An End-End Deep Learning Framework for lung infection recognition using Attention-based features and Cross average pooling

Abstract

Diseases like pneumonia, influenza, bronchitis, corona virus (COVID – 19) are some of the major respiratory infections that have made a major impact globally leading to disability and death around the world. Automated detection of lung infections from medical imaging combined with computer vision has a lot of promise for improving healthcare towards COVID-19 and its consequences due to restricted healthcare emergencies. Finding the affected tissues and segmenting them from lung X-ray and CT images is difficult due to comparable neighbouring tissues, hazy boundaries, and unpredictable infections. To overcome these issues, we propose a novel deep learning framework that employs attention-based feature vectors and cross average pooling to detect the lung infection from the images. Multimodal images, after enhancement are processed independently through a pretrained DenseNet where the feature extraction is performed from fully connected and average pooled layers. Instead of assigning equal weight to each feature value in the feature vectors, an attention weight is assigned to each feature to highlight how much attention should be paid to it. The obtained attention-based features are then fused using cross average pooling method to produce a discriminatory feature set leading to improved diagnosis. The fused features are passed through a proposed deep learning modified neural network classifier to diagnose the repository infection. Experiments are performed on the standard Kaggle and Mendeley datasets and the results indicated an average accuracy of 99.2% with appreciable Kappa-index and F1-Score. The results of our DL method for categorising respiratory tract infections we