Gated Deep Reinforcement Learning With Red Deer Optimization for Medical Image Classification

One of the most complex areas image processing is classification, which heavily relied upon in clinical care and educational activities. However, conventional models have reached their limits effectiveness require extensive time effort to extract choose classification variables. In addition, large volume medical data being produced makes manual procedures ineffective prone errors. Deep learning has shown promise for many problems. this study, a deep learning-based model developed decrease misclassifications handle amounts data. The Adaptive Guided Bilateral Filter used filter images, texture edge attributes are gathered using Spectral Gabor Wavelet Transform. Black Widow Optimization method best features, then input into Red Deer Optimization-enhanced Gated Reinforcement Learning network classification. brain tumor MRI dataset was test on MATLAB platform, results showed an accuracy 98.8%.