X-ray image classification with dual-model information fusion and improved PSO algorithm

A Dual-model improved PSO (DMIPS) hybrid model architecture that integrates a custom-designed deep convolutional model with a pre-trained ResVGG16 model having residual connections for more accurate lung CXR image classification, and an improved particle swarm optimization (IPSO) algorithm with an exclusion strategy for data fusion to reduce model variance and bias and enhance prediction performance is proposed.