Abstract
Breast cancer is the most common cancer among women and it is one of the main causes of death for women worldwide. To attain an optimum medical treatment for breast cancer, an early breast cancer detection is crucial. This paper proposes a multi- stage feature selection method that extracts statistically significant features for breast cancer size detection using proposed data normalization techniques. Ultra-wideband (UWB) signals, controlled using microcontroller are transmitted via an antenna from one end of the breast phantom and are received on the other end. These ultra-wideband analogue signals are represented in both time and frequency domain. The preprocessed digital data is passed to the proposed multi- stage feature selection algorithm. This algorithm has four selection stages. It comprises of data normalization methods, feature extraction, data dimensional reduction and feature fusion. The output data is fused together to form the proposed datasets, namely, 8-HybridFeature, 9-HybridFeature and 10-HybridFeature datasets. The classification performance of these datasets is tested using the Support Vector Machine, Probabilistic Neural Network and Naïve Bayes classifiers for breast cancer size classification. The research findings indicate that the 8-HybridFeature dataset performs better in comparison to the other two datasets. For the 8-HybridFeature dataset, the Naïve Bayes classifier (91.98%) outperformed the Support Vector Machine (90.44%) and Probabilistic Neural Network (80.05%) classifiers in terms of classification accuracy. The finalized method is tested and visualized in the MATLAB based 2D and 3D environment.
Highlights
The rate of a woman contracting breast cancer is reported at a worrying rate globally, in developing countries
For Sure Entropy (SU)-ZS dataset, the accuracies for Support Vector Machine (SVM), Naïve Bayes (NB) and Probabilistic Neural Network (PNN) are recorded as 84.39%, 83.69% and 82.97% respectively
For PNN classifier, the highest result is achieved by 8-HybridFeature dataset by obtaining 80.05%, 78.67%, 81.84% for accuracy, sensitivity and specificity respectively
Summary
The rate of a woman contracting breast cancer is reported at a worrying rate globally, in developing countries. It can be clearly concluded that breast cancer cases are increasing every year and it is still recorded as second top causes of the woman’s death [4, 5]. Common diagnostic methods are mammography, magnetic resonance imaging (MRI) and ultrasound scans [6,7] These methods are proven costly, bulky, invasive and are unable to detect the early stages of breast cancer. Taking into consideration all the limitations of the conventional diagnostic methods, microwave based ultra-wide-band (UWB) imaging technology can be a potential and promising method for early breast cancer detection as it is convenient, non- invasive, secure and lowcost [7, 10,11,12]. The features are selected based on the different feature selection methods proposed by various researchers in breast cancer size detection. The performance of the proposed method is validated using statistical and machine learning approaches
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
