Deep Learning Based CNN Model for Automated Detection of Pneumonia from Chest XRay Images

Pneumonia has been one of the major causes of morbidities and mortality in the world and the prevalence of this disease is disproportionately high among the pediatric and elderly populations especially in resources trained areas Fast and precise diagnosis is a prerequisite for successful clinical intervention but due to inter observer variation fatigue among experts and a shortage of qualified radiologists traditional approaches that rely on manual interpretation of chest radiographs are frequently constrained To address these problems this paper introduces a unified automated diagnostic model using a custom Convolutional Neural Network CNN that can recognize pneumonia in chest Xray images with high precision and at minimal computational expense In contrast like other generic transfer learning based models which often possess redundant parameters the offered architecture uses a tailor made depth wise separable convolutional design which is optimized towards textural characteristics of grayscale medical images Contrast Limited Adaptive Histogram Equalization CLAHE and geometric augmentation are two significant preprocessing techniques used to ensure that the system does not experience class imbalance and is more likely to generalize The system is tested using a dataset of 5863 anterior posterior chest Xrays.

💡 Research Summary

**
The paper addresses the critical need for rapid, accurate pneumonia diagnosis from chest X‑ray (CXR) images, especially in resource‑constrained settings where radiologist shortages and observer fatigue lead to delayed or erroneous assessments. Leveraging a publicly available pediatric CXR dataset (Kermany et al.) comprising 5,863 anterior‑posterior images labeled as “Pneumonia” or “Normal,” the authors develop a lightweight, custom‑designed convolutional neural network (CNN) that emphasizes computational efficiency without sacrificing diagnostic performance.

Pre‑processing and Data Augmentation
All images are resized to 150 × 150 pixels, intensity‑scaled to the