Radiomic analysis of HTR-DCE MR sequences improves diagnostic performance compared to BI-RADS analysis of breast MR lesions

To assess the diagnostic performance of radiomic analysis using high temporal resolution (HTR)-dynamic contrast enhancement (DCE) MR sequences compared to BI-RADS distinguish benign from malignant breast lesions. We retrospectively analyzed data consecutive women who underwent MRI including HTR-DCE sequencing for abnormal enhancing lesions and had subsequent pathological at our tertiary center. Semi-quantitative parameters textural features were extracted. Temporal change across each phase in was calculated called “kinetic parameters.” Statistical by LASSO logistic regression cross validation performed build a model. The model results score analysis. included 117 with mean age 54 years (28–88). Of 174 analyzed, 75 99 malignant. Seven semi-quantitative 57 Regression selected 15 significant variables (called “malignant probability score”) which displayed an AUC = 0.876 (sensitivity 0.98, specificity 0.52, accuracy 0.78). (AUC 0.876, 95%CI 0.825–0.925) significantly better than that 0.831, 0.769–0.892). reduced false positives (42%) same number missed cancers (n 2). A kinetic extracted sequence improves over • Radiomic is 0.876) conventional reading 0.831) (p < 0.001). under 19.5% gives negative predictive value 100% while 81% positive 100%. Kinetic HTR-DCE-MRI have major role play distinguishing