CDO-VIB DenseNet: An Improved DenseNet-121 Network for Multi-Label Chest X-ray Disease Classification

Chenxin Pan

doi:10.63313/hmt.9031

Authors

Chenxin Pan Tianjin University of Technology and Education, Tianjin, 300222, China Author

DOI:

https://doi.org/10.63313/hmt.9031

Keywords:

Chestx-Ray14, Densenet-121, CDO-VIB, Multi-Label Classification, Evidential Deep Learning, Variational Information Bottleneck

Abstract

Multi-label chest X-ray classification is challenging because multiple diseases may appear simultaneously, abnormal regions are often subtle, and class distributions are strongly imbalanced. This paper proposes CDO-VIB DenseNet, an improved DenseNet-121 network for ChestX-ray14 classification. The model introduces Dense Squeeze-and-Excitation channel recalibration, Asymmetric Convolution Blocks, and a Class-Decoupled Orthogonal Variational Information Bottleneck head with evidential prediction. Based on available ROC screenshots, the macro-average AUC improves from 0.79 for the DenseNet-121 baseline to 0.81 for the proposed model. The results indicate that disease-specific attention, variational representation compression, and orthogonal global-local fusion are effective for multi-label radiographic classification.

References

[1] Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., & Summers, R. M. (2017). ChestX-ray8: Hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2097-2106. https://doi.org/10.1109/CVPR.2017.369

[2] Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4700-4708. https://doi.org/10.1109/CVPR.2017.243

[3] Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 7132-7141. https://doi.org/10.1109/CVPR.2018.00745

[4] Ding, X., Guo, Y., Ding, G., & Han, J. (2019). ACNet: Strengthening the kernel skeletons for powerful CNN via asymmetric convolution blocks. Proceedings of the IEEE/CVF International Conference on Computer Vision, 1911-1920.

[5] Alemi, A. A., Fischer, I., Dillon, J. V., & Murphy, K. (2017). Deep variational information bottleneck. International Conference on Learning Representations. https://arxiv.org/abs/1612.00410

[6] Sensoy, M., Kaplan, L., & Kandemir, M. (2018). Evidential deep learning to quantify classification uncertainty. Advances in Neural Information Processing Systems, 31, 3179-3189.

[7] Rajpurkar, P., Irvin, J., Zhu, K., Yang, B., Mehta, H., Duan, T., Ding, D., Bagul, A., Langlotz, C., Shpanskaya, K., Lungren, M. P., & Ng, A. Y. (2017). CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning. arXiv:1711.05225.

[8] Yao, L., Poblenz, E., Dagunts, D., Covington, B., Bernard, D., & Lyman, K. (2018). Learning to diagnose from scratch by exploiting dependencies among labels. arXiv:1710.10501.

[9] Irvin, J., Rajpurkar, P., Ko, M., Yu, Y., Ciurea-Ilcus, S., Chute, C., Marklund, H., Haghgoo, B., Ball, R., Shpanskaya, K., Seekins, J., Mong, D. A., Halabi, S. S., Sandberg, J. K., Jones, R., Larson, D. B., Langlotz, C. P., Patel, B. N., Lungren, M. P., & Ng, A. Y. (2019). CheXpert: A large chest radiograph dataset with uncertainty labels and expert comparison. Proceedings of the AAAI Conference on Artificial Intelligence, 33(1), 590-597.

[10] Baltruschat, I. M., Nickisch, H., Grass, M., Knopp, T., & Saalbach, A. (2019). Comparison of deep learning approaches for multi-label chest X-ray classification. Scientific Reports, 9, 6381. https://doi.org/10.1038/s41598-019-42294-8