A review on Brain Tumor Detection using Deep Neural Networks

Artificial Intelligence has in the last 10 years drastically transformed the globe. Owing to its ability to manage vast volumes of data, deep Learning (DL) a subsection of Artificial Intelligence and machine learning, especially in the healthcare area, has proven exceptional accomplishments. New developments in DL based techniques such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), Generative adversarial neural networks, and many more that have shown exceptional potential for inaccurate categorization of brain cancers. The major goal of this paper is mainly to critically examine the previous identification and classification efforts of brain tumors using MRI (Magnetic Resonance Imaging) data. In this work, we review the best current algorithms for deep learning applications in Brain tumor classification problem contexts and utilization. The most significant findings that have been documented thus far are addressed, and finally, the research’s present hurdles are also highlighted. The conclusion discusses the pros and limitations of deep neural networks. In the time ahead using the results reported in this paper, researchers will be able to evaluate recent studies extensively and gain a knowledge of how different DL algorithms function.