Matching Tumour Candidate Points in Multiple Mammographic Views for Breast Cancer Detection

Matching candidate points from multiple mammographic views corresponding to the same patient may lead to an improvement in the accuracy of Computer Aided Diagnosis systems and it can help the radiologists to detect breast cancer in early stages, leading to a reduction of the percentage of mortality. In this paper, we propose a matching approach in order to detect correspondences between some candidate points from multiple mammographic views. Initially, a Scale Invariant Feature Transform detector is used to determine some candidate points in the mammographic views, then a combination between texture features is proposed to check the abnormality of the local region that surrounds each candidate point. The candidate points can be matched by integrating the information given by the texture analysis, the distance from the nipple and the location of the candidate points relative to the nipple. Some experiments are presented to show the effectiveness of the proposed approach.