Meeting Banner
Abstract #1714

Prediction molecular subtypes of Breast Cancer by MRI Radiomics

Shuangyan Sun1, Dingli Ye2, Changliang Yang3, Jianqing Sun4, and Jihong Zhao2

1Radiology, JiLin Cancer Hospital, ChangChun, China, 2Radiology, Jilin Cancer Hospital, ChangChun, China, 3Thoracic Oncology, Jilin Cancer Hospital, ChangChun, China, 4Philips Healthcare, shanghai, China

Breast cancer molecular subtypes are indicators of disease free and overall survival. This study aimed to investigate whether quantitative radiomic features extracted from MRI images are associated with molecular subtypes of breast cancer. 135 women diagnosed with invasive breast cancer were enrolled and divided into 3 groups as follow: triple-negative vs non–triple-negative, HER2-enriched vs non–HER2-enriched, and luminal (A + B) vs nonluminal. A machine learning scheme was employed for the classification. The mean AUC of the three models are 0.76, 0.85 and 0.73, respectively. There is a moderate association between tumour molecular biomarkers and radiomic features extracted from MRI images.

This abstract and the presentation materials are available to members only; a login is required.

Join Here