Heuristically Modified Attention Residual Network Aided Pulmonary Emphysema Detection with Adaptive Pre-processing and Deep Unet-Based Segmentation

Pulmonary emphysema is one of the lung disorders that are caused owing to the uncharacteristic enhancement of alveoli. Some early emphysema detection medical analyses are CT scanning and spirometry to minimize mortality. Thus, to resolve the drawbacks presented in the existing approach, a new pulmonary emphysema detection model will be developed in this paper. Initially, the required images related to pulmonary emphysema were collected from standard resources and fed to pre-processing stage. Further, the pre-processing is done with Gabor filtering, adaptive contrast and histogram equalization. The parameters of adaptive contrast and histogram equalization are tuned by utilizing a developed hybrid approach named Hybrid Mud Ring Tunicate Swarm Algorithm (H-MRTSA). Additionally, the pre-processed images are offered to the phase of segmentation, where it is performed using the Deep U-net model. Further, the input segmented images are given to the pulmonary emphysema disease detection region. In this phase, pulmonary emphysema is detected using an Attention-based Residual Network (A-ResNet), in which the parameters in the network are tuned using MR-TSA. The performance of the developed H-MRTSA-A-ResNet model achieves superior performance like 97% and 98% concerning accuracy and precision. Thus, the developed pulmonary emphysema disease detection approach achieves an improved disease identification rate than the conventional approaches through experimental analysis.