Exploration and evaluation of efficient pre-processing and segmentation technique for breast cancer diagnosis based on mammograms

Abstract

Breast cancer is the second leading cause of death for women everywhere in the world. Since the reason behind the disease remains unknown, early detection and diagnosis is the key challenge for breast cancer control. In this work, mammogram images are initially subject to pre-processing using Laplacian ilter for enhancement of tumour regions, Gaussian mixture model, Gaussian kernel FCM, Otsu global thresholding and FCM technique are employed for segmentation. Further, the ef iciency of segmentation techniques is analyzed by classifying the samples into benign, malignant and healthy using Gray Level Co-occurrence Matrix (GLCM) features. Linear discriminant analysis classiier is used a combination based on which ef iciency used for classi ication of mammograms. Ensemble methods are evaluated. The ef iciency has resulted in better accuracy with the ensemble-based method. The experimentation is conducted in the mini MIAS database of mammograms, and the ef iciency of the linear discriminant analyzer is found to be 89.19% for GKFCM, 83.78% with Otsu and 78.38% with FCM method with GLCM features.

The Effect of Feature Selection on Gray Level Co-Occurrence Matrix (GLCM) for the Four Breast Cancer Classifications

“…In the image processing stage, we proposed to do multiply the segmentation result and enhancement result. Otsu Thresholding is used as the segmentation method and CLAHE as the enhancement method [15], [16]. The mammograms were extracted based on the texture using the Gray Level Co-Occurrence Matrix (GLCM).…”

“…Otsu Thresholding is applied to separate the breast picture (foreground) from the background. It works by finding a threshold value based on the histogram of image intensity [16]. The next step is the contrast improvement process with CLAHE.…”