Fig. 1From: Diagnostic performance of machine learning applied to texture analysis-derived features for breast lesion characterisation at automated breast ultrasound: a pilot studyAxial images obtained with automated breast ultrasound (ABUS). A region of interest was drawn freehand marking the outer edge of the lesion or the maximal continuous area of fat or fibroglandular tissue included in the image. Invasive ductal carcinoma in a 53-year-old patient undergoing screening mammography and ABUS (a). Stable benign solid lesion after a 48-month follow-up in a 35-year-old woman undergoing routine control (b). Fatty tissue (c). Fibroglandular tissue (d)Back to article page