Finding Orientated Line Patterns in Digital Mammographic Images

Abstract

In mammography the presence of subtle abnormalities such as stellate patterns and architectual distortions indicates possible malignancy. Radiologists do not always detect these abnormalities in screening mammograms; this has led to interest in computer-aided mammographic interpretation where the radiologist is presented with computer-generated 'prompts' for abnormalities. A first step in this process is the detection of the "orientation", "scale" and "strength" of linear structures in the mammograms. We discuss several generic methods for extracting this information from images and compare their performance using synthetic images intended to simulate the appearance of mammograms. We show significant differences in performance between the different methods. We also show results obtained for real mammograms.

A review of computer-aided diagnosis of breast cancer: Toward the detection of subtle signs

“…Zwiggelaar et al [89] investigated the performance of different methods for the detection and classification of CLS in mammograms, including: a line operator [90], orientated bins [91], steerable filters [92], and ridge detectors [93]. It was observed that the best method for CLS detection (line operator) yielded an area under the ROC curve of A z ¼ 0:94.…”

Enhancement of blood vessels in digital fundus photographs via the application of multiscale line operators

“…Multiscale techniques are thus often employed in vessel segmentation in order to overcome this problem. A relatively straightforward multiscale approach is provided by the multiscale line operator (MSLO) [24][25][26][27][28]. This method has been used with great success in detecting linear structures in mammograms [24][25][26][27][28].…”

Breast Cancer: Modelling and Detection

“…GAVAGHAN et al range of spatial scales in mammograms. More recent work (Zwiggelaar et al, 1996) attempts to detect CLS using a set of "modal variations" determined by principal components analysis on a training set of idealised cases of CLS. Current work aims to apply recently developed techniques for feature detection, based largely on the observed phase congruency of features.…”