The early and accurate detection of brain tumors is important in providing effective and efficient therapy and thus can result in increased survival rates.  Current image-based tumor detection and diagnosis methods depend heavily on the interpretation of the neuro specialists and/or radiologists.  Therefore, it is quite possible for the interpretation process to be time-consuming, and prone to human error and subjectivity. Automatic detection and classification of brain tumors have the potential to achieve efficiency and higher degree of predictable accuracy. However, it is well established that the accuracy performance of automatic detection and classification techniques varies from technique to technique, and tends to be image modality dependent. Thus, it is prudent to explore the variability in the performance of these techniques as a means to achieve consistent high accuracy performance. This paper presents a framework for fusing multiple tumor classifiers. The fusion process is based on the Dempster Shafer evidence fusion theory. Several tumor classifiers are employed. Experimental results will be presented to validate the efficiency of the proposed framework. It is concluded that fusing the classification decisions made by the various classifiers it is conceivable that efficient and consistent high accuracy classification performance can be attained.

<p class="Abstract">Even with the enormous progress in medical technology, brain tumor detection is still an extremely tedious and complex task for the physicians. The early and accurate detection of brain tumors enables effective and efficient therapy and thus can result in increased survival rates. Automatic detection and classification of brain tumors have the potential to achieve efficiency and a higher degree of predictable accuracy. However, it is well established that the accuracy performance of automatic detection and classification techniques varies from technique to technique, and tends to be image modality dependent. This paper reviews the state-of-the-art detection techniques and highlights their pros and cons.</p>

Deep Learning is a growing field of artificial intelligence that has become an operative research topic in a wide range of disciplines. Today we are witnessing the tangible successes of Deep Learning in our daily lives in various applications, including education, manufacturing, transportation, healthcare, military, and automotive, etc.<strong> </strong>Deep Learning is a subfield of Machine Learning that stems from Artificial Neural Networks, where a cascade of layers is employed to progressively extract higher-level features from the raw input and make predictive guesses about new data. This paper will discuss the effect of attribute extraction profoundly inherent in training<strong> </strong>approaches such as Convolutional Neural Networks (CNN). Furthermore, the paper aims to offer a study on Deep Learning techniques and attribute extraction methods that have appeared in the last few years. As the demand increases, considerable research in the attribute extraction assignment has become even more instrumental. Brain tumor characterization and detection will be used as a case study to demonstrate Deep Learning CNN's ability to achieve effective representational learning and tumor characterization.

Image segmentation plays a crucial role in recognizing image signification for checking and mining medical image records. Brain tumor segmentation is a complicated assignment in medical image analysis. It is challenging to identify precisely and extract that a portion of the image has abnormal tissues for further diagnosis and analysis. The method of segmenting a tumor from a brain MRI image is a highly concentrated medical science community field, as MRI is non-invasive. In this survey, brain MRI images' latest brain tumor segmentation techniques are addressed a thoroughgoing literature review. Besides, surveys the several approved techniques regularly applied for brain tumor MRI segmentation. Also, highlighting variances among them and reviews their abilities, pros, and weaknesses. Various approaches to image segmentation are described and explicated with the modern participation of several investigators.