An Empirical Analysis of Machine Learning Techniques for Brain Tumor Detection

Abstract

The human brain is made up of a variety of tissues that are essential for the normal functioning of the brain. Tumors of the brain is one of the most dangerous diseases that can harm the brain and cause death. Any genetic mutation in these tissues has the potential to alter the functioning of the brain, and this is referred to as a brain tumor. Finding a tumor at a preliminary phase gets critical in order that could save a person’s life. On the basis of medical imaging, one of the procedures utilised for the detection of brain tumors has been developed. The detection and segmentation of brain tumors is one of the most difficult and time-consuming tasks in computer - aided diagnosis. Medical imaging using magnetic resonance is known as MRI (Magnetic Resonance Imaging). This technique is mostly utilised by radiologists to visualize the inside human anatomy without the need for surgery. Image processing techniques are now playing a key role in the field of medical imaging. There are several different approaches for detecting and segmenting brain tumors. Methods for detecting and segmenting the brain tumor from MRI pictures are used to identify and segment the tumor from the images. A reduction in inaccuracy in conventional clinical diagnosis of disease has been demonstrated by using machine learning techniques. Brain tumor diagnosis, in particular, necessitates high precision because even minor errors in diagnosis might result in serious consequences. Brain tumor detection and disclosure continues to be a difficult task in medical image processing. The methods of brain tumor segmentation and classification are covered in detail in this work, which is well-structured and well-mannered throughout. This contributes to the provision of potential study directions in the classification of brain tumors in the future.