An enhanced framework for identifying brain tumor using discrete wavelet transform, deep convolutional network, and feature fusion-based machine learning techniques

Today, the histological study of biopsy specimens is still used to diagnose brain tumors (BTs). This existing procedure is intrusive, arduous, and liable to mistakes. These downsides highlight the standing of employing a completely computerized process for identifying the evolution of tumors in the brain. A primary BT affects an estimated 0.7 million persons in the United States now and more are expected to be detected in the coming years. The ability to categorize magnetic resonance (MR) brain images into ordinary and pathological categories has the boundless ability to significantly diminish the burden on the radiologist. Pre-processing, extraction, and reduction of features along with their classification are the parameters of statistical-based methodologies that have been frequently used for this purpose. In this work, an enhanced framework for the identification of the BT is proposed using discrete wavelet transform (DWT), deep convolutional network (DCN), and machine learning (ML). As DWT is primarily used for image compression and denoising applications however in the presented research work it has been utilized for extricating pivotal features from the MR images using the feature fusion technique. DCN is also utilized for the extraction of pivotal deep features which are then combined with the wavelet-based features for the purpose of BT identification. The classification of tumorous and non-tumorous MR images is done using ML applications. The results obtained from the proposed model exhibit an utmost accuracy of 99.5% with an area under curve of 1 in identifying tumorous and non-tumorous MR images as compared to various state-of-the-art models. The proposed model can be efficiently used for assisting radiologists and medical experts in validating their decisions for BT identification.