Automated diagnosis of childhood pneumonia in chest radiographs using modified densely residual bottleneck-layer features

Abstract

Pneumonia is a severe infection that affects the lungs due to viral or bacterial infections such as the novel COVID-19 virus resulting in mild to critical health conditions. One way to diagnose pneumonia is to screen prospective patient’s lungs using either a Computed Tomography (CT) scan or chest X-ray. To help radiologists in processing a large amount of data especially during pandemics, and to overcome some limitations in deep learning approaches, this paper introduces a new approach that utilizes a few light-weighted densely connected bottleneck residual block features to extract rich spatial information. Then, shrinking data batches into a single vector using four efficient methods. Next, an adaptive weight setup is proposed utilizing Adaboost ensemble learning which adaptively sets weight for each classifier depending on the scores generated to achieve the highest true positive rates while maintaining low negative rates. The proposed method is evaluated using the Kaggle chest X-ray public dataset and attained an accuracy of 99.6% showing superiority to other deep networks-based pneumonia diagnosis methods.