Abstract
In current clinical practice, the standard evaluation for axillary lymph node (ALN) status in breast cancer is based on the invasive procedure and many patients will suffer from operative associated complications. Hence, a novel signature incorporated tumor and lymph node magnetic resonance imaging (MRI) radiomics, clinical and pathological characteristics, and molecular subtypes based on the machine learning approach was established to accurately identify ALN metastasis in early-stage invasive breast cancer patients. Although the misjudgment of ALN status by clinicians according to preoperative MRI are common during clinical practice and even the senior radiologists make mistakes sometimes, this multiomic radiomic signature showed the superiority over clinicians and could precisely discriminate ALN metastasis among different molecular subtype patients. Furthermore, the association between MRI radiomic features and tumor-microenvironment features including immune cells, long non-coding RNAs, and types of methylated sites were found, which revealed the potential biological underpinning of MRI radiomics.
Machine learning magnetic resonance imaging radiomics predicts axillary lymph node metastasis in invasive breast cancer