{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T05:18:18Z","timestamp":1787635098829,"version":"build-2736575974"},"reference-count":30,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T00:00:00Z","timestamp":1787356800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001831","name":"Delft University of Technology","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001831","id-type":"DOI","asserted-by":"crossref"}]},{"id":[{"id":"https:\/\/ror.org\/02e2c7k09","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Clin. Med.","JCM"],"abstract":"<jats:p>Background: Breast cancer brain metastases (BCBMs) exhibit notable receptor discordance between primary tumors and metastases, yet obtaining intracranial biopsies is rarely practical. We created an interpretable deep learning radiogenomic model to predict estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) status from MRI scans in BCBM cases. Methods: A total of 241 post-contrast T1-weighted MRIs from 142 patients were analyzed. We developed a mask-free 3D Residual Neural Network (ResNet) ensemble trained directly on cropped, bias-corrected brain images, with comprehensive 3D geometric and intensity augmentations. The model was optimized in a multi-label setting using Asymmetric Focal Loss. Hyperparameters were fine-tuned via Bayesian optimization, and class probabilities were calibrated. Additionally, Integrated Gradients (IG) offered voxel-level saliency maps. Results: Our ResNet ensemble model achieved a micro-averaged AUROC of 0.74 and a macro-averaged AUROC of 0.67. Receptor-specific AUROCs were 0.57 for ER, 0.79 for PR, and 0.64 for HER2. The F1-scores were 0.56, 0.62, and 0.88 for ER, PR, and HER2, respectively. The held-out cohort contained only four HER2-negative patients, so threshold-dependent HER2 metrics are strongly prevalence-driven and AUROC is the more appropriate summary. Qualitatively inspected saliency maps were concentrated on enhancing metastases with limited background attribution. Conclusions: This proof-of-concept study shows that a segmentation-free, interpretable 3D Convolutional Neural Network (CNN) can be trained to capture receptor-associated patterns in post-contrast T1-weighted MRI of BCBMs. Accuracy was modest relative to published radiomics models, and the mask-free, single-sequence design is offered as a methodological contribution rather than a performance gain. These findings are preliminary, do not establish clinical utility, and require validation in larger, multi-center cohorts.<\/jats:p>","DOI":"10.3390\/jcm15176501","type":"journal-article","created":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T11:47:19Z","timestamp":1787572039000},"page":"6501","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Saliency-Curated Deep Learning for Predicting Receptor Status in Breast Cancer Brain Metastases"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6857-3927","authenticated-orcid":false,"given":"Rafail C.","family":"Christodoulou","sequence":"first","affiliation":[{"name":"Department of Radiology, Stanford University School of Medicine, Stanford, CA 94305, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5100-5802","authenticated-orcid":false,"given":"Giorgos","family":"Christofi","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, 2628 CD Delft, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Constantinos","family":"Theofylaktou","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, National Technical University of Athens, 15772 Zografou, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rafael","family":"Pitsillos","sequence":"additional","affiliation":[{"name":"Bioinformatics Department, Cyprus Institute of Neurology and Genetics, Nicosia 2371, Cyprus"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7779-8589","authenticated-orcid":false,"given":"Iliana","family":"Aristokleous","sequence":"additional","affiliation":[{"name":"Department of Surgery and Urology, Uppsala University Hospital, 75237 Uppsala, Sweden"},{"name":"Endocrine and Breast Surgery, Department of Surgical Sciences, Uppsala University, 75105 Uppsala, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elena E.","family":"Solomou","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine-Hematology, University of Patras Medical School, 26500 Rion, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evros","family":"Vassiliou","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences, Kean University, Union, NJ 07083, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michalis F.","family":"Georgiou","sequence":"additional","affiliation":[{"name":"Department of Radiology, Division of Nuclear Medicine, University of Miami, Miami, FL 33136, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1348","DOI":"10.1200\/OP.23.00794","article-title":"Breast Cancer Brain Metastasis: A Comprehensive Review","volume":"20","author":"Raghavendra","year":"2024","journal-title":"JCO Oncol. Pract."},{"key":"ref_2","doi-asserted-by":"crossref","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."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"3959","DOI":"10.1200\/JCO.21.01392","article-title":"Endocrine Treatment and Targeted Therapy for Hormone Receptor\u2013Positive, Human Epidermal Growth Factor Receptor 2\u2013Negative Metastatic Breast Cancer: ASCO Guideline Update","volume":"39","author":"Burstein","year":"2021","journal-title":"J. Clin. Oncol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"894","DOI":"10.1093\/neuonc\/noaa285","article-title":"The incidence of brain metastases among patients with metastatic breast cancer: A systematic review and meta-analysis","volume":"23","author":"Kuksis","year":"2021","journal-title":"Neuro-Oncology"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"466","DOI":"10.1634\/theoncologist.2014-0107","article-title":"Breast Cancer with Brain Metastases: Clinicopathologic Features, Survival, and Paired Biomarker Analysis","volume":"20","author":"Shen","year":"2015","journal-title":"Oncologist"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"942","DOI":"10.1093\/annonc\/mdp407","article-title":"Breast cancer brain metastases: Differences in survival depending on biological subtype, RPA RTOG prognostic class and systemic treatment after whole-brain radiotherapy (WBRT)","volume":"21","author":"Murawska","year":"2010","journal-title":"Ann. Oncol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"131","DOI":"10.3747\/co.2007.129","article-title":"Management of Single Brain Metastasis: A Practice Guideline","volume":"14","author":"Mintz","year":"2007","journal-title":"Curr. Oncol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"4387","DOI":"10.1038\/s41598-022-08366-y","article-title":"A preliminary study of the diagnostic efficacy and safety of the novel boring biopsy for brain lesions","volume":"12","author":"Ogiwara","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1038\/s41416-021-01328-7","article-title":"Breast cancer as an example of tumour heterogeneity and tumour cell plasticity during malignant progression","volume":"125","author":"Tiede","year":"2021","journal-title":"Br. J. Cancer"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"vdab010","DOI":"10.1093\/noajnl\/vdab010","article-title":"Systematic review and meta-analysis of breast cancer brain metastasis and primary tumor receptor expression discordance","volume":"3","author":"Kotecha","year":"2021","journal-title":"Neuro-Oncol. Adv."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Luo, X., Xie, H., Yang, Y., Zhang, C., Zhang, Y., Li, Y., Yang, Q., Wang, D., Luo, Y., and Mai, Z. (2022). Radiomic Signatures for Predicting Receptor Status in Breast Cancer Brain Metastases. Front. Oncol., 12.","DOI":"10.3389\/fonc.2022.878388"},{"key":"ref_12","doi-asserted-by":"crossref","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":"ref_13","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1148\/radiol.2015151169","article-title":"Radiomics: Images Are More than Pictures, They Are Data","volume":"278","author":"Gillies","year":"2016","journal-title":"Radiology"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Christodoulou, R.C., Pitsillos, R., Papageorgiou, P.S., Petrou, V., Vamvouras, G., Rivera, L., Papageorgiou, S.G., Solomou, E.E., and Georgiou, M.F. (2025). Artificial Intelligence in Glioma Diagnosis: A Narrative Review of Radiomics and Deep Learning for Tumor Classification and Molecular Profiling Across Positron Emission Tomography and Magnetic Resonance Imaging. Eng, 6.","DOI":"10.3390\/eng6100262"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Choi, S., Lee, Y., Lee, M., Byon, J.H., and Choi, E.J. (2025). Deep Learning-Based Recurrence Prediction in HER2-Low Breast Cancer: Comparison of MRI-Alone, Clinicopathologic-Alone, and Combined Models. Diagnostics, 15.","DOI":"10.3390\/diagnostics15151895"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Taha, B., Wu, D., Sabal, L., Kollitz, M., Venteicher, A., and Watanabe, Y. (2026, June 25). MRI Dataset of Metastatic Breast Cancer to the Brain with Expert-Reviewed Segmentations and Tumor-derived Radiomic Features (BCBM-RadioGenomics) (Version 1) [Dataset]. The Cancer Imaging Archive. Available online: https:\/\/www.cancerimagingarchive.net\/collection\/BCBM-RadioGenomics\/.","DOI":"10.1038\/s41597-025-06066-6"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Heitkamp, A., Madesta, F., Amberg, S., Wahaj, S., Schr\u00f6der, T., Bechstein, M., Meyer, L., Broocks, G., Hanning, U., and Gauer, T. (2023). Discordant and Converting Receptor Expressions in Brain Metastases from Breast Cancer: MRI-Based Non-Invasive Receptor Status Tracking. Cancers, 15.","DOI":"10.3390\/cancers15112880"},{"key":"ref_18","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019). PyTorch: An Imperative Style, High-Performance Deep Learning Library. arXiv."},{"key":"ref_19","unstructured":"Simard, P.Y., Steinkraus, D., and Platt, J.C. (2003). Best practices for convolutional neural networks applied to visual document analysis. Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings. Edinburgh, UK, IEEE. Available online: http:\/\/ieeexplore.ieee.org\/document\/1227801\/."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, IEEE. Available online: http:\/\/ieeexplore.ieee.org\/document\/7780459\/.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_21","unstructured":"Lin, M., Chen, Q., and Yan, S. (2014). Network In Network. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Ridnik, T., Ben-Baruch, E., Zamir, N., Noy, A., Friedman, I., Protter, M., and Zelnik-Manor, L. (2021). Asymmetric Loss For Multi-Label Classification. 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada, IEEE. Available online: https:\/\/ieeexplore.ieee.org\/document\/9710171\/.","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"ref_23","unstructured":"Loshchilov, I., and Hutter, F. (2019). Decoupled Weight Decay Regularization. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M. (2019). Optuna: A Next-generation Hyperparameter Optimization Framework. arXiv.","DOI":"10.1145\/3292500.3330701"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1002\/bimj.200710415","article-title":"Youden Index and Optimal Cut--Point Estimated from Observations Affected by a Lower Limit of Detection","volume":"50","author":"Ruopp","year":"2008","journal-title":"Biom. J."},{"key":"ref_26","unstructured":"Simonyan, K., Vedaldi, A., and Zisserman, A. (2014). Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Niculescu-Mizil, A., and Caruana, R. (2005). Predicting good probabilities with supervised learning. Proceedings of the 22nd International Conference on Machine Learning\u2014ICML \u201905, Bonn, Germany, ACM Press. Available online: http:\/\/portal.acm.org\/citation.cfm?doid=1102351.1102430.","DOI":"10.1145\/1102351.1102430"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Hou, Y., Nitta, H., and Li, Z. (2023). HER2 Intratumoral Heterogeneity in Breast Cancer, an Evolving Concept. Cancers, 15.","DOI":"10.3390\/cancers15102664"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Guliyev, M., G\u00fcren, A.K., \u00d6zge, E., \u00c7olak, R., Majidova, N., Alkan \u015een, G., Safarov, S., G\u00fcnalt\u0131l\u0131, M., Fidan, M.C., and G\u00fclt\u00fcrk, \u0130. (2025). The Impact of Progesterone Receptor Status on Survival Outcomes in Metastatic Breast Cancer Patients Treated with First-Line CDK4\/6 Inhibitors. Cancers, 17.","DOI":"10.3390\/cancers17040693"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"9947","DOI":"10.1038\/s41598-018-28315-y","article-title":"Apparent diffusion coefficient histogram in breast cancer brain metastases may predict their biological subtype and progression","volume":"8","author":"Ahn","year":"2018","journal-title":"Sci. Rep."}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/17\/6501\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T04:18:34Z","timestamp":1787631514000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/17\/6501"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,22]]},"references-count":30,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["jcm15176501"],"URL":"https:\/\/doi.org\/10.3390\/jcm15176501","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,22]]}}}