Automated Chest X-Ray Image Classification Using Manta Ray Optimization with Deep Learning Approach

Automated chest X-ray image classification is a critical tool for efficient and timely diagnosis of various pulmonary conditions. In this study, we propose a novel approach utilizing Manta Ray Optimization (MRO) in conjunction with state-of-the-art deep learning architectures, specifically Mobile Net and ResNet, for enhanced accuracy in classifying chest X-ray images.

Mobile Net and ResNet are popular deep learning architectures known for their efficiency and high performance in image classification tasks. We leverage the strengths of Mobile Net and ResNet, integrating them with Manta Ray Optimization, an evolutionary algorithm inspired by the movement patterns of manta rays. The MRO algorithm helps optimize the model parameters and enhance the convergence speed during the training process, ultimately improving the classification accuracy.

We conducted experiments on a well-curated chest X-ray dataset and compared the performance of our proposed approach with traditional deep learning methods. The results demonstrate superior classification accuracy and efficiency achieved by the combined MRO and deep learning approach. The incorporation of Manta Ray Optimization significantly enhances the convergence speed, enabling quicker and more accurate diagnoses of chest X-ray images. Our approach holds great promise in revolutionizing automated chest X-ray image classification, aiding healthcare professionals in timely and precise diagnosis of respiratory ailments.

Keywords: deep learning, mobile net, resnet-50, image processing, chest x-rays.