Brain cancer classification based on multistage ensemble generative adversarial network and convolutional neural network

Abstract

An advanced approach that capitalizes on the synergies between multimodal feature fusion and the dual‐path network is presented in this manuscript. Our proposed methodology harnesses a combination of potent techniques, merging the benefits of nonlinear mapping and expansive perception. The foundation of our methodology lies in leveraging well‐established pretrained models, namely EfficientNet‐B7, ResNet‐152, and a meticulously crafted custom convolutional neural network (CNN), to effectively extract salient features from the data. These models are combined in a two‐stage ensemble approach. We employ maximum variance unfolding (MVU) to select the most relevant attributes from the extracted features. In this study, we propose a hybrid approach that integrates a generative adversarial network and Neural Autoregressive Distribution Estimation (NADE‐K) with a CNN. The resulting two‐stage ensemble hybrid CNN model achieves an accuracy of 99.63%. The implementation of the two‐stage ensemble hybrid CNN with MVU demonstrates significant improvements in brain tumor classification.