Multiparametric MRI Radiomics With Machine Learning for Differentiating HER2-Zero, -Low, and -Positive Breast Cancer: Model Development, Testing, and Interpretability Analysis
Yongxin Chen, Si–Yi Chen, Wenjie Tang, Qingcong Kong, Zhidan Zhong, Xiaomeng Yu, Yi Sui, Wenke Hu, Xinqing Jiang, Yuan Guo
Abstract
BACKGROUND. MRI radiomics has been explored for three-tiered classification of HER2 expression levels (i.e., HER2-zero, HER2-low, or HER2-positive) in patients with breast cancer, although an understanding of how such models reach their predictions is lacking.
Topics & Concepts
MedicineInterpretabilityRadiomicsBreast cancerArtificial intelligenceMedical physicsMachine learningCancerRadiologyInternal medicineComputer scienceRadiomics and Machine Learning in Medical ImagingAI in cancer detectionMRI in cancer diagnosis