A Federated Learning-Integrated Autoencoder Model for Robust and Decentralized Pneumonia Detection in Chest X-Rays
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".