Enhancing diagnostic accuracy of BI-RADS 4 breast lesions: integrating ADC and microcalcifications into the kaiser score

Abstract

Abstract Background Breast Imaging Reporting and Data System (BI-RADS) 4 lesions represent a heterogeneous group with variable malignancy risk. While the Kaiser score (KS) provides lesion assessment, its performance may be enhanced by integrating additional imaging parameters. Therefore, this study aimed to evaluate the diagnostic performance of combining apparent diffusion coefficient (ADC) values and suspicious mammographic microcalcifications with the Kaiser score in MRI BI-RADS 4 lesions. Methods A total of 115 patients with 122 breast lesions categorized as BI-RADS 4 on MRI were included in the study. All patients had an MRI and a mammogram. Two independent observers evaluated lesion characteristics and calculated the Kaiser score (KS) and three modifier scores: KS1 (KS + microcalcifications), KS2 (KS + ADC), and KS3 (KS + ADC + microcalcifications). Diagnostic performance and interobserver agreement were assessed. Results The Kaiser score demonstrated high diagnostic performance in BI-RADS 4 lesions, with sensitivity approaching 92%. Integration of ADC values and mammographic microcalcifications further improved sensitivity, diagnostic accuracy, and interobserver agreement, with the KS3 showing the most consistent performance. Microcalcifications primarily enhanced sensitivity, whereas ADC improved specificity and overall diagnostic accuracy. Conclusion Combining ADC values and mammographic microcalcifications with the Kaiser score enhances diagnostic performance and accuracy in MRI BI-RADS 4 lesions. The multiparametric composite approach may improve diagnostic confidence and assist in more informed clinical decision-making.