Multi-Class Tumor Diseases Classification Using Discrete Wavelet Transform and Principal Component Analysis

Abstract

A brain tumor is an extreme danger to the patient in the current era, leading to confirmed death. Furthermore, the precise classification of brain tumor image is one of the significant issues in clinical analysis fields. Therefore, enhancing tumor classification is required in the medical area. Moreover, brain tumor classification using machine learning (ML) for Magnetic Resonance Imaging scan (MRI) plays a huge vital role in different treatments applications. However, unfortunately, the previous schemes have recorded insufficient accuracy in the classification of brain tumors. The introduced technique contains feature extraction, feature reduction, and classification-based machine learning. Firstly, the low-frequency features of images using Discrete wavelet Transformation (DWT) have been obtained. Secondly, the reduced features have been provided using Principal Component Analysis (PCA). Lastly, The Random Forest (RF) classifier has been used to classify seven tumor classes. RF has obtained classification with a success of accuracy-based-metric with 96.83%. This result explores that the introduced DWT-PCA is more effective than other recent schemes.Clinical Relevance–Tumor Diseases.