An automated method for breast mass segmentation
Sourour Khouaja, Jlassi Hajer, Kamel Hamrouni · 2014
Breast cancer continues to be a significant health problem in the world. The most familiar breast anomalies types are mass and microcalcification. However Automatic methods for detecting these abnormalities can identify breast cancer at an early stage. In this paper, we propose a marker-controlled watershed algorithm to locate breast masses. The preprocessing step has been introduced to remove all undesirable areas from mammogram. Foreground and background markers are then selected in order to apply a watershed segmentation algorithm that identifies the location of tumor region in mammogram. The proposed method was successful to segment mass anomalies. It has been tested on publicly available Mammographic Image Analysis Society (MIAS) database and it has achieved an overall mass detection rate of 90.83% and an area Az of 0.913 under the receiver operating characteristic curve ROC for mass segmentation.