Deep Learning-Based Automated Pneumonia Detection from Chest X-Rays: A Comparative Study of Custom CNN and Transfer Learning Architectures

Pneumonia is a leading global cause of mortality, claiming approximately 2.5 million lives an-nually and placing exceptional diagnostic pressure on radiologists in resource-limited settings. Manual interpretation of chest X-ray (CXR) images is time-consuming, subject to inter-observer variability, and limited by radiologist availability. This thesis presents a systematic investiga-tion into deep learning-based automated pneumonia detection comparing five convolutional neural network (CNN) architectures: a custom-designed 2D CNN and four pretrained transfer learning models—ResNet, DenseNet, MobileNet, and VGG19. A targeted data augmentation pipeline addresses the severe class imbalance in the Kag-gle Chest X-Ray Pneumonia dataset, expanding the Normal class from 1,583 to 9,495 images using clinically motivated transformations. The proposed Custom CNN incorporates progres-sive multi-scale filters (128→256→512), bottleneck 1×1 convolutions, and calibrated dropout regularization—all tailored for pneumonia-specific feature patterns. Evaluated on 2,066 held-out test images, the Custom CNN achieved the highest test accuracy of 97.5%, with 0.97 precision and recall across both classes and only 52 total misclassifications—outperforming all four transfer learning baselines. These results demonstrate that domain-specific architectural design combined with principled data balancing can surpass generic pretrained models for specialized medical imag-ing tasks on limited datasets.