Linear Discriminant Analysis Tumour Classification for Unsupervised Segmented Mammographies

Abstract

Between 2015 and 2020, 7.8 million women were diagnosed with breast cancer. If the cancer is discovered early, it can be completely cured. Computer-aided detection and diagnosis systems are a helpful tool. We propose such a system: after pre-processing the mammography, the region of interest is identified using an unsupervised manner. Textural features are extracted from the Gray-Level Co-occurrence Matrix and used with the Linear Discriminant Analysis classifier, obtaining a diagnosis: benign or malignant. The proposed system is tested on the Mini-MIAS dataset, reaching an accuracy score of 95% and a precision and specificity of 100%.