Accuracy of Sono-mammographic Features in Molecular Classification of Breast Cancer

Breast cancer is the most prevalent form of cancer among women. In the Middle East, it is the primary reason for cancer-related deaths among women

Breast cancer has been classified into various histopathological and molecular subtypes based on its hormone receptor status. Their biological behaviour and prognosis depend on these hormonal subtypes.

Based on gene expression patterns, breast cancer has been classified into five different molecular subtypes by the St. Gallen International Expert Consensus. They include:

* Luminal A (LA). * Human epidermal growth factor receptor 2 (HER2) enriched. * Luminal B (LB) \[LB HER2-, LB HER2+\]. * Basal-like (triple-negative). The detection of these hormone receptors requires immunohistochemistry (IHC), which is an invasive, expensive method and may not be available in all centres, especially in less developed countries

Hence, it is important to establish imaging signatures that can play an adjunct role in predicting these subtypes and assist in pre-treatment planning (4)

Mammography (MG) and Ultrasound (US) are routinely used during breast cancer screening, and are commonly used to identify and characterise breast lesions and guide biopsy. Unlike breast MRI, these two modalities are virtually always and everywhere available at the time of cancer diagnosis. In this work, the investigators thus investigate the feasibility of predicting molecular subtypes of breast cancer from the combination of Mammography and Ultrasound.

• -AUC, sensitivity, specificity, accuracy, PPV/NPV for each subtype. -Agreement between imaging-based classification and reference standard (histopathology + IHC): -Cohen's kappa (overall and per subtype). [Срок оценки: From imaging to histopathological and immunohistochemical confirmation (up to 2 weeks).]