A Federated Learning-Integrated Autoencoder Model for Robust and Decentralized Pneumonia Detection in Chest X-Rays

A novel pneumonia detection system integrates Federated Learning (FL) with autoencoders to address data scarcity and privacy concerns commonly faced in medical diagnostics.Traditional pneumonia detection relies on supervised learning methods primarily Convolutional Neural Networks (CNNs) and transfer learning which require large, labelled datasets stored centrally, raising significant ethical and privacy challenges.In contrast, the proposed system leverages FL to enable collaborative model training across multiple medical institutions without sharing sensitive patient data.Autoencoders further enhance the model's ability to learn effectively from limited labelled data, improving its generalization in real-world clinical settings.Performance evaluations demonstrate that this approach outperforms existing models in detecting pneumonia from chest X-ray images, achieving superior accuracy, precision, recall, and F1-score.Specifically, the model reaches an accuracy of 95.15%, a precision of 95.8%, and a recall of 98.35%, significantly exceeding results from conventional CNN and transfer learning-based methods.The system not only delivers high diagnostic accuracy but also promotes ethical data handling by eliminating the need for centralized data storage.Overall, this solution addresses the critical limitations of traditional diagnostic frameworks and sets the foundation for secure, privacy-preserving, AI-driven clinical tools.