AUTHOR=Ming Wenlong , Zhu Yanhui , Bai Yunfei , Gu Wanjun , Li Fuyu , Hu Zixi , Xia Tiansong , Dai Zuolei , Yu Xiafei , Li Huamei , Gu Yu , Yuan Shaoxun , Zhang Rongxin , Li Haitao , Zhu Wenyong , Ding Jianing , Sun Xiao , Liu Yun , Liu Hongde , Liu Xiaoan TITLE=Radiogenomics analysis reveals the associations of dynamic contrast-enhanced–MRI features with gene expression characteristics, PAM50 subtypes, and prognosis of breast cancer JOURNAL=Frontiers in Oncology VOLUME=Volume 12 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.943326 DOI=10.3389/fonc.2022.943326 ISSN=2234-943X ABSTRACT=Background: To investigate reliable associations between dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) features and gene expression characteristics in breast cancer (BC), and to develop and validate classifiers for predicting PAM50 subtypes and prognosis from DCE-MRI non-invasively. Methods: Two radiogenomics cohorts with paired DCE-MRI and RNA-seq data were collected from local and public databases, and divided into discovery (n =174) and validation cohorts (n = 72). Six external datasets (n = 1,443) were used for prognostic validation. Spatial-temporal features of DCE-MRI were extracted, normalized properly and associated to gene expression to identify the imaging features that can indicate subtypes and prognosis. Results: Expression of genes including RBP4, MYBL2, and LINC00993 correlated significantly with DCE-MRI features (q-value < 0.05). Importantly, genes in cell cycle pathway exhibited significant association with imaging features (P-value < 0.001). With eight imaging-associated genes (CHEK1, TTK, CDC45, BUB1B, PLK1, E2F1, CDC20 and CDC25A), we developed a radiogenomics prognostic signature that can distinguish BC outcomes in multiple datasets well. High expression of the signature indicated a poor prognosis (P values < 0.01). Based on DCE-MRI features, we established classifiers to predict BC clinical receptors, PAM50 subtypes and prognostic gene sets. The imaging-based machine learning classifiers performed well in the independent dataset (AUCs of 0.8361, 0.809, 0.7742, and 0.7277 for ER, HER2-Enriched, basal-like and the obtained radiogenomics signature). Furthermore, we developed a prognostic model directly using DCE-MRI features (P-value < 0.0001). Conclusions: Our results identified the DCE-MRI features that robust associated with the gene expression in BC, and displayed the possibility of using the features to predict clinical receptors and PAM50 subtypes, and to indicate BC prognosis.