Abstract
Lung diseases are one of the primary causes of mortality worldwide. The majority of lung disorders are not discovered until they have progressed significantly. Therefore, the development of systems and methods that allow for immediate and earlier diagnosis will play a crucial role in the modern world. Computer Aided Diagnosis (CADx) systems presently performs this role and are being expanded. This study investigates the feasibility of employing methods for learning features from fine-tuned adaptive learning rate deep learning architectures to provide robust and comprehensive features on NIH Chest X-ray Dataset for three class (are Cardiomegaly, Emphysema, and Hernia) lung disease. A novel dual feature extraction using residual networks with nature inspired Gray Wolf Optimization (GWO) algorithm and Deep Dense Neural Network (ResNet-GWO-DD) is proposed in this study. Dual feature extraction is experimented using two fine-tuned ResNet-50 and ResNet-101 Transfer Learning (TL) architectures. The deep learned features were optimized using Grey Wolf Optimization (GWO). The global best optimal features extracted using GWO are combined for classification using Deep Dense Neural Network. The dual learning of deep features using ResNet-50 and ResNet-101 help the GWO to learn global best optimal features. These dual learning capabilities greatly enhance the performance of the proposed model and achieve significant accuracy while comparing the state-of-the-art methods. The performance of proposed method is further evaluated using three different optimizers such as Adam, stochastic gradient descent (SGD), and Continuous Coin Betting (COCOB). Deep features extracted using GWO and optimizer Adam has yielded maximum accuracy of 99.68%, 96.63% and 96.58% for Hernia, Emphysema, and Cardiomegaly respectively compared to SGD and COCOB.