An Improved Cuttlefish Optimization Algorithm Based Faster R-CNN for Brain Tumour Detection

Brain tumor is caused due to the anomalous development of tissues in the brain. Precise identification of the tumor in premature stage is essential to provide effective medication and curtail further impact of the disease in affected individuals. This present research includes four main stages for the diagnosis of brain tumor including segmentation and classification based on deep learning approaches. The preprocessing stage makes use of filters to reduce the noise impact in the brain imagery. The segmentation stage is responsible to segment the tumor portions from the images using Enhanced Region Growth algorithm. Feature selection stage utilizes Improved Cuttlefish Optimization (ICO) algorithm to extricate the optimal features from the segmented images. The final stage is classification in which Faster R-CNN (FRCNN) algorithm is employed to categorize the brain images as tumor affected or not. BRA TS-2020 dataset is used for the experimental investigation of the proposed FRCNN-ICO method. Performance of this method is assessed using parameters such as Accurate Prediction Rate (APR), Imprecise Prediction Rate (IPR) and Imprecise Denial Rate (IDR). The proposed FRCNN-ICO produces the highest APR value of 99.2% compared to the existing researches on brain tumor detection and proves to perform superior than the methods considered for comparison purposes.