⚡ Quick Summary
This study introduces the LungMaxViT, an explainable hybrid transformer designed for the multi-classification of lung diseases using chest X-rays. The model achieved an impressive classification accuracy of 96.8% on the COVID-19 dataset, showcasing its potential in enhancing clinical diagnostics. 🌟
🔍 Key Details
- 📊 Datasets Used: Two public datasets, including COVID-19 and Chest X-ray 14.
- 🧩 Model Architecture: Hybrid transformer combining CNN and SE blocks.
- ⚙️ Technology: LungMaxViT, pre-trained with ImageNet 1K datasets.
- 🏆 Performance Metrics: Accuracy: 96.8%, AUC: 98.3%, F1-score: 96.7% (COVID-19 dataset).
🔑 Key Takeaways
- 🌟 LungMaxViT outperformed classical models like ResNet50 and MobileNetV2.
- 📈 AUC scores of 98.3% and 93.2% demonstrate its effectiveness in disease detection.
- 🔍 Grad-CAM visual technique was utilized for interpretability in model predictions.
- 🛠️ Enhancement techniques such as CLAHE and denoising were applied to improve performance.
- 💡 The model shows robust generalization in detecting multiple lung lesions.
- 🌍 Study conducted by a team of researchers including Fu X and Lin R.
- 📅 Published in: Sci Rep, 2025.
📚 Background
Lung diseases are a leading cause of mortality worldwide, often requiring timely and accurate diagnosis for effective treatment. Traditional diagnostic methods can be costly and time-consuming. The advent of deep learning technologies, particularly in analyzing chest X-ray images, offers a promising alternative for rapid and reliable lung disease detection.
🗒️ Study
The study aimed to develop an innovative model, LungMaxViT, which integrates a hybrid network structure to enhance feature recognition in chest X-ray images. By leveraging transfer learning and fine-tuning hyperparameters, the researchers compared the performance of LungMaxViT against four classical pre-training models across two public datasets.
📈 Results
The LungMaxViT model achieved remarkable results, with a classification accuracy of 96.8% and AUC scores of 98.3% on the COVID-19 dataset. In contrast, it recorded AUC scores of 93.2% and F1 scores of 70.7% on the Chest X-ray 14 dataset, indicating its superior performance in lung disease classification.
🌍 Impact and Implications
The findings from this study could significantly impact clinical practices by providing a cost-effective and efficient tool for lung disease diagnosis. The integration of explainable AI through techniques like Grad-CAM enhances trust and understanding among healthcare professionals, paving the way for broader adoption of AI technologies in medical imaging.
🔮 Conclusion
The LungMaxViT model represents a significant advancement in the field of medical imaging for lung disease classification. Its high accuracy and interpretability suggest a promising future for AI in healthcare, particularly in enhancing diagnostic processes. Continued research and development in this area could lead to even more effective tools for clinicians. 🚀
💬 Your comments
What are your thoughts on the use of AI in diagnosing lung diseases? We would love to hear your insights! 💬 Share your comments below or connect with us on social media:
Explainable hybrid transformer for multi-classification of lung disease using chest X-rays.
Abstract
Lung disease is an infection that causes chronic inflammation of the human lung cells, which is one of the major causes of death around the world. Thoracic X-ray medical image is a well-known cheap screening approach used for lung disease detection. Deep learning networks, which are used to identify disease features in X-rays medical images, diagnosing a variety of lung diseases, are playing an increasingly important role in assisting clinical diagnosis. This paper proposes an explainable transformer with a hybrid network structure (LungMaxViT) combining CNN initial stage block with SE block to improve feature recognition for predicting Chest X-ray images for multiple lung disease classification. We contrast four classical pre-training models (ResNet50, MobileNetV2, ViT and MaxViT) through transfer learning based on two public datasets. The LungMaxVit, based on maxvit pre-trained with ImageNet 1K datasets, is a hybrid transformer with fine-tuning hyperparameters on the both X-ray datasets. The LungMaxVit outperforms all the four mentioned models, achieving a classification accuracy of 96.8%, AUC scores of 98.3%, and F1 scores of 96.7% on the COVID-19 dataset, while AUC scores of 93.2% and F1 scores of 70.7% on the Chest X-ray 14 dataset. The LungMaxVit distinguishes by its superior performance in terms of Accuracy, AUC and F1-score compared with other hybrids Networks. Several enhancement techniques, such as CLAHE, flipping and denoising, are employed to improve the classification performance of our study. The Grad-CAM visual technique is leveraged to represent the heat map of disease detection, explaining the consistency among clinical doctors and neural network models in the treatment of lung disease from Chest X-ray. The LungMaxVit shows the robust results and generalization in detecting multiple lung lesions and COVID-19 on Chest X-ray images.
Author: [‘Fu X’, ‘Lin R’, ‘Du W’, ‘Tavares A’, ‘Liang Y’]
Journal: Sci Rep
Citation: Fu X, et al. Explainable hybrid transformer for multi-classification of lung disease using chest X-rays. Explainable hybrid transformer for multi-classification of lung disease using chest X-rays. 2025; 15:6650. doi: 10.1038/s41598-025-90607-x