MRI-based radiomics for the diagnosis of triple-negative breast cancer: a meta-analysis

Abstract

To analyse the diagnostic value of magnetic resonance imaging (MRI)-based radiomics for triple-negative breast cancer (TNBC) by conducting a meta-analysis. A comprehensive search was performed to identify relevant English articles concerning the MRI-based radiomics diagnosis of TNBC (from the date of database establishment to November 2021). The pooled sensitivity (SEN), pooled specificity (SPE), positive likelihood ratio (LR+), negative likelihood ratio (LR-), diagnostic odds ratio (DOR) with 95% confidence interval (CI), summary receiver operating characteristic (SROC) curve and area under the curve (AUC) for the accuracy of MRI-based radiomics in the diagnosis of TNBC were calculated. The I2 test was used to assess heterogeneity and the source of heterogeneity was investigated by performing a meta-regression analysis. Publication bias was assessed using Deeks' funnel plot asymmetry test. Six studies (1,223 patients) met the eligibility criteria. The pooled sensitivity and specificity were 0.72 and 0.91, respectively. The LR+ of the malignant ultrasonic features was 8.0, and the LR- was 0.31, revealing that MRI-based radiomics exhibited excellent ability to confirm or exclude TNBC. SROC curves showed that the AUC of the MRI-based radiomics diagnosis of TNBC was 0.88, indicating that MRI-based radiomics has good diagnostic value for TNBC. MRI radiomics is an excellent diagnostic tool with high specificity for the diagnosis of TNBC.