Linear discriminant analysis based stage wise breast cancer identification
Nellore Kapileswar, B. Sankeetha, Mamta Mamta, V. Harini, S. K. Abinaya, Phani Kumar Polasi · AIP conference proceedings · 2022
One of the most fatal diseases among women is breast cancer. It is also called the second leading cause of death due to delay in the diagnosis of cancerous tissues. The most common symptoms of breast cancer are post- menopause, obesity, family genes, hormonal imbalance, and genetically muted abnormalities. Death rates are still excessive as breast cancer detection in many developing countries is diagnosed during later stages. To reduce the death rates, we need to diagnose it at the early stages. Digital mammogram images are used as input in the proposed method. Our main focus in this paper is differentiating between normal, benign, and malignant cancer. The pre-processing is done using a median filter. The K-means Segmentation is used for the segmentation process. The feature extraction is done using GLCM (Grey Level Co-occurrence Matrix) algorithm. The last step which is object classification is done using LDA (Linear Discriminant Analysis). We have classified them into different stages of cancer using the digital image processing technique and the performance of the classifier is evaluated through a confusion matrix.