Microcalcifications segmentation from mammograms for breast cancer detection

Abstract

The presence of microcalcifications (MCs) in X-ray mammograms provides an important early sign of women breast cancer. However, their detection still remains very complex due to the diversity in shape, size, their distributions and to the low contrast between the cancerous areas and surrounding bright structures in mammograms. This paper presents an effective approach based on mathematical morphology for detection of MCs in digitised mammograms. The developed approach performs an initial step in order to extract the breast area and removing unwanted artefacts out of the mammogram. Subsequently, an enhancement process is applied to improve appearance and increase the contrast of images and to eliminate noise. Once the breast region has been found, a segmentation phase through morphological watershed is performed in order to detect MCs. The performance of our approach is evaluated using a total of 22 mammograms extracted from the MIAS mammographic database, showing the presence of MCs. The obtained results were compared with manual detection, marked by an expert mammographic radiologist. These results show that the system is very effective, especially in terms of sensitivity.

Computer Vision-Based Microcalcification Detection in Digital Mammograms Using Fully Connected Depthwise Separable Convolutional Neural Network

“…Several methods were employed to develop CAD systems in the previous studies, such as the enhancement, edge detection, wavelet transform, microcalcification detection, and ROI segmentation of images and then classifying them into malignant and benign. There are many limitations to these methods, for example: Hadijidj et al [ 6 ] proposed a watershed morphology operation to extract the segmented regions from mammograms for the detection of microcalcifications. In addition, the watershed morphology technique was employed for edge detection and region growing, while noise removal was still a problem.…”