{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:28:39Z","timestamp":1757618919901,"version":"3.44.0"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T00:00:00Z","timestamp":1752710400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T00:00:00Z","timestamp":1752710400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Zhanjiang Competitive Science and Technology Projec","award":["2021A05076"],"award-info":[{"award-number":["2021A05076"]}]},{"name":"Clinical Research Program, Affiliated Hospital of Guangdong Medical University","award":["LCYJ2018B001"],"award-info":[{"award-number":["LCYJ2018B001"]}]},{"name":"Cohort Study Program of Affiliated Hospital of Guangdong Medical University","award":["LCYJ2022DL003"],"award-info":[{"award-number":["LCYJ2022DL003"]}]},{"name":"General Project of Guangdong Provincial Bureau of Traditional Chinese Medicine","award":["2022107"],"award-info":[{"award-number":["2022107"]}]}],"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>Objectives<\/jats:title>\n            <jats:p>This study aims to explore the role of intra- and peri-tumoral radiomics features in tumor risk prediction, with a particular focus on the impact of peri-tumoral characteristics on the tumor microenvironment.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Methods<\/jats:title>\n            <jats:p>A total of 133 patients, including 128 with thymomas and 5 with thymic carcinomas, were ultimately enrolled in this study. Based on the high- and low-risk classification, the cohort was divided into a training set (<jats:italic>n<\/jats:italic>\u2009=\u200993) and a testing set (<jats:italic>n<\/jats:italic>\u2009=\u200940) for subsequent analysis.Based on imaging data from these 133 patients, multiple radiomics prediction models integrating intra-tumoral and peritumoral features were developed. The data were sourced from patients treated at the Affiliated Hospital of Guangdong Medical University between 2015 and 2023, with all imaging obtained through preoperative CT scans. Radiomics feature extraction involved three primary categories: first-order features, shape features, and high-order features. Initially, the tumor\u2019s region of interest (ROI) was manually delineated using ITK-SNAP software. A custom Python algorithm was then used to automatically expand the peri-tumoral area, extracting features within 1\u00a0mm, 2\u00a0mm, and 3\u00a0mm zones surrounding the tumor. Additionally, considering the multimodal nature of the imaging data, image fusion techniques were incorporated to further enhance the model\u2019s ability to capture the tumor microenvironment. To build the radiomics models, selected features were first standardized using z-scores. Initial feature selection was performed using a t-test (<jats:italic>p<\/jats:italic>\u2009&lt;\u20090.05), followed by Spearman correlation analysis to remove redundancy by retaining only one feature from each pair with a correlation coefficient\u2009\u2265\u20090.90. Subsequently, hierarchical clustering and the LASSO algorithm were applied to identify the most predictive features. These selected features were then used to train machine learning models, which were optimized on the training dataset and assessed for predictive performance. To further evaluate the effectiveness of these models, various statistical methods were applied, including DeLong\u2019s test, NRI, and IDI, to compare predictive differences among models. Decision curve analysis (DCA) was also conducted to assess the clinical applicability of the models.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results<\/jats:title>\n            <jats:p>The results indicate that the IntraPeri1mm model performed the best, achieving an AUC of 0.837, with sensitivity and specificity at 0.846 and 0.84, respectively, significantly outperforming other models. SHAP value analysis identified several key features, such as peri_log_sigma_2_0_mm 3D_firstorder RootMeanSquared and intra_wavelet_LLL_firstorder Skewness, which made substantial contributions to the model\u2019s predictive accuracy. NRI and IDI analyses further confirmed the model\u2019s superior clinical applicability, and the DCA curve demonstrated robust performance across different thresholds. DeLong\u2019s test highlighted the statistical significance of the IntraPeri1mm model, underscoring its potential utility in radiomics research.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusions<\/jats:title>\n            <jats:p>Overall, this study provides a new perspective on tumor risk assessment, highlighting the importance of peri-tumoral features in the analysis of the tumor microenvironment. It aims to offer valuable insights for the development of personalized treatment plans.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Clinical trial number<\/jats:title>\n            <jats:p>Not applicable.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1186\/s12880-025-01790-2","type":"journal-article","created":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T17:29:13Z","timestamp":1752773353000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Integrative radiomics of intra- and peri-tumoral features for enhanced risk prediction in thymic tumors: a multimodal analysis of tumor microenvironment contributions"],"prefix":"10.1186","volume":"25","author":[{"given":"Liang","family":"zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiamin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuefeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuyan","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Biao","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,17]]},"reference":[{"issue":"8","key":"1790_CR1","doi-asserted-by":"publisher","first-page":"101146","DOI":"10.1016\/j.xcrm.2023.101146","volume":"4","author":"Y Jiang","year":"2023","unstructured":"Jiang Y, Zhou K, Sun Z, Wang H, et al. Non-invasive tumor microenvironment evaluation and treatment response prediction in gastric cancer using deep learning radiomics. Cell Rep Med. 2023;4(8):101146.","journal-title":"Cell Rep Med"},{"key":"1790_CR2","doi-asserted-by":"publisher","first-page":"103460","DOI":"10.1016\/j.ebiom.2021.103460","volume":"69","author":"Y Yu","year":"2021","unstructured":"Yu Y, He Z, Ouyang J, et al. Magnetic resonance imaging radiomics predicts preoperative axillary lymph node metastasis to support surgical decisions and is associated with tumor microenvironment in invasive breast cancer: A machine learning, multicenter study. EBioMedicine. 2021;69:103460.","journal-title":"EBioMedicine"},{"key":"1790_CR3","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1002\/pro6.70000","volume":"9","author":"Z Li","year":"2025","unstructured":"Li Z, Su Y, Cui Y, Yin Y, Li Z. Multi-sequence MRI-based clinical-radiomics models for the preoperative prediction of microsatellite instability-high status in endometrial cancer. Prec Radiat Oncol. 2025;9:43\u201353.","journal-title":"Prec Radiat Oncol"},{"issue":"9","key":"1790_CR4","doi-asserted-by":"publisher","first-page":"101719","DOI":"10.1016\/j.xcrm.2024.101719","volume":"5","author":"YJ Qi","year":"2024","unstructured":"Qi YJ, Su GH, et al. Radiomics in breast cancer: current advances and future directions. Cell Rep Med. 2024;5(9):101719.","journal-title":"Cell Rep Med"},{"issue":"1","key":"1790_CR5","doi-asserted-by":"publisher","first-page":"e233356","DOI":"10.1148\/radiol.233356","volume":"311","author":"JH Sohn","year":"2024","unstructured":"Sohn JH, Fields BKK. Radiomics and deep learning to predict pulmonary nodule metastasis at CT. Radiology. 2024;311(1):e233356.","journal-title":"Radiology"},{"issue":"1","key":"1790_CR6","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1097\/JTO.0b013e31818e105c","volume":"4","author":"N Girard","year":"2009","unstructured":"Girard N, Mornex F, et al. Thymoma: a focus on current therapeutic management. J Thorac Oncol. 2009;4(1):119\u201326.","journal-title":"J Thorac Oncol"},{"issue":"1","key":"1790_CR7","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1186\/s12880-025-01711-3","volume":"25","author":"S He","year":"2025","unstructured":"He S, Deng B, Chen J, et al. Preoperative DBT-based radiomics for predicting axillary lymph node metastasis in breast cancer: a multi-center study. BMC Med Imaging. 2025;25(1):169.","journal-title":"BMC Med Imaging"},{"issue":"1","key":"1790_CR8","doi-asserted-by":"publisher","first-page":"482","DOI":"10.1016\/j.acra.2024.07.026","volume":"32","author":"J Xu","year":"2025","unstructured":"Xu J, Liu L, Ji Y, et al. Enhanced CT-Based intratumoral and peritumoral radiomics nomograms predict High-Grade patterns of invasive lung adenocarcinoma. Acad Radiol. 2025;32(1):482\u201392.","journal-title":"Acad Radiol"},{"issue":"9","key":"1790_CR9","doi-asserted-by":"publisher","first-page":"e1117","DOI":"10.1016\/j.crad.2024.05.010","volume":"79","author":"W Liu","year":"2024","unstructured":"Liu W, Wang W, Guo M, Zhang H. Tumor habitat and peritumoral region evolution-based imaging features to assess risk categorization of thymomas. Clin Radiol. 2024;79(9):e1117\u201325.","journal-title":"Clin Radiol"},{"issue":"10","key":"1790_CR10","doi-asserted-by":"publisher","first-page":"6241","DOI":"10.1007\/s00330-024-10699-3","volume":"34","author":"G Marvaso","year":"2024","unstructured":"Marvaso G, Isaksson LJ, Zaffaroni M, Vincini MG, Summers PE, Pepa M, Corrao G, Mazzola GC, Rotondi M, Mastroleo F, Raimondi S, Alessi S, Pricolo P, Luzzago S, Mistretta FA, Ferro M, Cattani F, Ceci F, Musi G, De Cobelli O, Cremonesi M, Gandini S, La Torre D, Orecchia R, Petralia G, Jereczek-Fossa BA. Can we predict pathology without surgery? Weighing the added value of multiparametric MRI and whole prostate radiomics in integrative machine learning models. Eur Radiol. 2024;34(10):6241\u201353.","journal-title":"Eur Radiol"},{"issue":"11","key":"1790_CR11","doi-asserted-by":"publisher","first-page":"1722","DOI":"10.1200\/JCO.1988.6.11.1722","volume":"6","author":"WJ Curran Jr","year":"1988","unstructured":"Curran WJ Jr, Kornstein MJ, Brooks JJ, Turrisi AT 3. Invasive thymoma: the role of mediastinal irradiation following complete or incomplete surgical resection. J Clin Oncol. 1988;6(11):1722\u20137.","journal-title":"J Clin Oncol"},{"key":"1790_CR12","doi-asserted-by":"crossref","unstructured":"Travis WD et al. Introduction to the 2015 world health organization classification of tumors of the lung, pleura, thymus, and heart. J Thorac Oncol.10, 1240\u20132.","DOI":"10.1097\/JTO.0000000000000663"},{"key":"1790_CR13","doi-asserted-by":"publisher","unstructured":"Gharibi O et al. Oct. Myocardial perfusion SPECT radiomic features reproducibility assessment: Impact of image reconstruction and harmonization. Medical physics, 2024;29 Oct. https:\/\/doi.org\/10.1002\/mp.17490.","DOI":"10.1002\/mp.17490"},{"issue":"2","key":"1790_CR14","doi-asserted-by":"publisher","first-page":"e240281","DOI":"10.1148\/radiol.240281","volume":"315","author":"SJ Winham","year":"2025","unstructured":"Winham SJ, McCarthy AM, Scott CG, et al. Radiomic parenchymal phenotypes of breast texture from mammography and association with risk of breast Cancer. Radiology. 2025;315(2):e240281.","journal-title":"Radiology"},{"key":"1790_CR15","doi-asserted-by":"crossref","unstructured":"Palmeri F, Zerunian M, Polici M et al. Virtual biopsy through CT imaging: can radiomics differentiate between subtypes of non-small cell lung cancer? Radiol Med. Published online May 22, 2025.","DOI":"10.1007\/s11547-025-02022-x"},{"key":"1790_CR16","doi-asserted-by":"crossref","unstructured":"Fu J, Lin Z, Zhang B, Qiu J, Yang M, Zou Y. MRI-Based Radiomics to Predict Renal Function Response to Renal Artery Stenting for Atherosclerotic Renal Artery Stenosis. Cardiovasc Intervent Radiol. Published online May 12, 2025.","DOI":"10.1007\/s00270-025-04007-9"},{"issue":"6","key":"1790_CR17","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1007\/s12149-025-02034-7","volume":"39","author":"H Liu","year":"2025","unstructured":"Liu H, Meng X, Wang G, et al. Differentiating second primary lung cancer from pulmonary metastasis in patients of single solitary pulmonary lesion with extrapulmonary tumor using multiparametric analysis of FDG PET\/CT. Ann Nucl Med. 2025;39(6):567\u201375.","journal-title":"Ann Nucl Med"},{"key":"1790_CR18","doi-asserted-by":"crossref","unstructured":"Liu Y, Luo C, Wu Y, Zhou S, Ruan G, Li H, Chen W, Lin Y, Liu L, Quan T, He X. Computed tomography Radiomics-based combined model for predicting thymoma risk subgroups: A multicenter retrospective study. Acad Radiol. 2025. Jun;32(6):3258\u201368.","DOI":"10.1016\/j.acra.2025.01.010"},{"key":"1790_CR19","doi-asserted-by":"crossref","unstructured":"Liang Z, Li J, He S et al. Thymoma habitat segmentation and risk prediction model using CT imaging and K-means clustering. Med Phys. 2025 May 19.","DOI":"10.1002\/mp.17892"},{"key":"1790_CR20","doi-asserted-by":"publisher","first-page":"391","DOI":"10.2340\/1651-226X.2025.42982","volume":"64","author":"Y Yang","year":"2025","unstructured":"Yang Y, Cheng J, Cui C, et al. Multi-dimensional interpretable deep learning-radiomics based on intra-tumoral and Spatial habitatfor preoperative prediction of thymic epithelial tumours risk categorisation. Acta Oncol. 2025;64:391\u2013405.","journal-title":"Acta Oncol"},{"issue":"1","key":"1790_CR21","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1186\/s12880-024-01367-5","volume":"24","author":"C Gao","year":"2024","unstructured":"Gao C, Yang L, Xu Y, Wang T, Ding H, Gao X, Li L. Differentiating low-risk thymomas from high-risk thymomas: preoperative radiomics nomogram based on contrast enhanced CT to minimize unnecessary invasive thoracotomy. BMC Med Imaging. 2024;24(1):197.","journal-title":"BMC Med Imaging"},{"key":"1790_CR22","doi-asserted-by":"publisher","first-page":"915835","DOI":"10.3389\/fonc.2022.915835","volume":"12","author":"R Chang","year":"2022","unstructured":"Chang R, Qi S, Zuo Y, Yue Y, Zhang X, Guan Y, Qian W. Predicting chemotherapy response in non-small-cell lung cancer via computed tomography radiomic features: peritumoral, intratumoral, or combined? Front Oncol. 2022;12:915835.","journal-title":"Front Oncol"},{"key":"1790_CR23","doi-asserted-by":"publisher","first-page":"100653","DOI":"10.1016\/j.pacs.2024.100653","volume":"40","author":"S Mo","year":"2024","unstructured":"Mo S, Luo H, Wang M, Li G, Kong Y, Tian H, Wu H, Tang S, Pan Y, Wang Y, Xu J, Huang Z, Dong F. Machine learning radiomics based on intra and Peri tumor PA\/US images distinguish between luminal and non-luminal tumors in breast cancers. Photoacoustics. 2024;40:100653.","journal-title":"Photoacoustics"},{"issue":"1","key":"1790_CR24","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1186\/s13244-024-01623-w","volume":"15","author":"HF Liu","year":"2024","unstructured":"Liu HF, Wang M, Wang Q, Lu Y, Lu YJ, Sheng Y, Xing F, Zhang JL, Yu SN, Xing W. Multiparametric MRI-based intratumoral and peritumoral radiomics for predicting the pathological differentiation of hepatocellular carcinoma. Insights Imaging. 2024;15(1):97.","journal-title":"Insights Imaging"}],"container-title":["BMC Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-025-01790-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12880-025-01790-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-025-01790-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T13:19:29Z","timestamp":1757251169000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedimaging.biomedcentral.com\/articles\/10.1186\/s12880-025-01790-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,17]]},"references-count":24,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1790"],"URL":"https:\/\/doi.org\/10.1186\/s12880-025-01790-2","relation":{},"ISSN":["1471-2342"],"issn-type":[{"type":"electronic","value":"1471-2342"}],"subject":[],"published":{"date-parts":[[2025,7,17]]},"assertion":[{"value":"4 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The study was conducted in accordance with the Declaration of Helsinki (as revised in 2013). The study was approved by the Institutional Review Board and Ethical Committee of Affiliated Hospital of Guangdong Medical University. The need for informed consent was waived by the ethics committee of Affiliated Hospital of Guangdong Medical University, because of the retrospective nature of the study.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"286"}}