DenseNet for Brain Tumor Classification in MRI Images

During the last decade, Computer Vision and Artificial Intelligence (A.I) have transformed the world in every way possible. Deep Learning is a subfield of machine learning that has shown extraordinary results in every field, particularly the biomedical field, due to its proficiency in handling huge amounts of data. Its potential and ability have also been applied and examined in detecting brain tumors’ using MRI images for effective prognosis and have shown impressive performance. The main objective of this research is to present a detailed fundamental analysis of the research and findings performed to detect and classify brain tumors through MRI images in the recent past. This analysis is especially beneficial for researchers who are deep learning connoisseurs and enthusiastic about applying their expertise to brain tumor detection and classification. A brief review of the past research papers using Deep Learning for brain tumor classification and detection is carried out as a first step. Afterwards, a critical analysis of Deep Learning techniques like Transfer Learning, Classic Neural Networks, Convolution Neural Networks, etc., are proposed in these research papers and are being carried out in the form of a graph. Ultimately, the conclusion highlights the merits and demerits of deep neural networks. The outcomes formulated in this paper will deliver a thorough comparison of recent studies to future researchers and the effectiveness of numerous deep learning approaches. We are optimistic that this study would extensively assist in advancing and improving brain tumor research.