Radiogenomics analysis reveals the associations of dynamic contrast-enhanced-MRI features with gene expression characteristics, PAM50 subtypes, and prognosis of breast cancer

Wenlong Ming; Yanhui Zhu; Yunfei Bai; Wanjun Gu; Fuyu Li; Zixi Hu; Tiansong Xia; Zuolei Dai; Xiafei Yu; Huamei Li; Yu Gu; Shaoxun Yuan; Rongxin Zhang; Haitao Li; Wenyong Zhu; Jianing Ding; Xiao Sun; Yun Liu; Hongde Liu; Xiaoan Liu

doi:10.3389/fonc.2022.943326

Radiogenomics analysis reveals the associations of dynamic contrast-enhanced-MRI features with gene expression characteristics, PAM50 subtypes, and prognosis of breast cancer

Front Oncol. 2022 Jul 28:12:943326. doi: 10.3389/fonc.2022.943326. eCollection 2022.

Authors

Wenlong Ming¹, Yanhui Zhu², Yunfei Bai¹, Wanjun Gu^{1

3}, Fuyu Li¹, Zixi Hu¹, Tiansong Xia², Zuolei Dai⁴, Xiafei Yu², Huamei Li¹, Yu Gu¹, Shaoxun Yuan¹, Rongxin Zhang¹, Haitao Li¹, Wenyong Zhu¹, Jianing Ding¹, Xiao Sun¹, Yun Liu⁴, Hongde Liu¹, Xiaoan Liu²

Affiliations

¹ State Key Laboratory of Bioelectronics, School of Biological Science and Medical Engineering, Southeast University, Nanjing, China.
² Department of Breast Surgery, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China.
³ Collaborative Innovation Center of Jiangsu Province of Cancer Prevention and Treatment of Chinese Medicine, School of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine, Nanjing, China.
⁴ Department of Information, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China.

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-sequencing (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 with 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 the cell cycle pathway exhibited a 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 (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 (p-value < 0.0001).

Conclusions: 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.

Keywords: DCE-MRI; PAM50 subtypes; breast cancer; machine learning; radiogenomics; radiomics.