An approach to segmentation of a solid focal lesion in breast and its peripheral areas in ultrasound images

Abstract

The paper proposes an approach to the segmentation of solid breast lesions and their peripheral areas in ultrasound images. It is noted that identifying the outermost breast lesion structures is an important step for the further lesion classification, directly affecting the final classification of its type. The main feature of the proposed approach is that its implementation takes into account peculiarities of pixel brightness variations in the original image, without using speckle noise filters. The method was tested on a set of ultrasound images of morphologically verified 42 benign and 49 malignant breast lesions marked by a radiologist. The segmentation results were compared with the results of manual marking performed by the radiologist. The average errors in the segmentation of benign and malignant lesion were 5 pixels – for the lesion area and 7 pixels – for the peripheral area, which is insignificant, taking into account the error of manual marking performed by radiologist (3.9 and 4.7 pixels, respectively). The average intersection-over-union (IoU) metrics were 0.82 and 0.80, respectively. The presented results indicate the possibility of using the developed technology in a combination with the system of lesion differentiation.