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=12

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=<sec><title>Background</title><p>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.</p></sec><sec><title>Methods</title><p>Two radiogenomics cohorts with paired DCE-MRI and RNA-sequencing (RNA-seq) data were collected from local and public databases and divided into discovery (<italic>n</italic> = 174) and validation cohorts (<italic>n</italic> = 72). Six external datasets (<italic>n</italic> = 1,443) were used for prognostic validation. Spatial–temporal features of DCE-MRI were extracted, normalized properly, and associated with gene expression to identify the imaging features that can indicate subtypes and prognosis.</p></sec><sec><title>Results</title><p>Expression of genes including RBP4, MYBL2, and LINC00993 correlated significantly with DCE-MRI features (q-value &lt; 0.05). Importantly, genes in the cell cycle pathway exhibited a significant association with imaging features (<italic>p</italic>-value &lt; 0.001). With eight imaging-associated genes (<italic>CHEK1</italic>, <italic>TTK</italic>, <italic>CDC45</italic>, <italic>BUB1B</italic>, <italic>PLK1</italic>, <italic>E2F1</italic>, <italic>CDC20</italic>, and <italic>CDC25A</italic>), we developed a radiogenomics prognostic signature that can distinguish BC outcomes in multiple datasets well. High expression of the signature indicated a poor prognosis (<italic>p</italic>-values &lt; 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 (areas under the receiver operating characteristic curve (AUCs) of 0.8361, 0.809, 0.7742, and 0.7277 for estrogen receptor (ER), human epidermal growth factor receptor 2 (HER2)-enriched, basal-like, and obtained radiogenomics signature). Furthermore, we developed a prognostic model directly using DCE-MRI features (<italic>p</italic>-value &lt; 0.0001).</p></sec><sec><title>Conclusions</title><p>Our results identified the DCE-MRI features that are robust and 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.</p></sec>