This research concerned a clinical need for precise breast cancer lesion characterization imaged by ultrasound sequences. Using therefore BI-RADS features that would be carefully extracted, the purpose of this study could be mainly to prove and to demonstrate the possibility of surveying precisely the changing characteristics of a breast cancer lesion within a considered ultrasound images' sequence. This was in fact a clinical need of a computer aided diagnosis (CAD) system permitting flexible and convivial clinical analysis of multi-slices' ultrasound breast cancer lesion with greater precision. The obtained results of our images' sequence breast cancer ultrasound analysis had shown the lesion form changing depending on the treated slice, as well as the values' differences for the morphological and the textural features. This would allow extracting more information about breast cancer lesions helping then radiologist to converge more rapidly and with a certain reinforced precision to the accurate clinical action to conduct. Such results would be reassembled and rearranged for constituting one computer aided diagnosis (CAD) system that could be provided for clinical explorations permitting on the other hand to avoid possible confusion between benign and malignant masses.

In this paper, we will focus on the Spatial Gray Level Dependence Matrices SGLDM to extract the Haralick's texture features of the ultrasound breast lesions. This method relies on the manual selection of the region of interest, which results in the dependence of parameters values on the extracted region. For that reason, an improved Spatial Gray Level Dependence Matrices based on the segmented masses using active contour was applied. This method outperforms the existing SGLDM method because it allows establishing a well determined threshold for the classification of lesions.

No abstract

No abstract

No abstract