{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T05:55:09Z","timestamp":1781502909953,"version":"3.54.1"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"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. Hum. Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Breast cancer brain metastases (BCBMs) represent a severe neurological complication affecting 10\u201320% of patients with metastatic breast cancer, with significant implications for treatment planning and prognosis. Accurate determination of hormone receptor (HR) status is critical for guiding personalized therapeutic strategies. However, traditional biopsy-based assessment is invasive, carries procedural risks, and may not capture the molecular heterogeneity of multiple metastatic lesions. Non-invasive methods for predicting HR status from brain MRI could transform clinical practice, yet existing approaches face three critical limitations: incomplete information utilization from single-modal features, ignored biological correlations among hormone receptors, and underexploited anatomical position information.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed a novel multi-modal deep learning (DL) framework leveraging the BCBM-RadioGenomics dataset from The Cancer Imaging Archive (TCIA), comprising 268 MRI studies from 165 patients with expert-validated tumor segmentations, 107 PyRadiomics-derived radiomic features, and clinical HR status. Our framework introduces three key methodological components: (1) a three-modal complementary fusion architecture integrating 3D DL features extracted from tumor regions of interest using a 3D ResNet, radiomic features, and anatomical position encoding representing tumor location through hemisphere and brain region one-hot encoding; (2) a multi-task collaborative learning framework with hard parameter sharing to simultaneously predict ER, PR, and HER2 status, employing a weighted loss function to address class imbalance; and (3) a lesion-level sampling strategy to maximize data utilization while preventing data leakage.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed model achieved area under the curve (ROC-AUC) values of 0.8763 \u00b1 0.0393 for HER2, 0.8621 \u00b1 0.0304 for ER, and 0.8993 \u00b1 0.0192 for PR prediction, outperforming traditional machine learning baselines. The multi-task learning framework demonstrated improvements for the challenging PR prediction task, while the three-modal fusion architecture consistently outperformed single-modal approaches across all tasks.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>This study demonstrates the feasibility and clinical potential of non-invasive molecular profiling of BCBMs using a multi-modal DL approach. These findings might offer a promising tool for treatment planning and patient management, reducing the need for invasive biopsies while enabling more accurate and comprehensive molecular characterization of brain metastases.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnhum.2026.1858163","type":"journal-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T05:33:55Z","timestamp":1781501635000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Prediction of hormone receptor status in breast cancer brain metastases using an MRI-based multimodal deep learning framework"],"prefix":"10.3389","volume":"20","author":[{"given":"Qiqi","family":"Sun","sequence":"first","affiliation":[{"name":"The Third Affiliated Hospital of Beijing University of Chinese Medicine","place":["Beijing, China"]},{"name":"School of Clinical Medicine, Beijing University of Chinese Medicine","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiong","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Third Affiliated Hospital of Beijing University of Chinese Medicine","place":["Beijing, China"]},{"name":"School of Clinical Medicine, Beijing University of Chinese Medicine","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yabo","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Beijing University of Posts and Telecommunications","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohua","family":"Pei","sequence":"additional","affiliation":[{"name":"The Third Affiliated Hospital of Beijing University of Chinese Medicine","place":["Beijing, China"]},{"name":"School of Clinical Medicine, Beijing University of Chinese Medicine","place":["Beijing, China"]},{"name":"Xiamen Hospital of Traditional Chinese Medicine","place":["Xiamen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"4644","DOI":"10.1038\/ncomms5644","article-title":"Corrigendum: decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach","volume":"5","author":"Aerts","year":"2014","journal-title":"Nat. Commun"},{"key":"B2","doi-asserted-by":"publisher","first-page":"2645","DOI":"10.3390\/cancers13112645","article-title":"Molecular profiles of brain metastases: a focus on heterogeneity","volume":"13","author":"Ali","year":"2021","journal-title":"Cancers"},{"key":"B3","doi-asserted-by":"publisher","first-page":"49","DOI":"10.4274\/mirt.galenos.2022.59140","article-title":"Can radiomics analyses in 18f-fdg pet\/ct images of primary breast carcinoma predict hormone receptor status?","volume":"31","author":"Araz","year":"2022","journal-title":"Mol. Imaging Radionucl. Ther"},{"key":"B4","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1038\/s41416-020-01175-y","article-title":"Treatment strategies for breast cancer brain metastases","volume":"124","author":"Bailleux","year":"2021","journal-title":"Br. J. Cancer"},{"key":"B5","doi-asserted-by":"publisher","first-page":"127","DOI":"10.3322\/caac.21552","article-title":"Artificial intelligence in cancer imaging: clinical challenges and applications","volume":"69","author":"Bi","year":"2019","journal-title":"CA Cancer J. Clin"},{"key":"B6","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1007379606734","article-title":"Multitask learning","volume":"28","author":"Caruana","year":"1997","journal-title":"Mach. Learn"},{"key":"B7","doi-asserted-by":"publisher","first-page":"107080","DOI":"10.1016\/j.compbiomed.2023.107080","article-title":"Multi-task banded regression model: a novel individual survival analysis model for breast cancer","volume":"162","author":"Chen","year":"2023","journal-title":"Comput. Biol. Med"},{"key":"B8","doi-asserted-by":"publisher","first-page":"2388","DOI":"10.1016\/S0140-6736(18)31645-3","article-title":"Deep learning algorithms for detection of critical findings in head ct scans: a retrospective study","volume":"392","author":"Chilamkurthy","year":"2018","journal-title":"Lancet"},{"key":"B9","doi-asserted-by":"publisher","first-page":"573","DOI":"10.3349\/ymj.2023.0047","article-title":"A radiomics-based model for potentially more accurate identification of subtypes of breast cancer brain metastases","volume":"64","author":"Cho","year":"2023","journal-title":"Yonsei Med. J"},{"key":"B10","doi-asserted-by":"publisher","first-page":"e232780","DOI":"10.1148\/radiol.232780","article-title":"Asymmirai: interpretable mammography-based deep learning model for 1-5-year breast cancer risk prediction","volume":"310","author":"Donnelly","year":"2024","journal-title":"Radiology"},{"key":"B11","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1038\/s41591-018-0316-z","article-title":"A guide to deep learning in healthcare","volume":"25","author":"Esteva","year":"2019","journal-title":"Nat. Med"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1482020","DOI":"10.3389\/fimmu.2024.1482020","article-title":"Predicting axillary lymph node metastasis in breast cancer using a multimodal radiomics and deep learning model","volume":"15","author":"Guo","year":"2024","journal-title":"Front. Immunol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"6546","DOI":"10.1109\/CVPR.2018.00685","article-title":"\u201cCan spatiotemporal 3d cnns retrace the history of 2d cnns and imagenet?,\u201d","author":"Hara","year":"2018","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2103.10504","article-title":"UNETR: transformers for 3D medical image segmentation","author":"Hatamizadeh","year":"2021","journal-title":"arXiv"},{"key":"B15","doi-asserted-by":"publisher","first-page":"873","DOI":"10.1093\/neuonc\/nov301","article-title":"A prospective trial of dynamic contrast-enhanced mri perfusion and fluorine-18 fdg pet-ct in differentiating brain tumor progression from radiation injury after cranial irradiation","volume":"18","author":"Hatzoglou","year":"2016","journal-title":"Neuro-oncology"},{"key":"B16","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","article-title":"\u201cDeep residual learning for image recognition,\u201d","author":"He","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.3390\/cancers15112880","article-title":"Discordant and converting receptor expressions in brain metastases from breast cancer: Mri-based non-invasive receptor status tracking","author":"Heitkamp","year":"2023","journal-title":"Cancers"},{"key":"B18","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1186\/s13244-024-01810-9","article-title":"Explainable breast cancer molecular expression prediction using multi-task deep-learning based on 3d whole breast ultrasound","volume":"15","author":"Huang","year":"2024","journal-title":"Insights Imaging"},{"key":"B19","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1038\/s43018-020-0087-6","article-title":"Pan-cancer image-based detection of clinically actionable genetic alterations","volume":"1","author":"Kather","year":"2020","journal-title":"Nat. Cancer"},{"key":"B20","doi-asserted-by":"publisher","first-page":"e0188542","DOI":"10.1371\/journal.pone.0188542","article-title":"Subtypes of breast cancer show different spatial distributions of brain metastases","volume":"12","author":"Kyeong","year":"2017","journal-title":"PLoS ONE"},{"key":"B21","doi-asserted-by":"publisher","first-page":"3608","DOI":"10.1200\/JCO.2004.01.175","article-title":"Cns metastases in breast cancer","volume":"22","author":"Lin","year":"2004","journal-title":"J. Clin. Oncol"},{"key":"B22","doi-asserted-by":"publisher","first-page":"2980","DOI":"10.1109\/ICCV.2017.324","article-title":"\u201cFocal loss for dense object detection,\u201d","author":"Lin","year":"2017","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"B23","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med. Image Anal"},{"key":"B24","doi-asserted-by":"publisher","first-page":"9628","DOI":"10.5555\/3327546.3327630","article-title":"An intriguing failing of convolutional neural networks and the coordconv solution","volume":"31","author":"Liu","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B25","doi-asserted-by":"publisher","first-page":"102035","DOI":"10.1016\/j.media.2021.102035","article-title":"Loss odyssey in medical image segmentation","volume":"71","author":"Ma","year":"2021","journal-title":"Med. Image Anal"},{"key":"B26","doi-asserted-by":"publisher","first-page":"2170","DOI":"10.3390\/diagnostics15172170","article-title":"Enhanced breast cancer diagnosis using multimodal feature fusion with radiomics and transfer learning","volume":"15","author":"Maruf","year":"2025","journal-title":"Diagnostics"},{"key":"B27","doi-asserted-by":"publisher","first-page":"4786","DOI":"10.1158\/0008-5472.CAN-18-0125","article-title":"Lifex: a freeware for radiomic feature calculation in multimodality imaging to accelerate advances in the characterization of tumor heterogeneity","volume":"78","author":"Nioche","year":"2018","journal-title":"Cancer Res"},{"key":"B28","doi-asserted-by":"publisher","first-page":"774","DOI":"10.1186\/s12967-025-06617-w","article-title":"Attention-based multimodal deep learning for interpretable and generalizable prediction of pathological complete response in breast cancer","volume":"23","author":"Nishizawa","year":"2025","journal-title":"J. Transl. Med"},{"key":"B29","doi-asserted-by":"publisher","first-page":"732","DOI":"10.1148\/radiol.2018172171","article-title":"Precision medicine and radiogenomics in breast cancer: new approaches toward diagnosis and treatment","volume":"287","author":"Pinker","year":"2018","journal-title":"Radiology"},{"key":"B30","doi-asserted-by":"publisher","first-page":"666","DOI":"10.1001\/jamaoncol.2016.5630","article-title":"Intrinsic subtype switching and acquired erbb2\/her2 amplifications and mutations in breast cancer brain metastases","volume":"3","author":"Priedigkeit","year":"2017","journal-title":"JAMA Oncol"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.05098","article-title":"An overview of multi-task learning in deep neural networks","author":"Ruder","year":"2017","journal-title":"arXiv"},{"key":"B32","doi-asserted-by":"publisher","first-page":"8894","DOI":"10.1088\/1361-6560\/aa93d4","article-title":"Multi-task transfer learning deep convolutional neural network: application to computer-aided diagnosis of breast cancer on mammograms","volume":"62","author":"Samala","year":"2017","journal-title":"Phys. Med. Biol"},{"key":"B33","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1093\/jnci\/djx273","article-title":"Receptor conversion in distant breast cancer metastases: a systematic review and meta-analysis","volume":"110","author":"Schrijver","year":"2018","journal-title":"J. Natl. Cancer Inst"},{"key":"B34","doi-asserted-by":"publisher","first-page":"102802","DOI":"10.1016\/j.media.2023.102802","article-title":"Transformers in medical imaging: a survey","volume":"88","author":"Shamshad","year":"2023","journal-title":"Med. Image Anal"},{"key":"B35","doi-asserted-by":"publisher","first-page":"209","DOI":"10.3322\/caac.21660","article-title":"Global cancer statistics 2020: globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA Cancer J. Clin"},{"key":"B36","doi-asserted-by":"publisher","first-page":"4489","DOI":"10.1109\/ICCV.2015.510","article-title":"\u201cLearning spatiotemporal features with 3d convolutional networks,\u201d","author":"Tran","year":"2015","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"B37","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/s13058-015-0665-1","article-title":"Breast cancer brain metastases: biology and new clinical perspectives","volume":"18","author":"Witzel","year":"2016","journal-title":"Breast Cancer Res"}],"container-title":["Frontiers in Human Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnhum.2026.1858163\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T05:33:56Z","timestamp":1781501636000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnhum.2026.1858163\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":37,"alternative-id":["10.3389\/fnhum.2026.1858163"],"URL":"https:\/\/doi.org\/10.3389\/fnhum.2026.1858163","relation":{},"ISSN":["1662-5161"],"issn-type":[{"value":"1662-5161","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,15]]},"article-number":"1858163"}}