Breast cancer prognosis remains challenging due to tumor heterogeneity and the limited predictive power of conventional clinical models. Integrating imaging features with molecular data may improve individualized risk stratification and clinical decision-making.We developed a closed-loop prognostic model based on a macro-micro-macro radiogenomic framework that combines MRI-based radiomics with transcriptomic and proteomic data. A total of 788 radiomics-guided candidate genes were screened. Prognostic gene signatures were identified using multiple machine learning algorithms and validated in TCGA and GEO cohorts. We further analyzed immune infiltration, drug sensitivity, and gene enrichment profiles across risk groups. Causal relationships between gene expression and survival were assessed using Mendelian randomization. Hub gene expression was validated in patient plasma using ELISA, and Olink proteomics and radiomic information was conducted for biological association analysis.XGBoost-Cox prognostic model was constructed integrating 10 consensus genes identified by stepwise Cox regression and Elastic Net, achieving the concordance index 0.703 in GEO validation cohort. High-risk patients showed reduced immune activation, increased expression of pro-inflammatory cytokines, and worse survival. Among consensus genes, FIBCD1 was demonstrated as a hub gene with a significant causal association with survival. Its expression was significantly elevated in high-risk plasma samples, positively correlated with inflammatory proteins (e.g., OSM, and TNFSF14), and associated with MRI phenotype, including tumor sphericity and inverse difference normalized feature.Our findings establish a novel radiogenomic strategy that bridges MRI-derived imaging phenotypes with molecular mechanisms. FIBCD1 may serve as an immune-modulating prognostic biomarker linked to imaging characteristics, providing new insights into non-invasive breast cancer risk assessment and therapeutic targeting.© 2025. The Author(s).