作者
Yuqin Peng,Xiang Zhang,Ya Qiu,Baoxun Li,Zehong Yang,Jiayi Huang,Jinru Lin,Chushan Zheng,Lanxin Hu,Jun Shen
摘要
BACKGROUND. Breast cancer HER2 expression has been redefined using a three-tiered system: HER2-zero (ineligible for HER2-targeted therapy), HER2-low (novel HER2-targeted drugs), and HER2-positive (traditional HER2-targeted medications). OBJECTIVE. To assess MRI radiomics models for three-tiered classification of HER2 expression of breast cancer. METHODS. This retrospective study included 592 patients with pathologically confirmed breast cancer (mean age, 47.0±18.0 years) who underwent breast MRI at either of a health system's two hospitals from April 2016 to June 2022. Three-tiered HER2 status was pathologically determined. Radiologists assessed tumors' conventional MRI features and manually segmented tumors on multiparametric sequences (T2-weighted images, DWI, ADC, delayed contrast-enhanced images) to extract radiomics features. Least-absolute shrinkage and selection operator analysis was used to develop two radiomics signatures, to differentiate HER2-zero from HER2-low or HER2-positive cancers (task 1), and HER2-low from HER2-positive cancers (task 2). Patients from hospital 1 were randomly assigned to discovery (task 1: n=376; task 2: n=335) or internal validation sets (task 1: n=161; task 2: n=143); patients from hospital 2 formed an external validation set (task 1: n=55; task 2: n=50). Multivariable logistic regression analysis was used to create nomograms combining radiomics signatures with clinicopathologic and conventional MRI features. RESULTS. AUC, sensitivity, and specificity in discovery, internal validation, and external validation sets were, for task 1, 0.89, 99.4%, and 69.0%; 0.86, 98.6%, and 76.5%; and 0.78, 100.0%, and 0.0%; and, for task 2, 0.77, 93.8%, and 32.3%; 0.75, 92.9%, and 6.8%; and 0.77, 97.0%, and 29.4%. For task 1, no nomogram was created because no clinicopathologic or conventional MRI feature was associated with HER2 status independent of MRI radiomics signature. For task 2, a nomogram including MRI radiomics signature and three pathologic features (histologic grade III, high Ki-67, positive progesterone receptor status) independently associated with HER2-low expression had AUC in the three sets of 0.87, 0.83, and 0.80. CONCLUSION. MRI radiomics features were used to differentiate HER2-zero from HER2-low or HER2-positives cancers, and HER2-low from HER2-positive cancers. CLINICAL IMPACT. MRI radiomics may help select patients for novel or traditional HER2-targeted therapies, particularly in those with ambiguous immunohistochemical results or limited access to fluorescence in situ hybridization.