{"doi":"10.3390/diagnostics15101242","title":"Hybrid Deep Learning for Survival Prediction in Brain Metastases Using Multimodal MRI and Clinical Data","abstract":"<jats:p>Background: Survival prediction in patients with brain metastases remains a major clinical challenge, where timely and individualized prognostic estimates are critical for guiding treatment strategies and patient counseling. Methods: We propose a novel hybrid deep learning framework that integrates volumetric MRI-derived imaging biomarkers with structured clinical and demographic data to predict overall survival time. Our dataset includes 148 patients from three institutions, featuring expert-annotated segmentations of enhancing tumors, necrosis, and peritumoral edema. Two convolutional neural network backbones—ResNet-50 and EfficientNet-B0—were fused with fully connected layers processing tabular data. Models were trained using mean squared error loss and evaluated through stratified cross-validation and an independent held-out test set. Results: The hybrid model based on EfficientNet-B0 achieved state-of-the-art performance, attaining an R2 score of 0.970 and a mean absolute error of 3.05 days on the test set. Permutation feature importance highlighted edema-to-tumor ratio and enhancing tumor volume as the most informative predictors. Grad-CAM visualizations confirmed the model’s attention to anatomically and clinically relevant regions. Performance consistency across validation folds confirmed the framework’s robustness and generalizability. Conclusions: This study demonstrates that multimodal deep learning can deliver accurate, explainable, and clinically actionable survival predictions in brain metastases. The proposed framework offers a promising foundation for integration into real-world oncology workflows to support personalized prognosis and informed therapeutic decision-making.</jats:p>","journal":"Diagnostics","year":2025,"id":622373,"datarank":0.24141568686511508,"base_score":1.6094379124341003,"endowment":1.6094379124341003,"self_citation_contribution":0.24141568686511508,"citation_network_contribution":0.0,"self_endowment_contribution":0.24141568686511508,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":4,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1608032,"name":"Călin Gheorghe Buzea","orcid":"0000-0003-2791-3400","position":1,"is_corresponding":false},{"id":1608033,"name":"Diana-Ioana Boboc","orcid":"0009-0007-7650-7798","position":2,"is_corresponding":false},{"id":1608034,"name":"Mădălina-Raluca Ostafe","orcid":null,"position":3,"is_corresponding":false},{"id":1608035,"name":"Maricel Agop","orcid":null,"position":4,"is_corresponding":false},{"id":1608036,"name":"Lăcrămioara Ochiuz","orcid":"0000-0001-6447-0958","position":5,"is_corresponding":false},{"id":1608038,"name":"Ștefan Lucian Burlea","orcid":null,"position":6,"is_corresponding":false},{"id":1608039,"name":"Dragoș Ioan Rusu","orcid":"0000-0002-5485-0620","position":7,"is_corresponding":false},{"id":1608040,"name":"Laurențiu Bujor","orcid":null,"position":8,"is_corresponding":false},{"id":1608041,"name":"Dragoș Teodor Iancu","orcid":null,"position":9,"is_corresponding":false},{"id":1608042,"name":"Simona Ruxandra Volovăț","orcid":null,"position":10,"is_corresponding":false},{"id":1608031,"name":"Cristian Constantin Volovăț","orcid":null,"position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"Hybrid Deep Learning for Survival Prediction in Brain Metastases Using Multimodal MRI and Clinical Data","abstract":"<jats:p>Background: Survival prediction in patients with brain metastases remains a major clinical challenge, where timely and individualized prognostic estimates are critical for guiding treatment strategies and patient counseling. Methods: We propose a novel hybrid deep learning framework that integrates volumetric MRI-derived imaging biomarkers with structured clinical and demographic data to predict overall survival time. Our dataset includes 148 patients from three institutions, featuring expert-annotated segmentations of enhancing tumors, necrosis, and peritumoral edema. Two convolutional neural network backbones—ResNet-50 and EfficientNet-B0—were fused with fully connected layers processing tabular data. Models were trained using mean squared error loss and evaluated through stratified cross-validation and an independent held-out test set. Results: The hybrid model based on EfficientNet-B0 achieved state-of-the-art performance, attaining an R2 score of 0.970 and a mean absolute error of 3.05 days on the test set. Permutation feature importance highlighted edema-to-tumor ratio and enhancing tumor volume as the most informative predictors. Grad-CAM visualizations confirmed the model’s attention to anatomically and clinically relevant regions. Performance consistency across validation folds confirmed the framework’s robustness and generalizability. Conclusions: This study demonstrates that multimodal deep learning can deliver accurate, explainable, and clinically actionable survival predictions in brain metastases. The proposed framework offers a promising foundation for integration into real-world oncology workflows to support personalized prognosis and informed therapeutic decision-making.</jats:p>","is_dataset_classified":null,"base_score":1.6094379124341003,"endowment":1.6094379124341003,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"40428235","pmcid":null,"openalex_id":"https://openalex.org/W4410369028","authors":[],"funders":[],"total_grants":0,"fwci":3.1193,"citation_percentile":0.91468786,"influential_citations":0,"citation_trend":[{"year":2025,"count":3},{"year":2026,"count":1}],"oa_status":"gold","license":"cc-by","oa_locations":[{"url":"https://www.mdpi.com/2075-4418/15/10/1242/pdf?version=1747221193","host_type":"journal"},{"url":"https://www.mdpi.com/2075-4418/15/10/1242/pdf?version=1747221193","host_type":"publisher"},{"url":"https://www.mdpi.com/2075-4418/15/10/1242/pdf","host_type":"publisher"},{"url":"https://doi.org/10.3390/diagnostics15101242","host_type":"journal"},{"url":"https://pubmed.ncbi.nlm.nih.gov/40428235","host_type":"repository"},{"url":"https://doaj.org/article/18f758b2229d44659d727211c6412af1","host_type":"repository"},{"url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12109748","host_type":"repository"}],"fields_of_study":["Brain Metastases and Treatment","Radiomics and Machine Learning in Medical Imaging","Medical Imaging Techniques and Applications"],"mesh_terms":[],"keywords":["Multimodal therapy","Deep learning","Artificial intelligence","Medicine","Computer science","Internal medicine"],"sdg_mappings":[],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-08-03T19:21:19.300866Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}