/s41586-019-1799-6","article-title":"International evaluation of an AI system for breast cancer screening","volume":"577","author":"McKinney","year":"2020","journal-title":"Nature"},{"key":"B23","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1007\/s10911-005-5400-6","article-title":"Microcalcifications associated with breast cancer: an epiphenomenon or biologically significant feature of selected tumors?","volume":"10","author":"Morgan","year":"2005","journal-title":"J. Mammary Gland. Biol. Neoplasia"},{"key":"B24","doi-asserted-by":"publisher","first-page":"216","DOI":"10.2214\/AJR.13.11047","article-title":"Detection of mammographically occult architectural distortion on digital breast tomosynthesis screening: initial clinical experience","volume":"203","author":"Partyka","year":"2014","journal-title":"AJR Am. J. Roentgenol."},{"key":"B25","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1002\/jum.15722","article-title":"A new practical decision rule to better differentiate BI-RADS 3 or 4 breast masses on breast ultrasound","volume":"41","author":"Pfob","year":"2022","journal-title":"J. Ultrasound Med."},{"key":"B26","doi-asserted-by":"publisher","first-page":"20628","DOI":"10.1038\/s41598-020-77456-6","article-title":"Diagnostic accuracy of digital breast tomosynthesis in combination with 2D mammography for the characterisation of mammographic abnormalities","volume":"10","author":"Sanmugasiva","year":"2020","journal-title":"Sci. Rep."},{"key":"B27","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1007\/s10549-015-3332-4","article-title":"BI-RADS update for breast cancer caregivers","volume":"150","author":"Sedgwick","year":"2015","journal-title":"Breast Cancer Res. Treat."},{"key":"B28","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1007\/s11906-022-01212-6","article-title":"Machine learning for hypertension prediction: a systematic review","volume":"24","author":"Silva","year":"2022","journal-title":"Curr. Hypertens. Rep."},{"key":"B29","doi-asserted-by":"publisher","first-page":"e36315","DOI":"10.1097\/MD.0000000000036315","article-title":"Peripheral blood inflammatory indexes in breast cancer: a review","volume":"102","author":"Xie","year":"2023","journal-title":"Med. Baltim."},{"key":"B30","doi-asserted-by":"publisher","first-page":"41","DOI":"10.3892\/ol.2024.14787","article-title":"Diagnostic role of the neutrophil-to-lymphocyte ratio and the platelet-to-lymphocyte ratio in breast cancer: a systematic review and meta-analysis","volume":"29","author":"Yang","year":"2025","journal-title":"Oncol. Lett."}],"container-title":["Frontiers in Cell and Developmental Biology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2026.1917987\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T06:40:24Z","timestamp":1788417624000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2026.1917987\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,3]]},"references-count":30,"alternative-id":["10.3389\/fcell.2026.1917987"],"URL":"https:\/\/doi.org\/10.3389\/fcell.2026.1917987","relation":{},"ISSN":["2296-634X"],"issn-type":[{"value":"2296-634X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,3]]},"article-number":"1917987"}}