This study presents an approach for classifying lung diseases using a tailored convolutional neural network (CNN) that combines several chest X-ray (CXR) datasets and applies extensive data augmentation to build a balanced dataset and improve generalization.
Abstract
The global spread of COVID-19 has affected health and economic conditions worldwide, and new variants continue to appear despite the availability of vaccines. These variants share a common effect on the respiratory system, which keeps pulmonary disease detection a major priority. This study presents an approach for classifying lung diseases using a tailored convolutional neural network (CNN). The system combines several chest X-ray (CXR) datasets and applies extensive data augmentation to build a balanced dataset and improve generalization. The model distinguishes five classes: Normal, COVID-19, Tuberculosis, Viral Pneumonia, and Bacterial Pneumonia. Cross-validation ensures more stable performance and reduces overfitting risks. The method uses the AdamW optimizer to improve convergence and training stability. Performance evaluation includes confusion matrix indicators such as accuracy, specificity, precision, sensitivity, and F1-score, along with ROC curves. The results show that the method is reliable and efficient for automatic classification of CXR images. The CNN model had an average accuracy of 95.26% and a macro-AUC of 99.32% across five folds. Our model is implemented on the TensorFlow framework with the datasets that are public and available for the research community.
The proposed deep learning models provide an efficient and accurate tool for multiclass pneumonia detection from CXR images and have the potential to support healthcare professionals in making more accurate diagnoses.
Timothy Karani, Stephen Waithaka· Journal of the Kenya Nationa...· 0 citations
Background: Deep learning models, particularly convolutional neural networks (CNNs), have shown promising performance for pneumonia detection using chest X-ray images. However, the impact of preprocessing, architecture selection, data augmentation, and ensemble strategies has not been systematically evaluated. This study investigated how these factors affect model robustness and diagnostic performance. Methods: A public pediatric chest X-ray dataset was used to systematically evaluate pixel normalization methods, six CNN architectures, progressive data augmentation strategies for class imbalance, and both feature-level and decision-level ensemble approaches. Model performance was assessed by considering not only overall classification accuracy but also clinically relevant risk metrics, particularly false-negative rates. Results: Pixel normalization to the 0–1 range improved model convergence, while Xception and InceptionV3 achieved the best overall performance. Model-specific augmentation strategies were more effective than a fixed 1:1 class ratio for reducing false negatives. Feature-level ensembles tended to overfit, whereas decision-level ensembles provided more stable but only modest performance improvements. Conclusions: These findings demonstrate that reliable medical AI systems require systematic optimization of preprocessing techniques, model architecture, data augmentation strategies, and clinically meaningful evaluation metrics rather than maximizing a single performance indicator. The proposed framework provides practical guidelines for developing robust deep learning models for pneumonia diagnosis in clinical settings.
YongJun Kim, Ji-Yeoun Lee· BioMedInformatics· 0 citations
A hybrid ensemble learning approach to classify chest X-ray images into four classes—Normal, COVID-19, Pneumonia, and Tuberculosis exhibited high sensitivity in detecting Tuberculosis with considerable stability in classifying Normal, COVID-19, and Pneumonia.
Abdul Rehman Khan Tareen, Muhammad Laiq Ur Rahman Shahid, Muhammad Hamza Zafar et al.· Allied Medical Research Jour...· 0 citations
: Pneumonia continues to be a major source of morbidity and mortality globally, especially in developing countries where a shortage of specialists makes radiological assessment challenging. Patients' survival and appropriate treatment depend on a timely and accurate diagnosis. This study examines a deep learning technique called a Convolutional Neural Network (CNN) that looks at chest X-rays to identify pneumonia. To accurately classify normal and pneumonia-infected lungs, the proposed system makes use of sophisticated picture preprocessing, data augmentation, and improved CNNs to find discriminative spatial characteristics. Using pre-trained models like VGG16, ResNet50, and DenseNet121, it also investigated transfer learning to improve model performance and generalization with little datasets. The CNN model demonstrated 96.8 accuracy, 95.6 precision, 97.3 recall, and 96.4 F1-score on the publicly available Chest X-Ray (Pneumonia) dataset. The results suggest that CNN-based models have the capacity to aid radiologists in the early diagnosis to ease the medical intervention and minimize diagnostic errors. This study is part of the developing body of AI-based healthcare diagnostics, and it highlights the possibility of deep learning in medical image processing and disease prediction.
M. Devi, Tanya, Aradhya Mittal et al.· Proceedings of the 1st Inter...· 0 citations
Lung disease remains a major global health concern, and accurate diagnosis using chest X-ray images plays a crucial role in supporting effective clinical decision-making. The contribution of this work lies in empirically demonstrating how internal redundancy removal through standard magnitude-based pruning can improve both performance and stability of an established CNN architecture. The COVID-Qu-Ex dataset was utilized, consisting of 11,956 COVID, 11,263 pneumonia, and 10,701 normal X-ray images. All models were trained under identical preprocessing, augmentation, and evaluation protocols, with three different random seeds to ensure result stability and reproducibility. Experimental results show that the pruned InceptionV3 model achieved superior performance, with an accuracy of 95.54% ± 0.0041, precision of 95.62% ± 0.0039, recall of 95.54% ± 0.0041, and F1-score of 95.54% ± 0.0041, outperforming the baseline InceptionV3 as well as other modern CNN architectures such as ResNet101 and VGG19. These findings demonstrate that network pruning can effectively reduce model redundancy while maintaining, and even improving, classification performance. Future work will focus on extending the proposed approach to other CNN architectures, integrating interpretability techniques, and addressing data imbalance issues to enhance clinical reliability.
Joshua Pinem, Widi Astuti, A. Adiwijaya· International Conference on...· 0 citations
A deep learning-based system that uses chest X-ray pictures to automatically detect tuberculosis, using transfer learning using MobileNetV2 and DenseNet architectures to classify chest Xrays as either TB-positive or Healthy, reaching notable accuracy.
Zoya Nasreen, Afshan Fatima, Ruqiya Fatima· International Journal of AI...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
