{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["15(1)"],"submitter":["Gao Y"],"pubmed_abstract":["Multi-modal image analysis using deep learning (DL) lays the foundation for neoadjuvant treatment (NAT) response monitoring. However, existing methods prioritize extracting multi-modal features to enhance predictive performance, with limited consideration on real-world clinical applicability, particularly in longitudinal NAT scenarios with multi-modal data. Here, we propose the Multi-modal Response Prediction (MRP) system, designed to mimic real-world physician assessments of NAT responses in breast cancer. To enhance feasibility, MRP integrates cross-modal knowledge mining and temporal information embedding strategy to handle missing modalities and remain less affected by different NAT settings. We validated MRP through multi-center studies and multinational reader studies. MRP exhibited "],"journal":["Nature communications"],"pagination":["9613"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11544255"],"repository":["biostudies-literature"],"pubmed_title":["An explainable longitudinal multi-modal fusion model for predicting neoadjuvant therapy response in women with breast cancer."],"pmcid":["PMC11544255"],"pubmed_authors":["Kok M","Han L","Zhou HY","He M","Mann R","Longo V","Weir A","van Duijnhoven FH","Li X","Liu Z","Ventura-Diaz S","Zhang T","Horlings HM","Gao Y","Tan T","Wang X","Beets-Tan R","Teuwen J","Xu Z","D'Angelo A"],"additional_accession":[]},"is_claimable":false,"name":"An explainable longitudinal multi-modal fusion model for predicting neoadjuvant therapy response in women with breast cancer.","description":"Multi-modal image analysis using deep learning (DL) lays the foundation for neoadjuvant treatment (NAT) response monitoring. However, existing methods prioritize extracting multi-modal features to enhance predictive performance, with limited consideration on real-world clinical applicability, particularly in longitudinal NAT scenarios with multi-modal data. Here, we propose the Multi-modal Response Prediction (MRP) system, designed to mimic real-world physician assessments of NAT responses in breast cancer. To enhance feasibility, MRP integrates cross-modal knowledge mining and temporal information embedding strategy to handle missing modalities and remain less affected by different NAT settings. We validated MRP through multi-center studies and multinational reader studies. MRP exhibited ","dates":{"release":"2024-01-01T00:00:00Z","publication":"2024 Nov","modification":"2026-07-16T19:52:15.496Z","creation":"2025-04-06T02:51:45.381Z"},"accession":"S-EPMC11544255","cross_references":{"pubmed":["39511143"],"doi":["10.1038/s41467-024-53450-8"]}}