A hybrid deep learning approach for detecting lung abnormalities from chest X-ray images
,
,
,
and
*
Article Sidebar
Full Text: 
PDF
Main Article Content
Abstract
This paper proposes a hybrid deep learning model for lung abnormalities detection using X-ray images. To improve the performance and accuracy of the model, we use the transfer learning technique with two pre-trained models VGG16 and DenseNet121. Moreover, to extract deeply the feature of lung abnormal, frontal and lateral views of X-ray images have been trained using ensemble technique. The features extracted by these two models will be combined and passed to the classification layer. The experimental results on three datasets demonstrate the effectiveness of the proposed model, which outperforms the individual performance of the two base models, achieving a higher accuracy rate of 89%. Furthermore, in comparative assessments against several alternative models and datasets from previous research, our method demonstrates its efficiency, boasting an impressive AUC value of 0.95. These results underscore the promise of our approach in advancing the accuracy and effectiveness of lung abnormality detection in chest X-ray images.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
References
REFERENCES
Farooq, M., & Hafeez A. (2020). COVID-resnet: A deep learning framework for screening of COVID19 from radiographs. ArXiv, abs/2003.14395.
Gao, H., Zhuang, L., Laurens van der, M., Kilian, Q. W. (2017). Densely connected convolutional networks. CVPR, arXiv:1608.06993.
Ioannis, L., Andreas, K., Panagiotis, P. (2019). Detecting lung abnormalities from X-rays using an improved SSL algorithm. Electronic Notes in Theoretical Computer Science, 343, 19-33.
Jeremy, I., Pranav, R., Michael, K., Yifan, Y., Silviana, C., Chri,s C., Henrik, M., Behzad, H., Robyn, B., Katie, S., Jayne, S., David, A. Mong, Safwan, S. H., Jesse, K. S., Ricky, J., David, B. L., Curtis, P. L., Bhavik, N. P., Matthew, P. L., Andrew, Y. N. (2019). CheXpert: A large chest radiograph dataset with uncertainty labels and expert comparison. Proceedings of the 33rd AAAI Conference on Artificial Intelligence/31st IAAI Conference/9th AAAI Symposium on Educational Advances in Artificial Intelligence, 33, 590–597.
Karen, S., Andrew, Z. (2014). Very deep convolutional networks for large-scale image recognition. CVPR, arXiv:1409.1556.
Li, Y., Eric, P., Dmitry, D., Ben, C., Devon, B., Kevin, L. (2017) Learning to diagnose from scratch by exploiting dependencies among labels. CVPR, arXiv:1701.10501
Mundher, M. T., Ningbo, Z., Talal, A. A., Mohammed, A., Asaad, S. H., Modhi, L. M. (2021). KL- MOB: Automated COVID-19 recognition using a novel approach based on image enhancement and a modified MobileNet CNN. PeerJ Computer Science, 7, e694. https://peerj.com/articles/cs-694
NIH dataset. (2020). CXR8. https://nihcc.app.box.com/v/ChestXray-NIHCC
Pranav, R., Jeremy, I., Kaylie, Z., Matthew, P. L., Andrew, Y. Ng. (2017), CheXNet: Radiologist- level pneumonia detection on chest X-rays with deep learning. ArXiv, 1-7. https://arxiv.org/abs/1711.05225
Rahman, T., Chowdhury, M., Khandakar, A., Islam, K., Islam, K., Mahbub, Z. (2020). Transfer learning with deep convolutional neural network (CNN) for pneumonia detection using chest X-ray. Applied Sciences, 10, 3233.
Sabbir, A., Moi, H. Y., Maxine, T., Md.Kamrul, H. (2020). ReCoNet: multi-level preprocessing of Chest X-rays for COVID-19 detection using convolutional neural networks. Medrxiv, 1-9. https://doi.org/10.1101/2020.07.11.20149112
VinBigData. (2020). Chest X-ray abnormalities detection - automatically localize and classify thoracic abnormalities from chest radiographs. https://www.kaggle.com/competitions/vinbigdata-chest-xray-abnormalities-detection
Xiaosong, W., Yifan, P., Le L., Zhiyong, L., Mohammadhadi, B., & Ronald, M. S. (2017). Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. IEEE Conference on Computer Vision and Pattern Recognition (pp. 2097-2106).