Oltu Burcu, Güney Selda, Yuksel Seniha Esen, Dengiz Berna
Department of Biomedical Engineering, Baskent University, Etimesgut, Ankara, 06790, Türkiye.
Department of Electrical and Electronics Engineering, Baskent University, Etimesgut, Ankara, 06790, Türkiye.
BMC Med Imaging. 2025 Mar 4;25(1):71. doi: 10.1186/s12880-025-01604-5.
Pulmonary diseases such as COVID-19 and pneumonia, are life-threatening conditions, that require prompt and accurate diagnosis for effective treatment. Chest X-ray (CXR) has become the most common alternative method for detecting pulmonary diseases such as COVID-19, pneumonia, and lung opacity due to their availability, cost-effectiveness, and ability to facilitate comparative analysis. However, the interpretation of CXRs is a challenging task.
This study presents an automated deep learning (DL) model that outperforms multiple state-of-the-art methods in diagnosing COVID-19, Lung Opacity, and Viral Pneumonia. Using a dataset of 21,165 CXRs, the proposed framework introduces a seamless combination of the Vision Transformer (ViT) for capturing long-range dependencies, DenseNet201 for powerful feature extraction, and global average pooling (GAP) for retaining critical spatial details. This combination results in a robust classification system, achieving remarkable accuracy.
The proposed methodology delivers outstanding results across all categories: achieving 99.4% accuracy and an F1-score of 98.43% for COVID-19, 96.45% accuracy and an F1-score of 93.64% for Lung Opacity, 99.63% accuracy and an F1-score of 97.05% for Viral Pneumonia, and 95.97% accuracy with an F1-score of 95.87% for Normal subjects.
The proposed framework achieves a remarkable overall accuracy of 97.87%, surpassing several state-of-the-art methods with reproducible and objective outcomes. To ensure robustness and minimize variability in train-test splits, our study employs five-fold cross-validation, providing reliable and consistent performance evaluation. For transparency and to facilitate future comparisons, the specific training and testing splits have been made publicly accessible. Furthermore, Grad-CAM-based visualizations are integrated to enhance the interpretability of the model, offering valuable insights into its decision-making process. This innovative framework not only boosts classification accuracy but also sets a new benchmark in CXR-based disease diagnosis.
诸如新冠病毒病和肺炎等肺部疾病是危及生命的病症，需要迅速且准确的诊断以进行有效治疗。胸部X光（CXR）因其可用性、成本效益以及便于进行对比分析的能力，已成为检测新冠病毒病、肺炎以及肺部模糊等肺部疾病最常用的替代方法。然而，对胸部X光片的解读是一项具有挑战性的任务。
本研究提出了一种自动化深度学习（DL）模型，该模型在诊断新冠病毒病、肺部模糊和病毒性肺炎方面优于多种先进方法。利用一个包含21165张胸部X光片的数据集，所提出的框架引入了用于捕捉长程依赖关系的视觉Transformer（ViT）、用于强大特征提取的DenseNet201以及用于保留关键空间细节的全局平均池化（GAP）的无缝组合。这种组合产生了一个强大的分类系统，实现了显著的准确率。
所提出的方法在所有类别中都取得了出色的结果：新冠病毒病的准确率达到99.4%，F1分数为98.43%；肺部模糊的准确率为96.45%，F1分数为93.64%；病毒性肺炎的准确率为99.63%，F1分数为97.05%；正常受试者的准确率为95.97%，F1分数为95.87%。
所提出的框架实现了97.87%的显著总体准确率，超过了多种先进方法，具有可重复和客观的结果。为确保稳健性并最小化训练 - 测试分割中的变异性，我们的研究采用了五折交叉验证，提供了可靠且一致的性能评估。为了提高透明度并便于未来比较，特定的训练和测试分割已公开可用。此外，基于Grad-CAM的可视化被整合以增强模型的可解释性，为其决策过程提供有价值的见解。这个创新框架不仅提高了分类准确率，还在基于胸部X光的疾病诊断中树立了新的标杆。
