e-space
Manchester Metropolitan University's Research Repository

Automatic Quantification of Breast Arterial Calcification on Mammographic Images

Mazidi, N and Roobottom, C and Masala, G (2019) Automatic Quantification of Breast Arterial Calcification on Mammographic Images. In: Innovation in Medincine & Heathcare, 17 June 2019 - 19 June 2019, St Julians, Malta.

[img]
Preview

Download (1MB) | Preview

Abstract

© 2019, Springer Nature Singapore Pte Ltd. This paper describes the research and development of an automatic computer system that is used to quantify breast arterial calcifications in mammography scans. A few prior studies have attempted to establish a relationship between breast arterial calcification (BAC) and the rate of coronary artery disease (CAD) risk factors. The majority of these studies demonstrated a positive association between BAC and increasing age. Large scale cohort studies and retrospective studies have almost uniformly suggested a strong association between BAC and cardiovascular disease-related morbidity and mortality. This strong association of BAC with cardiovascular pathology suggests that BAC should also be persistently associated with radiographically determined CAD. A method of image processing, segmentation, and quantification used to highlight and recognise calcified blood vessels in the breast is proposed and described in detail. This project aims to introduce a new use for digital Mammography, which is currently solely used for diagnosing breast cancer in female patients. A method of detecting BAC is introduced at no additional cost, having an adequate degree of accuracy, around 82%, which means that this type of system could be used to assist a radiographer in diagnosing BAC by indicating whether the patient has a high or low severity of calcification.

Impact and Reach

Statistics

Downloads
Activity Overview
66Downloads
80Hits

Additional statistics for this dataset are available via IRStats2.

Altmetric

Actions (login required)

Edit Item Edit Item