{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T22:42:17Z","timestamp":1793313737651,"version":"4.5.0"},"reference-count":41,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"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. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Early identification of the primary tumor types in brain metastases (BMs) is crucial for developing effective treatment strategies. This study aimed to evaluate the potential of multiparametric MRI (mpMRI)-based habitat radiomics analysis in differentiating the pathological types of BMs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>Pre-treatment MR images from 328 BMs patients at a single center were retrospectively collected and randomly divided into a training set (229 cases) and a test set (99 cases). Tumor regions were manually segmented on contrast-enhanced T1-weighted images (CE-T1WI), and the K-means clustering algorithm was employed to classify the tumor into four distinct sub-regions. Radiomics features were extracted separately from each sub-region to construct the habitat model. The resulting habitat model was compared alongside a traditional whole-tumor radiomics model, a clinical model, and a combined model (integrating habitat and clinical variables). Model performance was evaluated by the area under the receiver operating characteristic curve (AUC), as well as accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The combined model achieved the highest overall performance (training AUC: 0.992, accuracy: 0.952; test AUC: 0.939, accuracy: 0.845), outperforming the habitat model (training AUC: 0.965, accuracy: 0.876; test AUC: 0.888, accuracy: 0.835), traditional radiomics model (training AUC: 0.984, accuracy: 0.866; test AUC: 0.884, accuracy: 0.754), and clinical model (training AUC: 0.788, accuracy: 0.731; test AUC: 0.716, accuracy: 0.653). However, class-specific evaluation revealed substantial performance variation, with F1-scores of 0.874 for lung cancer BMs, but only 0.333 and 0.200 for breast and gastrointestinal cancer BMs, respectively.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study demonstrates that while habitat radiomics shows potential for classifying BMs, its current performance is constrained by class imbalance and scanner heterogeneity. Consequently, our primary contribution lies in providing a critical baseline and a clear direction, prioritizing data-centric solutions as the essential next step for the field.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2025.1714315","type":"journal-article","created":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T05:14:41Z","timestamp":1764652481000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Multiparametric-MRI habitat radiomics analysis for discriminating pathological types of brain metastases"],"prefix":"10.3389","volume":"15","author":[{"given":"Jinling","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jixuan","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruizhe","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wu","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,12,2]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.pmr.2016.08.005","article-title":"Brain tumors and metastases","volume":"28","author":"Vargo","year":"2017","journal-title":"Phys Med Rehabil Clin N Am"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1093\/neuonc\/noab101","article-title":"Epidemiology of brain metastases and leptomeningeal disease","volume":"23","author":"Lamba","year":"2021","journal-title":"Neuro Oncol"},{"key":"B3","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1038\/s41572-018-0055-y","article-title":"Brain metastases","volume":"5","author":"Achrol","year":"2019","journal-title":"Nat Rev Dis Primers."},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejso.2016.10.006","article-title":"The evolving clinical management of cerebral metastases","volume":"43","author":"Sinha","year":"2017","journal-title":"Eur J Surg Oncol"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.nec.2020.06.001","article-title":"Epidemiology of brain metastases","volume":"31","author":"Sacks","year":"2020","journal-title":"Neurosurg Clin N Am"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.wneu.2018.11.086","article-title":"Gamma knife radiosurgery for metastatic brain tumors from cancer of unknown primary","volume":"122","author":"Matsunaga","year":"2019","journal-title":"World Neurosurg"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1007\/s00401-016-1545-1","article-title":"The 2016 world health organization classification of tumors of the central nervous system: a summary","volume":"131","author":"Louis","year":"2016","journal-title":"Acta Neuropathol."},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2018180946","article-title":"Radiomics of brain MRI: utility in prediction of metastatic tumor type","volume":"290","author":"Kniep","year":"2019","journal-title":"Radiology."},{"key":"B9","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1007\/s11547-024-01934-4","article-title":"Radiomics based on brain-to-tumor interface enables prediction of metastatic tumor type of brain metastasis: a proof-of-concept study","volume":"130","author":"Jiang","year":"2025","journal-title":"Radiol Med"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.crad.2023.10.022","article-title":"Peritumoural MRI radiomics signature of brain metastases can predict epidermal growth factor receptor mutation status in lung adenocarcinoma","volume":"79","author":"Huang","year":"2024","journal-title":"Clin Radiol"},{"key":"B11","doi-asserted-by":"publisher","first-page":"11085","DOI":"10.1038\/s41598-024-60781-5","article-title":"Prediction of treatment response after stereotactic radiosurgery of brain metastasis using deep learning and radiomics on longitudinal MRI data","volume":"14","author":"Cho","year":"2024","journal-title":"Sci Rep"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1858","DOI":"10.3390\/cancers14081858","article-title":"Measurement of perfusion heterogeneity within tumor habitats on magnetic resonance imaging and its association with prognosis in breast cancer patients","volume":"14","author":"Cho","year":"2022","journal-title":"Cancers (Basel)"},{"key":"B13","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1148\/radiol.13122697","article-title":"Quantitative imaging in cancer evolution and ecology","volume":"269","author":"Gatenby","year":"2013","journal-title":"Radiology."},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2025.02.009","article-title":"Multi-parametric MRI habitat radiomics based on interpretable machine learning for preoperative assessment of microsatellite instability in rectal cancer","volume":"32","author":"Wang","year":"2025","journal-title":"Acad Radiol"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1158\/1078-0432.CCR-14-0990","article-title":"Imaging intratumor heterogeneity: role in therapy response, resistance, and clinical outcome","volume":"21","author":"O'Connor","year":"2015","journal-title":"Clin Cancer Res"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1177\/08465371241231573","article-title":"Do habitat MRI and fractal analysis help distinguish triple-negative breast cancer from non-triple-negative breast carcinoma","volume":"75","author":"Xu","year":"2024","journal-title":"Can Assoc Radiol J"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-023-10149-6","article-title":"Preoperative vascular heterogeneity based on dynamic susceptibility contrast MRI in predicting spatial pattern of locally recurrent high-grade gliomas","volume":"34","author":"Wang","year":"2024","journal-title":"Eur Radiol"},{"key":"B18","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1186\/s40644-024-00670-2","article-title":"Using tumor habitat-derived radiomic analysis during pretreatment (18)F-FDG PET for predicting KRAS\/NRAS\/BRAF mutations in colorectal cancer","volume":"24","author":"Zhao","year":"2024","journal-title":"Cancer Imaging."},{"key":"B19","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1186\/s12967-024-04904-6","article-title":"A novel sub-regional radiomics model to predict immunotherapy response in non-small cell lung carcinoma","volume":"22","author":"Peng","year":"2024","journal-title":"J Transl Med"},{"key":"B20","doi-asserted-by":"publisher","first-page":"106980","DOI":"10.1016\/j.oraloncology.2024.106980","article-title":"Tumor habitat-based MRI features assessing early response in locally advanced nasopharyngeal carcinoma","volume":"158","author":"Yuan","year":"2024","journal-title":"Oral Oncol"},{"key":"B21","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1007\/s00330-021-08204-1","article-title":"Tumor habitat analysis by magnetic resonance imaging distinguishes tumor progression from radiation necrosis in brain metastases after stereotactic radiosurgery","volume":"32","author":"Lee","year":"2022","journal-title":"Eur Radiol"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2010.2046908","article-title":"N4ITK: improved N3 bias correction","volume":"29","author":"Tustison","year":"2010","journal-title":"IEEE Trans Med Imaging."},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-013-0329-y","article-title":"Subspace K-means clustering","volume":"45","author":"Timmerman","year":"2013","journal-title":"Behav Res Methods"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1364\/AO.448043","article-title":"Modulation format identification using the Calinski-Harabasz index","volume":"61","author":"Zhang","year":"2022","journal-title":"Appl Opt."},{"key":"B25","doi-asserted-by":"publisher","first-page":"597","DOI":"10.2147\/CIA.S406735","article-title":"Lasso-based machine learning algorithm for predicting postoperative lung complications in elderly: A single-center retrospective study from China","volume":"18","author":"Liu","year":"2023","journal-title":"Clin Interv Aging."},{"key":"B26","doi-asserted-by":"publisher","first-page":"e0274522","DOI":"10.1371\/journal.pone.0274522","article-title":"Data augmentation based on multiple oversampling fusion for medical image segmentation","volume":"17","author":"Wu","year":"2022","journal-title":"PloS One"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13678","article-title":"Machine and deep learning methods for radiomics","volume":"47","author":"Avanzo","year":"2020","journal-title":"Med Phys"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2025.1559398","article-title":"Habitat-based radiomics for preoperative differentiation between early-stage serous borderline ovarian tumors and Malignant ovarian tumors","volume":"15","author":"Yu","year":"2025","journal-title":"Front Oncol"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-018-5463-6","article-title":"Classifying brain metastases by their primary site of origin using a radiomics approach based on texture analysis: a feasibility study","volume":"28","author":"Ortiz-Ram\u00f3n","year":"2018","journal-title":"Eur Radiol"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17610","article-title":"Habitat-based MRI radiomics to predict the origin of brain metastasis","volume":"52","author":"Sun","year":"2025","journal-title":"Med Phys"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2022.04.008","article-title":"Differentiation of lung metastases originated from different primary tumors using radiomics features based on CT imaging","volume":"30","author":"Shang","year":"2023","journal-title":"Acad Radiol"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1007\/s10334-017-0653-9","article-title":"2D and 3D texture analysis to differentiate brain metastases on MR images: proceed with caution","volume":"31","author":"B\u00e9resov\u00e1","year":"2018","journal-title":"Magma."},{"key":"B33","doi-asserted-by":"publisher","first-page":"5147085","DOI":"10.1155\/2022\/5147085","article-title":"Differentiating primary tumors for brain metastasis with integrated radiomics from multiple imaging modalities","volume":"2022","author":"Cao","year":"2022","journal-title":"Dis Markers."},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2007.04.009","article-title":"Cost-sensitive boosting for classification of imbalanced data","volume":"40","author":"Sun","year":"2007","journal-title":"Pattern Recognit"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.3348\/kjr.2022.0492","article-title":"Tumor habitat analysis using longitudinal physiological MRI to predict tumor recurrence after stereotactic radiosurgery for brain metastasis","volume":"24","author":"Lee","year":"2023","journal-title":"Korean J Radiol"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.21037\/qims-20-1182","article-title":"A subregion-based positron emission tomography\/computed tomography (PET\/CT) radiomics model for the classification of non-small cell lung cancer histopathological subtypes","volume":"11","author":"Shen","year":"2021","journal-title":"Quant Imaging Med Surg"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2025.1504132","article-title":"Tumour habitat-based radiomics analysis enhances the ability to predict prostate cancer aggressiveness with biparametric MRI-derived features","volume":"15","author":"Li","year":"2025","journal-title":"Front Oncol"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.62347\/DDRR4923","article-title":"Subregion-specific (18)F-FDG PET-CT radiomics for the pre-treatment prediction of EGFR mutation status in solid lung adenocarcinoma","volume":"14","author":"Wang","year":"2024","journal-title":"Am J Nucl Med Mol Imaging."},{"key":"B39","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.compbiomed.2018.02.004","article-title":"Automatic detection and segmentation of brain metastases on multimodal MR images with a deep convolutional neural network","volume":"95","author":"Charron","year":"2018","journal-title":"Comput Biol Med"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.28276","article-title":"Radiomic-based MRI for classification of solitary brain metastases subtypes from primary lymphoma of the central nervous system","volume":"57","author":"Zhao","year":"2023","journal-title":"J Magn Reson Imaging."},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1001\/jamadermatol.2022.0160","article-title":"Global Burden of Cutaneous Melanoma in 2020 and Projections to 2040","volume":"158","author":"Arnold","year":"2020","journal-title":"JAMA Dermatol."}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1714315\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T05:14:42Z","timestamp":1764652482000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1714315\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,2]]},"references-count":41,"alternative-id":["10.3389\/fonc.2025.1714315"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2025.1714315","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,2]]},"article-number":"1714315"}}