{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T11:20:05Z","timestamp":1764156005965,"version":"3.46.0"},"reference-count":30,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T00:00:00Z","timestamp":1761609600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Int J Imaging Syst Tech"],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Identifying the primary tumor origin is a critical factor in determining treatment strategies for brain metastases, which remain a major challenge in clinical practice. Traditional diagnostic methods rely on invasive procedures, which may be limited by sampling errors. In this study, a dataset of 200 patients with brain metastases originating from six different cancer types (breast, gastrointestinal, small cell lung, melanoma, non\u2010small cell lung, and renal cell carcinoma) was included. Radiomic features were extracted from different magnetic resonance images (MRI) and selected using the Kruskal\u2013Wallis test, correlation analysis, and ElasticNet regression. Machine learning models, including support vector machine, logistic regression, and random forest, were trained and evaluated using cross\u2010validation and unseen test sets to predict the primary origins of metastatic brain tumors. Our results demonstrate that radiomic features can significantly enhance classification accuracy, with AUC values reaching 0.98 in distinguishing between specific cancer types. Additionally, survival analysis revealed significant differences in survival probabilities across primary tumor types. This study utilizes a larger, single\u2010center cohort and a standardized MRI protocol, applying rigorous feature selection and multiple machine learning classifiers to enhance the robustness and clinical relevance of radiomic predictions. Our findings support the potential of radiomics as a non\u2010invasive tool for metastatic tumor prediction and prognostic assessment, paving the way for improved personalized treatment strategies. Radiomic features extracted from MRI images can significantly enhance the prediction of the main origin of the metastatic tumor types in the brain, thereby informing treatment decisions and prognostic assessments.<\/jats:p>","DOI":"10.1002\/ima.70234","type":"journal-article","created":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T13:21:38Z","timestamp":1761657698000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Radiomic Feature\u2010Based Prediction of Primary Cancer Origins in Brain Metastases Using Machine Learning"],"prefix":"10.1002","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1124-3695","authenticated-orcid":false,"given":"Dilek Bet\u00fcl","family":"Sar\u0131dede","sequence":"first","affiliation":[{"name":"Biomedical Engineering Department Istanbul Atlas University  Istanbul Turkey"}]},{"given":"Sevim","family":"Cengiz","sequence":"additional","affiliation":[{"name":"College of Technological Innovation Zayed University  Dubai UAE"}]}],"member":"311","published-online":{"date-parts":[[2025,10,28]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-802997-8.00023-2"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trecan.2018.01.003"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.924245"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.3348\/kjr.2020.1433"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2021.110141"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41698-021-00205-z"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2018180946"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00234-020-02529-2"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2024.1474461"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.26643"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1097\/RCT.0000000000001499"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.7937\/6be1\u2010r748"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597\u2010024\u201003021\u20109"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00503.x"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022627411411"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/9781118548387"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1093\/annonc\/mdq692"},{"issue":"4","key":"e_1_2_9_20_1","first-page":"572","article-title":"Survival Rates of Patients With Metastatic Malignant Melanoma","volume":"7","author":"Sandru A.","year":"2014","journal-title":"Journal of Medicine and Life"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-021-08146-8"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1097\/JTO.0000000000000630"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-020-06896-5"},{"issue":"1","key":"e_1_2_9_24_1","first-page":"1","article-title":"The Effect of Dataset Size on Classification Performance: An Empirical Study With Medical Data","volume":"5","author":"Johnson J. M.","year":"2018","journal-title":"Journal of Big Data"},{"key":"e_1_2_9_25_1","first-page":"5998","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Vaswani A.","year":"2017"},{"key":"e_1_2_9_26_1","first-page":"15534","article-title":"Multimodal Deep Learning for Cancer Subtype Classification Using Genomic and Histopathological Data","volume":"11","author":"Kim J.","year":"2021","journal-title":"Scientific Reports"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.3390\/cancers14184399"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-90572-5"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-024-01312-w"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13721-025-00504-6"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.107387"}],"container-title":["International Journal of Imaging Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/ima.70234","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T11:16:10Z","timestamp":1764155770000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/ima.70234"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,28]]},"references-count":30,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["10.1002\/ima.70234"],"URL":"https:\/\/doi.org\/10.1002\/ima.70234","archive":["Portico"],"relation":{},"ISSN":["0899-9457","1098-1098"],"issn-type":[{"type":"print","value":"0899-9457"},{"type":"electronic","value":"1098-1098"}],"subject":[],"published":{"date-parts":[[2025,10,28]]},"assertion":[{"value":"2025-03-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-12","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70234"}}