Objectives: To investigate whether combining radiomics extracted from ultrafast dynamic contrast-enhanced MRI (DCE-MRI) with an artificial neural network enables differentiation of MR BI-RADS 4 breast lesions and thereby avoids false-positive biopsies.Methods: This retrospective study consecutively included patients with MR BI-RADS 4 lesions. The ultrafast imaging was performed using Differential sub-sampling with cartesian ordering (DISCO) technique and the tenth and fifteenth postcontrast DISCO images (DISCO-10 and DISCO-15) were selected for further analysis. An experienced radiologist used freely available software (FAE) to perform radiomics extraction. After principal component analysis (PCA), a multilayer perceptron artificial neural network (ANN) to distinguish between malignant and benign lesions was developed and tested using a random allocation approach. ROC analysis was performed to evaluate the diagnostic performance.Results: 173 patients (mean age 43.1 years, range 18–69 years) with 182 lesions (95 benign, 87 malignant) were included. Three types of independent principal components were obtained from the radiomics based on DISCO-10, DISCO-15, and their combination, respectively. In the testing dataset, ANN models showed excellent diagnostic performance with AUC values of 0.915-0.956. Applying the high-sensitivity cutoffs identified in the training dataset demonstrated the potential to reduce the number of unnecessary biopsies by 63.33%-83.33% at the price of one false-negative diagnosis within the testing dataset.Conclusions: The ultrafast DCE-MRI radiomics-based machine learning model could classify MR BI-RADS category 4 lesions into benign or malignant, highlighting its potential for future application as a new tool for clinical diagnosis.
Germline loss-of-function mutations in BRCA1 and BRCA2 (BRCA) genes are well-established as causative factors for hereditary breast and ovarian cancer (HBOC), conferring an approximately tenfold increased lifetime risk. The identification of BRCA mutations is essential for risk assessment and management in high-risk individuals and cancer patients. In this study, we utilized next-generation sequencing (NGS) to comprehensively analyze the entire coding regions of BRCA genes in a cohort of 100 unselected patients undergoing germline screening (average age ≤45 years and/or family history of related cancers). A total of twenty-two variants were identified, including thirteen pathogenic or likely pathogenic variants (PVs/LPVs) and nine variants of uncertain significance (VUSs). Notably, six novel variants (two in BRCA1 and four in BRCA2) were discovered. Molecular subtyping revealed that breast cancer (BC) patients with BRCA variants were predominantly human epidermal growth factor receptor-2 (HER2)-negative. Using in silico prediction tools, nine VUSs were reclassified, with functional impairment confirmed for the BRCA2 p.W2619C and BRCA2 p.N1023_I1024del variants. Functional assays demonstrated that the BRCA2 p.W2619C variant significantly enhanced cell proliferation, migration, and invasion. Moreover, cells harboring the BRCA2 p.W2619C mutation exhibited increased sensitivity to Olaparib, suggesting potential therapeutic benefit from PARP inhibitors for patients with this variant. Our study identified six novel BRCA mutations and functionally validated the pathogenicity of the BRCA2 p.W2619C variant, thereby advancing the understanding of BRCA-related cancer risk and supporting enhanced genetic counseling and testing strategies for at-risk populations.