Detection of Brain Tumour in MRI Images using Deep Belief Network (DBN)

Abstract

One of the world's deadliest illnesses is brain cancer. It is a cancer that often affects adults as much as children. It is the least likely species to survive, and its diversity is determined by its location, sweetness and structure. The negative effects will stem from the incorrect classification of the tumour brain. Therefore, determining the specific type and rank of the tumour in its early stages is required to select a specific treatment plan. A major concern is the elimination, segmentation and detection of tumour areas infected by magnetic resonance imaging (MRI). Despite the fact that it is a laborious and tedious task done by clinical experts or radiologists whose precision depends entirely on their experience. Computer-aided technology is becoming more and more important for circumventing these limitations. This study investigates a multi-layer Deep Belief Network (DBN) technique for MRI tumour detection. The proposed model is named as Brain Tumour Deep Belief Network (BT-DBN). The BT-DBN was tested with two datasets. The results demonstrate the importance of accuracy parameters relative to the most recent approaches. The results exhibit that the BT-DBN was effective in identifying different types of tumour tissue in MR images of the brain. The precision is 99.51%, the specificity is 94.28%, and the sensitivity is 98.72%.