Gated deep reinforcement learning with red deer optimization for medical image classification

Abstract

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