Texture Analysis of Mammogram Using Local Binary Pattern Method
Athraa H. Farhan, Mohammed Y. Kamil · Journal of Physics Conference Series · 2020
Abstract Breast cancer is one of the types of cancer that threatens the lives of women in their 40s. Based on the statistic reports, death-rate can be reduced by early detection of breast cancer. Breast cancer detection in early stages and lessen false positives in radiologist diagnosis can be achieved by combination Computer-Aided Diagnosis (CAD) with mammography. In this work, we offer a feature extraction technique as a method to lessen false-positive in breast mass recognition. Distinguishing explicit breast masses and ordinary tissue is the objective we strive to achieve. The mini-MIAS database of mammograms was used in this paper. LBP is the method that was used to extract features from the ROI. Comprehensive detection of this method can be developed, by taking the ROI inside the ground truth, which is automatically identified in the mini-MIAS and classifier majority voting. Better sensitivity, specificity, and accuracy are observed with a logistic regression classifier.