Abstract

This study proposes an explainable deep learning framework for the automatic detection of pneumonia from chest radiographs. ResNet-50 and EfficientNet-B3 architectures were trained with transfer learning, and class imbalance was addressed with a weighted loss function. Model decisions were visualised with Grad-CAM and LIME and compared with the annotations of two radiologists. The proposed ensemble model achieved 94.1% accuracy and an AUC of 0.97 on the test set. The heat maps overlapped with radiologist annotations by 71% on average, indicating that the model focuses on clinically meaningful regions.

Keywords:pneumoniachest X-raydeep learningexplainable artificial intelligenceGrad-CAM

Full Text

PDF Download · 9.5 KB

Declarations

Ethics Approval
This study does not require ethics committee approval.
Conflict of Interest
The authors declare no conflict of interest.
Funding
This work was supported by the Selçuk University Scientific Research Projects Coordination Unit (Project No: 24000).

References 8

  1. Rajpurkar, P., Irvin, J., Zhu, K., Yang, B., Mehta, H., Duan, T., et al. (2017). CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning. arXiv preprint arXiv:1711.05225.
  2. Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-CAM: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE International Conference on Computer Vision (pp. 618–626). https://doi.org/10.1109/ICCV.2017.74
  3. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 770–778). https://doi.org/10.1109/CVPR.2016.90
  4. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
  5. Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., et al. (2017). A survey on deep learning in medical image analysis. Medical Image Analysis, 42, 60–88. https://doi.org/10.1016/j.media.2017.07.005
  6. Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). "Why should I trust you?": Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1135–1144). https://doi.org/10.1145/2939672.2939778
  7. Tan, M., & Le, Q. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. In Proceedings of the 36th International Conference on Machine Learning (pp. 6105–6114).
  8. Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In International Conference on Learning Representations.

How to Cite

Karaca, E., Tekin, B., & Kurt, O. (2024). An Explainable Deep Learning Approach for Pneumonia Detection in Chest Radiographs. International Journal of Science and Technology Research, 6(1), 1–11. https://doi.org/10.99999/ubtad.2024.1
BibTeX RIS (EndNote, Zotero, Mendeley)

License

CC BY 4.0

© 2024 Elif Karaca, Burak Tekin, Oğuzhan Kurt. This article is distributed under the terms of the CC BY 4.0 license, which permits unrestricted use, distribution and reproduction in any medium, provided the original work is properly cited. License text