A Computer Aided Diagnosis System for Breast Cancer
Breast cancer is one of the most prevalent cancers, ranking second only to lung cancer and is the most prevalent form of cancer among worldwide women. Each year, about 1,000,000 women would be newly diagnosed with breast cancer and over 500,000 women died from breast cancer every year. In this paper, a computer-aided diagnosis (CAD) framework for breast cancer is developed using application of supervised machine learning techniques to the classification of cancerous /non-cancerous data. Here, we attempt to explore several different feature selection and extraction techniques and combine the optimal feature subsets with various learning classification methods such as K-nearest neighbors, probabilistic neural networks and support vector machines classifiers. To evaluate the generalization ability of the proposed system for distinguishing the benign and malignant cases, 2 benchmark FNAB and gene microarray datasets are utilized. The best overall accuracy for breast cancer diagnosis is achieved equal to 98.80% and 96.33% respectively using support vector machines classifier models against two widely used breast cancer benchmark datasets.
Keywords: Signal-to-noise, False positive, K-nearest neighbors, Probabilistic neural networks, Support vector machines
Download Full-Text
