A Radiomic and Clinical Data-Based Risk Model for Malignancy Prediction of Breast BI-RADS 4A Microcalcifications.

Abstract

Background: Mammography is the gold standard technique for early breast cancer screening, but it has a limited specificity for microcalcifications. Radiomics represents a promising tool for enhancing lesion risk stratification. This study aims to evaluate the reliability of radiomics in combination with clinical data to classify benign and malignant microcalcifications, potentially enhancing the standard radiological assessment and reducing the need for biopsies.

Materials and methods: This study retrospectively analyzed patients with BI-RADS 4A microcalcifications who underwent mammography (MX) and vacuum-assisted breast biopsy (VABB) at our center from January 2019 to February 2023. About 104 radiomics features were extracted from a region of interest, manually defined on images. Clinical data from each patient were collected. Using the Tyrer-Cuzick Model, we classified patients according to the risk of developing breast cancer. Two logistic regression models, using clinical and radiomics data were trained to predict the pathological classification of breast calcifications.

Results: A total of 167 calcification groups were included in the study. The final dataset was made of 14 radiomics features. The radiomics model alone achieved an AUC of 0.72 (95% CI, 0.61-0.33) while the model trained on clinical and radiomics features obtained AUC values of 0.81 (95% CI, 0.69-0.92).

Conclusions: Our findings suggest that the integration of clinical data with radiomics has the potential to reduce unnecessary biopsies for BI-RADS 4A microcalcifications, leading to more targeted and personalized patient care.