Oops, you're using an old version of your browser so some of the features on this page may not be displaying properly.

MINIMAL Requirements: Google Chrome 24+Mozilla Firefox 20+Internet Explorer 11Opera 15–18Apple Safari 7SeaMonkey 2.15-2.23

ePoster Display

133P - Magnetic resonance imaging radiomics predicts high and low recurrence risk and is associated with LncRNAs in early-stage invasive breast cancer


16 Sep 2021


ePoster Display


Tumour Site

Breast Cancer


Wei Ren


Annals of Oncology (2021) 32 (suppl_5): S407-S446. 10.1016/annonc/annonc687


W. Ren1, Y. Yu1, Z. He1, L. Mao1, Y. Chen2, W. Ouyang1, Y. Tan1, C. Li1, K. Chen1, J. Ouyang3, Q. Hu4, C. Xie5, H. Yao1

Author affiliations

  • 1 Oncology, 2nd Affiliated Hospital/Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University, 510120 - Guangzhou/CN
  • 2 Oncology, The Third Affiliated Hospital of Sun Yat-sen University, 510000 - Guang Zhou/CN
  • 3 Breast Surgery, Tungwah Hospital of Sun Yat-sen University, Dongguan/CN
  • 4 Radiology, Shunde Hospital of Southern Medical University, Foshan/CN
  • 5 Imaging Diagnostic And Interventional Center, Sun Yat-sen University Cancer Center, 510000 - Guang Zhou/CN


Login to get immediate access to this content.

If you do not have an ESMO account, please create one for free.

Abstract 133P


There are no satisfying approaches to identify high- and low-risk recurrence patients with early-stage invasive breast cancer in current clinical practice. Several studies indicated that the MRI radiomic profile could predict recurrence risk, but the potential biological underpinning of MRI radiomics remains indistinct.


The key magnetic resonance imaging (MRI) radiomic features were extracted and selected in 799 patients with early-stage invasive breast cancer (training cohort). Then, the MRI-based radiomic signature for recurrence-free survival (RFS) prediction was developed and validated in the prospective validation (n=105) and external validation (n=180) cohorts. 96 of 799 patients were performed RNA-seq with the FFPE samples to obtain lncRNAs data. The key lncRNAs significantly associated with radiomics and RFS were selected by Spearman correlation analysis and univariable Cox proportional hazards regression model.


The MRI radiomics could identify high and low recurrence risk patients in the training and validation cohorts (all P < 0.05), and achieved high 1-, 2-, 3-year AUCs (0.97, 0.95, and 0.98) in the training cohort, the prospective validation cohort (AUCs of 0.86, 0.89, and 0.87), and the external validation cohort (AUCs of 0.93, 0.94, and 0.91), respectively. A total of 15 lncRNAs were identified to be correlated with the key radiomic features and RFS. The signature composed of 15 lncRNAs was found to be significantly associated with RFS (HR 0.014, 95% CI 0.001-0.115, P < 0.001), and achieved AUCs of 0.99 and 0.95 for 6-, 12-month RFS prediction. Furthermore, one of the lncRNAs (AP002989.1) was significantly correlated with radiomic features that changed greatly after neoadjuvant chemotherapy. The differentially expressed genes in AP002989.1 low and high expression groups were enriched in various metastasis-associated physiological processes, such as extracellular structure organization, and were involved in the PI3K-Akt signaling pathway.


This study presented that MRI radiomics could be conveniently used for individualized prediction of RFS, and indicated that radiomics is associated with lncRNAs in early-stage invasive breast cancer.

Clinical trial identification

Editorial acknowledgement

Legal entity responsible for the study

Sun Yat-sen Memorial Hospital of Sun Yat-sen University.


This study was supported by grant 2020ZX09201021 from the National Science and Technology Major Project, grant YXRGZN201902 from the Medical Artificial Intelligence Project of Sun Yat-Sen Memorial Hospital, grants 81572596, 81972471, and 82073408 from the National Natural Science Foundation of China, grant 2017A030313828 from the Natural Science Foundation of Guangdong Province, grant 201704020131 from the Guangzhou Science and Technology Major Program, grant 2017B030314026 from the Guangdong Science and Technology Department, grant 2018007 from the Sun Yat-Sen University Clinical Research 5010 Program, grant SYS-C-201801 from the Sun Yat-Sen Clinical Research Cultivating Program, grant A2020558 from the Guangdong Medical Science and Technology Program.


All authors have declared no conflicts of interest.

This site uses cookies. Some of these cookies are essential, while others help us improve your experience by providing insights into how the site is being used.

For more detailed information on the cookies we use, please check our Privacy Policy.

Customise settings
  • Necessary cookies enable core functionality. The website cannot function properly without these cookies, and you can only disable them by changing your browser preferences.