Machine Learning-Based Approaches For Breast Cancer Detection in Microwave Imaging

Detection of breast cancer at an early stage can significantly reduce the mortality rate. Microwave imaging is a promising detection tool for harmless and non-ionizing screening of breast cancer. In this work, a fast and accurate machine learning algorithm is proposed for the prediction of the breast lesion using microwave signals. Machine learning has proved itself reliable in the field of biomedical application where the diagnosis of the disease is desired. The support vector machine (SVM) algorithm with the linear and polynomial kernel is trained and tested on raw backscattered signals data. SVM with third-degree polynomial kernel obtained 99.7% accuracy that outperforms the existing conventional machine learning binary classification algorithms. Thus, the prediction of tumor presence would help the radiologist to diagnose tumor correctly at early stages.