ASystematic Mapping Study on Brain Tumors Recognition Based on Machine Learning Algorithms

A brain tumor is a type of cancer of abnormal brain cells or mass. The skull is rather solid, and it encloses the brain. Any growth within such a confined space can cause problems. There could be cancerous (malignant) or noncancerous (benign) brain tumors. As benign or malignant tumors develop, they may increase the pressure within the skull. This can cause brain damage and could even be life-threatening. In the recent decade, lots of systems have been produced that provide automatic classification of brain tumors via utilizing means of magnetic resonance spectroscopy and pattern recognition. In spite of promising classification accuracies, none of these systems has established its direction into clinical practice, which is also concerning the missing transparency of the basis of their decision making. In this paper, a systematic mapping study on brain tumors recognition is presented. After four sorting methods, 857 relevant studies in total have been obtained. After applying four filters, 49 papers as primary studies related to the main topic are selected. The selected papers have classified respect to several facets. The results provide an overview of the existing relevant studies reported in the literature, highlight focus areas and research gaps.