Breast Cancer Classification Using Discrete Wavelet Transformation and Deep Learning

Background: One of the most prevalent diseases these days is breast cancer which is common amongst women. This sickness has been increasing to an alarming rate due to the lack of accurate diagnoses. Early and accurate detection is one of the safest ways to cure a breast cancer patient. Objectives: The objective of this study was to provide a more effective way to accurately classify a cancer sample; whether is benign or malignant. Methods: The classification model is based on the data collected from the UCI machine learning repository acquired from the Wisconsin hospital called Wisconsin Breast Cancer Data (WBCD). In this study, we preprocessed the dataset using Discrete Wavelet Transform (DWT) and then tested the efficiency of Deep Learning (DL) for breast cancer classification. The model was developed using a feed-forward neural network and the result was compared with the observed values. Results: The result of the experiment proved the effectiveness of the proposed classification technique. The new technique accomplished 98.90% accuracy for classifying breast cancer. Conclusions: The result from the experiment shows the importance of data preprocessing and the efficiency of the neural network over other classification algorithms.