Chest Diagnosis: Pneumonia Detection Model using CNN

Abstract

This paper investigates the application of Convolutional Neural Networks (CNNs) for automated pneumonia detection in chest X-ray images, a critical tool for improving diagnostic accuracy and efficiency in clinical settings. We explore the suitability of CNN architectures, particularly ResNet and VGG16, for extracting informative features from chest X-rays. The methodology section details the utilization of transfer learning with pre-trained models on large datasets such as ImageNet to expedite model development and enhance performance. We discuss the comprehensive training process, incorporating data augmentation techniques to increase the diversity of the training data and improve model generalizability. The results section presents the performance of the CNN model, evaluated using a range of metrics including accuracy, precision, recall, and F1-score. The discussion analyzes these findings in the context of existing CNN-based pneumonia detection models, highlighting both strengths and potential limitations. We also explore future research directions, emphasizing the importance of model interpretability for effective clinical integration and the potential for further advancements in automated diagnostic systems.

Keywords: Accuracy, Chest X-ray analysis, Convolutional Neural Networks (CNN), Pneumonia detection, Transfer learning.

View PDF