{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T09:07:51Z","timestamp":1785402471281,"version":"3.56.0"},"reference-count":24,"publisher":"IMR Press","issue":"7","license":[{"start":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T00:00:00Z","timestamp":1784851200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Discipline Development Project of Medical Imaging, the Shanghai Ninth People\u2019s Hospital, Shanghai Jiao Tong University School of Medicine","award":["XKQJS202403"],"award-info":[{"award-number":["XKQJS202403"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Br. J. Hosp. Med. (Lond)"],"abstract":"<jats:p>Aims\/Background:The differentiation of benign and malignant breast nodules, particularly those categorized as Breast Imaging Reporting and Data System (BI-RADS) 3\u20134, remains a clinical challenge due to the subjectivity and operator dependence of conventional ultrasound assessment. This study aimed to evaluate the diagnostic value of intratumoral and peritumoral ultrasound radiomics features in distinguishing benign from malignant BI-RADS 3\u20134 breast nodules and to construct interpretable machine learning models.Methods:Ultrasound images and parameters (BI-RADS classification) of breast nodules were retrospectively collected from female patients at two institutions between January 2021 and June 2024: 571 patients (880 nodules) from Institution 1 (Shanghai Ninth People\u2019s Hospital, Shanghai Jiao Tong University School of Medicine) and 333 patients (351 nodules) from Institution 2 (Shanghai Second People\u2019s Hospital). Included patients had BI-RADS 3\u20134 nodules confirmed by pathology or, for BI-RADS 3 nodules, stable findings on follow-up for at least 2 years. Nodules from Institution 1 were randomly divided into a training set (n = 615) and an internal validation set (n = 265) at a 7:3 ratio, while patients from Institution 2 constituted an external test set (n = 351). Radiomics features of intratumoral and peritumoral regions (3 and 5 pixels wide) were extracted using PyRadiomics. Features were screened using the independent t-test, Spearman correlation, and least absolute shrinkage and selection operator (LASSO) regression. Machine learning models\u2014including random forest (RF), multilayer perceptron (MLP), extra trees (ET), support vector machine (SVM), logistic regression (LR), k-nearest neighbor (KNN), eXtreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), Gradient Boosting Decision Tree (GBDT), and Light Gradient Boosting Machine (LightGBM)\u2014were trained and compared using area under the curve (AUC) and other metrics. The best-performing model was then used to compare intratumoral versus peritumoral regions. SHapley Additive exPlanations (SHAP) was applied to interpret feature importance.Results:Across the training, internal validation, and external test sets, SVM demonstrated the most stable and balanced performance. The 3 pixels transitional zone region of interest support vector machine (EI3_SVM) model achieved a higher AUC than the tumor core region of interest (T) model in the external test set (0.875 vs. 0.787, p &lt; 0.01), with accuracy 78.1%, sensitivity 42.2%, specificity 97.0%, and Brier score 0.166, outperforming other peritumoral models. Most models incorporating peritumoral features demonstrated AUCs that were higher than or comparable to those of the T model. SHAP analysis indicated that the high specificity was mainly driven by texture and shape features.Conclusion:Integrating intratumoral and peritumoral radiomics features significantly improves the diagnostic accuracy and objectivity for differentiating benign and malignant breast nodules. This approach may aid clinical decision-making, reduce unnecessary biopsies, and support early precision diagnosis of breast cancer.<\/jats:p>","DOI":"10.31083\/bjhm56311","type":"journal-article","created":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T07:59:43Z","timestamp":1785398383000},"source":"Crossref","is-referenced-by-count":0,"title":["Integrated Intratumoral and Peritumoral Ultrasound Radiomics Models for Breast Nodule Diagnosis Using Machine Learning"],"prefix":"10.31083","volume":"87","author":[{"given":"Xinru","family":"Yang","sequence":"first","affiliation":[{"name":"Department of Ultrasound Medicine, Shanghai Ninth People\u2019s Hospital, Shanghai Jiao Tong University School of Medicine, 200011 Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxin","family":"Zuo","sequence":"additional","affiliation":[{"name":"Department of Ultrasound Medicine, Shanghai Ninth People\u2019s Hospital, Shanghai Jiao Tong University School of Medicine, 200011 Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cuiping","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Ultrasound Medicine, Shanghai Second People\u2019s Hospital, 200011 Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huihong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Ultrasound Medicine, Shanghai Ninth People\u2019s Hospital, Shanghai Jiao Tong University School of Medicine, 200011 Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8755-6815","authenticated-orcid":true,"given":"Ping","family":"Xiong","sequence":"additional","affiliation":[{"name":"Department of Ultrasound Medicine, Shanghai Ninth People\u2019s Hospital, Shanghai Jiao Tong University School of Medicine, 200011 Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"16242","published-online":{"date-parts":[[2026,7,24]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","unstructured":"Bray F, Laversanne M, Sung H, Ferlay J, Siegel RL, Soerjomataram I, et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: a Cancer Journal for Clinicians. 2024; 74: 229\u2013263.","DOI":"10.3322\/caac.21834"},{"key":"ref2","doi-asserted-by":"publisher","unstructured":"Kim J, Harper A, McCormack V, Sung H, Houssami N, Morgan E, et al. Global patterns and trends in breast cancer incidence and mortality across 185 countries. Nature Medicine. 2025; 31: 1154\u20131162.","DOI":"10.1038\/s41591-025-03502-3"},{"key":"ref3","doi-asserted-by":"publisher","unstructured":"Wei Q, Yan YJ, Wu GG, Ye XR, Jiang F, Liu J, et al. The diagnostic performance of ultrasound computer-aided diagnosis system for distinguishing breast masses: a prospective multicenter study. European Radiology. 2022; 32: 4046\u20134055.","DOI":"10.1007\/s00330-021-08452-1"},{"key":"ref4","doi-asserted-by":"publisher","unstructured":"Giess CS, Frost EP, Birdwell RL. Difficulties and errors in diagnosis of breast neoplasms. Seminars in Ultrasound, CT, and MR. 2012; 33: 288\u2013299.","DOI":"10.1053\/j.sult.2012.01.007"},{"key":"ref5","doi-asserted-by":"publisher","unstructured":"Hong M, Fan S, Xu Z, Fang Z, Ling K, Lai P, et al. MRI radiomics and biological correlations for predicting axillary lymph node burden in early-stage breast cancer. Journal of Translational Medicine. 2024; 22: 826.","DOI":"10.1186\/s12967-024-05619-4"},{"key":"ref6","doi-asserted-by":"publisher","unstructured":"Magnuska ZA, Roy R, Palmowski M, Kohlen M, Winkler BS, Pfeil T, et al. Combining Radiomics and Autoencoders to Distinguish Benign and Malignant Breast Tumors on US Images. Radiology. 2024; 312: e232554.","DOI":"10.1148\/radiol.232554"},{"key":"ref7","doi-asserted-by":"publisher","unstructured":"Li SY, Li YM, Fang YQ, Jin ZY, Li JK, Zou XM, et al. Contrast-enhanced ultrasound radiomics model for predicting axillary lymph node metastasis and prognosis in breast cancer: a multicenter study. BMC Cancer. 2025; 25: 1315.","DOI":"10.1186\/s12885-025-14632-9"},{"key":"ref8","doi-asserted-by":"publisher","unstructured":"Hanahan D, Weinberg RA. Hallmarks of cancer: the next generation. Cell. 2011; 144: 646\u2013674.","DOI":"10.1016\/j.cell.2011.02.013"},{"key":"ref9","doi-asserted-by":"publisher","unstructured":"Quail DF, Joyce JA. Microenvironmental regulation of tumor progression and metastasis. Nature Medicine. 2013; 19: 1423\u20131437.","DOI":"10.1038\/nm.3394"},{"key":"ref10","doi-asserted-by":"publisher","unstructured":"Yu T, Yu R, Liu M, Wang X, Zhang J, Zheng Y, et al. Integrating intratumoral and peritumoral radiomics with deep transfer learning for DCE-MRI breast lesion differentiation: A multicenter study comparing performance with radiologists. European Journal of Radiology. 2024; 177: 111556.","DOI":"10.1016\/j.ejrad.2024.111556"},{"key":"ref11","doi-asserted-by":"publisher","unstructured":"Berg WA, Vourtsis A. Screening Breast Ultrasound Using Handheld or Automated Technique in Women with Dense Breasts. Journal of Breast Imaging. 2019; 1: 283\u2013296.","DOI":"10.1093\/jbi\/wbz055"},{"key":"ref12","doi-asserted-by":"publisher","unstructured":"Schwab F, Redling K, Siebert M, Sch\u00f6tzau A, Schoenenberger CA, Zanetti-D\u00e4llenbach R. Inter- and Intra-Observer Agreement in Ultrasound BI-RADS Classification and Real-Time Elastography Tsukuba Score Assessment of Breast Lesions. Ultrasound in Medicine & Biology. 2016; 42: 2622\u20132629.","DOI":"10.1016\/j.ultrasmedbio.2016.06.017"},{"key":"ref13","doi-asserted-by":"publisher","unstructured":"Youk JH, Kwak JY, Lee E, Son EJ, Kim JA. Grayscale Ultrasound Radiomic Features and Shear-Wave Elastography Radiomic Features in Benign and Malignant Breast Masses. Ultraschall in Der Medizin. 2020; 41: 390\u2013396.","DOI":"10.1055\/a-0917-6825"},{"key":"ref14","doi-asserted-by":"publisher","unstructured":"Gillies RJ, Kinahan PE, Hricak H. Radiomics: Images Are More than Pictures, They Are Data. Radiology. 2016; 278: 563\u2013577.","DOI":"10.1148\/radiol.2015151169"},{"key":"ref15","doi-asserted-by":"publisher","unstructured":"Hong ZL, Chen S, Peng XR, Li JW, Yang JC, Wu SS. Nomograms for prediction of breast cancer in breast imaging reporting and data system (BI-RADS) ultrasound category 4 or 5 lesions: A single-center retrospective study based on radiomics features. Frontiers in Oncology. 2022; 12: 894476.","DOI":"10.3389\/fonc.2022.894476"},{"key":"ref16","doi-asserted-by":"publisher","unstructured":"Huang Z, Mo S, Wu H, Kong Y, Luo H, Li G, et al. Optimizing breast cancer diagnosis with photoacoustic imaging: An analysis of intratumoral and peritumoral radiomics. Photoacoustics. 2024; 38: 100606.","DOI":"10.1016\/j.pacs.2024.100606"},{"key":"ref17","doi-asserted-by":"publisher","unstructured":"Kim ES, Ham S, Seo BK, Lee JY, Sun W, Jeon M, et al. Optimized prediction of breast cancer tumor microenvironment using MRI-based intratumoral and peritumoral radiomics: a prospective study. Frontiers in Oncology. 2025; 15: 1654508.","DOI":"10.3389\/fonc.2025.1654508"},{"key":"ref18","doi-asserted-by":"publisher","unstructured":"Wu J, Li B, Sun X, Cao G, Rubin DL, Napel S, et al. Heterogeneous Enhancement Patterns of Tumor-adjacent Parenchyma at MR Imaging Are Associated with Dysregulated Signaling Pathways and Poor Survival in Breast Cancer. Radiology. 2017; 285: 401\u2013413.","DOI":"10.1148\/radiol.2017162823"},{"key":"ref19","doi-asserted-by":"publisher","unstructured":"Grossmann P, Stringfield O, El-Hachem N, Bui MM, Rios Velazquez E, Parmar C, et al. Defining the biological basis of radiomic phenotypes in lung cancer. eLife. 2017; 6: e23421.","DOI":"10.7554\/eLife.23421"},{"key":"ref20","doi-asserted-by":"publisher","unstructured":"Beig N, Khorrami M, Alilou M, Prasanna P, Braman N, Orooji M, et al. Perinodular and Intranodular Radiomic Features on Lung CT Images Distinguish Adenocarcinomas from Granulomas. Radiology. 2019; 290: 783\u2013792.","DOI":"10.1148\/radiol.2018180910"},{"key":"ref21","doi-asserted-by":"publisher","unstructured":"Yao J, Jia X, Zhou W, Zhu Y, Chen X, Zhan W, et al. Predicting axillary response to neoadjuvant chemotherapy using peritumoral and intratumoral ultrasound radiomics in breast cancer subtypes. iscience. 2024; 27: 110716.","DOI":"10.1016\/j.isci.2024.110716"},{"key":"ref22","doi-asserted-by":"publisher","unstructured":"Ding J, Chen S, Serrano Sosa M, Cattell R, Lei L, Sun J, et al. Optimizing the Peritumoral Region Size in Radiomics Analysis for Sentinel Lymph Node Status Prediction in Breast Cancer. Academic Radiology. 2022; 29: S223\u2013S228.","DOI":"10.1016\/j.acra.2020.10.015"},{"key":"ref23","doi-asserted-by":"publisher","unstructured":"Guo S, Huang X, Xu C, Yu M, Li Y, Wu Z, et al. Multiregional radiomic model for breast cancer diagnosis: value of ultrasound-based peritumoral and parenchymal radiomics. Quantitative Imaging in Medicine and Surgery. 2023; 13: 3127\u20133139.","DOI":"10.21037\/qims-22-939"},{"key":"ref24","doi-asserted-by":"publisher","unstructured":"Singh H, Sharma V, Singh D. Comparative analysis of proficiencies of various textures and geometric features in breast mass classification using k-nearest neighbor. Visual Computing for Industry, Biomedicine, and Art. 2022; 5: 3.","DOI":"10.1186\/s42492-021-00100-1"}],"container-title":["British Journal of Hospital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.imrpress.com\/journal\/BJHM\/87\/7\/10.31083\/BJHM56311","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T07:59:46Z","timestamp":1785398386000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.imrpress.com\/journal\/BJHM\/87\/7\/10.31083\/BJHM56311"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,24]]},"references-count":24,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026]]}},"alternative-id":["S1750-8460(26)03359-0"],"URL":"https:\/\/doi.org\/10.31083\/bjhm56311","relation":{},"ISSN":["1750-8460","1759-7390"],"issn-type":[{"value":"1750-8460","type":"print"},{"value":"1759-7390","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,24]]},"article-number":"56311"}}