HYBRID FIREFLY META OPTIMIZATION FOR BIO MEDICAL IMAGE PROCESSING USING DEEP LEARNING

Signal and image processing is a part of biomedical science. In that, Biomedical have great value such as recognition, segmentation classification for disease diagnosis. one science, brain tumor considered with Magnetic Resonance Images (MRI) images using state art models. Initially, the Convolutional Neural Network (CNN), Fast (FCNN), U-Net M-Net model was classification. Further, Hybrid Firefly Meta Optimization (HFMO) proposed better prediction purpose. The work has three phases like normalization augmentation, deep attention first phase, data augmentation applied to increase scope dataset. second technique concentrate on hotspot in during segmentation. Finally, hybrid firefly optimization enhance performance convolution neural network by backtracking process. measuring parameters Dice coefficient, Jaccard index, Positive Projected Value (PPV), True Rate False were evaluated. comparative analysis various models classifier demonstrated. Thus produces training accuracy 98.62%, testing 95.31 % 1 loss.