Mammographic Ellipse Modelling Towards Birads Density Classification
It has been shown that breast density and parenchymal patterns are important indicators in mammographic risk assessment. In addition, the accuracy of detecting abnormalities depends strongly on the structure and density of breast tissue. As such, mammogra
- PDF / 2,459,902 Bytes
- 8 Pages / 439.37 x 666.142 pts Page_size
- 34 Downloads / 224 Views
2
Department of Computer Science, Aberystwyth University, Aberystwyth SY23 3DB, UK {mig24,yar,rrz}@aber.ac.uk Department of Radiology, Norfolk and Norwich University Hospital, Norwich NR4 7UY, UK [email protected]
Abstract. It has been shown that breast density and parenchymal patterns are important indicators in mammographic risk assessment. In addition, the accuracy of detecting abnormalities depends strongly on the structure and density of breast tissue. As such, mammographic parenchymal modelling and the related density estimation or classification are playing an important role in computer aided diagnosis. In this paper, we present a novel approach to the modelling of parenchymal tissue, which is directly linked to Tabar’s normal breast tissue representation and based on the multi-scale distribution of dark ellipses, and the complementary distribution of bright ellipses which represent dense tissue. Our initial evaluation is based on the full MIAS database. We provide analysis of the separation between the Birads density classes, which indicates significant differences and a way towards automatic Birads based density classification.
Keywords: Breast density modelling
1
· Blob and ellipse detection
Introduction
One of the major risk factors associated with breast cancer is breast tissue density and the appearance of the parenchymal tissue. It has a direct relation with the probability of developing breast cancer [1–3]. Examples of mammographic images illustrating various types of tissue densities as per Breast Imaging Reporting and Data System (BIRADS) density classification are illustrated in Fig. 1. The manual assessment of breast density and/or parenchymal patterns is covered in various classification schemes [1,2,4,5], which are all correlated [6]. The automatic segmentation of mammographic tissue and the related (BIRADS) density classification of the mammograms has been an active research area. In general this has concentrated on the modelling and detection of dense tissue [7,8,11]. The review by He et al. [10] demonstrated all recent approaches to finding the correlation between the breast density and its classification methods c Springer International Publishing Switzerland 2016 A. Tingberg et al. (Eds.): IWDM 2016, LNCS 9699, pp. 423–430, 2016. DOI: 10.1007/978-3-319-41546-8 53
424
M. George et al.
in risk assessment. In [10] they showed that the main approaches in the literature use techniques like thresholding, clustering, and statistical model building. In this study we look at incorporating the modelling of the complement of dense tissue: i.e. the modelling of the distribution of fatty tissue and how this can be exploited to provide BIRADS density classification. This work is closely related to that of Chen et al. [9], which developed a mammographic segmentation approach using topographic maps with an emphasis on the modelling and distribution of bright blobs in mammographic images.
Fig. 1. Some example mammograms showing various BIRADS density classification based on Birads 4th edition. (a
Data Loading...
