Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Dynamic Perturbation-Adaptive Adversarial Training on Medical Image Classification (2403.06798v1)

Published 11 Mar 2024 in eess.IV, cs.CV, and cs.LG

Abstract: Remarkable successes were made in Medical Image Classification (MIC) recently, mainly due to wide applications of convolutional neural networks (CNNs). However, adversarial examples (AEs) exhibited imperceptible similarity with raw data, raising serious concerns on network robustness. Although adversarial training (AT), in responding to malevolent AEs, was recognized as an effective approach to improve robustness, it was challenging to overcome generalization decline of networks caused by the AT. In this paper, in order to reserve high generalization while improving robustness, we proposed a dynamic perturbation-adaptive adversarial training (DPAAT) method, which placed AT in a dynamic learning environment to generate adaptive data-level perturbations and provided a dynamically updated criterion by loss information collections to handle the disadvantage of fixed perturbation sizes in conventional AT methods and the dependence on external transference. Comprehensive testing on dermatology HAM10000 dataset showed that the DPAAT not only achieved better robustness improvement and generalization preservation but also significantly enhanced mean average precision and interpretability on various CNNs, indicating its great potential as a generic adversarial training method on the MIC.

View on arXiv
Definition Search Book Streamline Icon: https://streamlinehq.com
References (32)
  1. S. K. Zhou, H. Greenspan, C. Davatzikos, J. S. Duncan, B. Van Ginneken, A. Madabhushi, J. L. Prince, D. Rueckert, and R. M. Summers, “A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises,” Proceedings of the IEEE, vol. 109, no. 5, pp. 820–838, 2021.
  2. S. K. Datta, M. A. Shaikh, S. N. Srihari, and M. Gao, “Soft attention improves skin cancer classification performance,” in Interpretability of Machine Intelligence in Medical Image Computing, and Topological Data Analysis and Its Applications for Medical Data, pp. 13–23, Springer, 2021.
  3. M. Anthimopoulos, S. Christodoulidis, L. Ebner, A. Christe, and S. Mougiakakou, “Lung pattern classification for interstitial lung diseases using a deep convolutional neural network,” IEEE transactions on medical imaging, vol. 35, no. 5, pp. 1207–1216, 2016.
  4. S. Pereira, A. Pinto, V. Alves, and C. A. Silva, “Brain tumor segmentation using convolutional neural networks in mri images,” IEEE transactions on medical imaging, vol. 35, no. 5, pp. 1240–1251, 2016.
  5. H. Zunair and A. B. Hamza, “Melanoma detection using adversarial training and deep transfer learning,” Physics in Medicine & Biology, vol. 65, no. 13, p. 135005, 2020.
  6. I. A. Bratchenko, L. A. Bratchenko, Y. A. Khristoforova, A. A. Moryatov, S. V. Kozlov, and V. P. Zakharov, “Classification of skin cancer using convolutional neural networks analysis of raman spectra,” Computer Methods and Programs in Biomedicine, vol. 219, p. 106755, 2022.
  7. P. Yao, S. Shen, M. Xu, P. Liu, F. Zhang, J. Xing, P. Shao, B. Kaffenberger, and R. X. Xu, “Single model deep learning on imbalanced small datasets for skin lesion classification,” IEEE transactions on medical imaging, vol. 41, no. 5, pp. 1242–1254, 2021.
  8. C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. Goodfellow, and R. Fergus, “Intriguing properties of neural networks,” arXiv preprint arXiv:1312.6199, 2013.
  9. A. Madry, A. Makelov, L. Schmidt, D. Tsipras, and A. Vladu, “Towards deep learning models resistant to adversarial attacks,” arXiv preprint arXiv:1706.06083, 2017.
  10. M. Zorzi, “Robust kalman filtering under model perturbations,” IEEE Transactions on Automatic Control, vol. 62, no. 6, pp. 2902–2907, 2016.
  11. K. Grosse, P. Manoharan, N. Papernot, M. Backes, and P. McDaniel, “On the (statistical) detection of adversarial examples,” arXiv preprint arXiv:1702.06280, 2017.
  12. F. Mahmood, R. Chen, and N. J. Durr, “Unsupervised reverse domain adaptation for synthetic medical images via adversarial training,” IEEE transactions on medical imaging, vol. 37, no. 12, pp. 2572–2581, 2018.
  13. C. Yoo, X. Liu, F. Xing, G. El Fakhri, J. Woo, and J.-W. Kang, “Noise-robust sleep staging via adversarial training with an auxiliary model,” IEEE Transactions on Biomedical Engineering, 2022.
  14. I. J. Goodfellow, J. Shlens, and C. Szegedy, “Explaining and harnessing adversarial examples,” arXiv preprint arXiv:1412.6572, 2014.
  15. D. Tsipras, S. Santurkar, L. Engstrom, A. Turner, and A. Madry, “Robustness may be at odds with accuracy,” arXiv preprint arXiv:1805.12152, 2018.
  16. S. Tang, X. Huang, M. Chen, C. Sun, and J. Yang, “Adversarial attack type i: Cheat classifiers by significant changes,” IEEE transactions on pattern analysis and machine intelligence, vol. 43, no. 3, pp. 1100–1109, 2019.
  17. L. Ma and L. Liang, “Adaptive adversarial training to improve adversarial robustness of dnns for medical image segmentation and detection,” arXiv preprint arXiv:2206.01736, 2022.
  18. Y. Balaji, T. Goldstein, and J. Hoffman, “Instance adaptive adversarial training: Improved accuracy tradeoffs in neural nets,” arXiv preprint arXiv:1910.08051, 2019.
  19. Z. Nie, Y. Lin, S. Ren, and L. Zhang, “Adaptive perturbation adversarial training: based on reinforcement learning,” arXiv preprint arXiv:2108.13239, 2021.
  20. A. Salih, I. Boscolo Galazzo, P. Gkontra, A. M. Lee, K. Lekadir, Z. Raisi-Estabragh, and S. E. Petersen, “Explainable artificial intelligence and cardiac imaging: Toward more interpretable models,” Circulation: Cardiovascular Imaging, p. e014519, 2023.
  21. S. Bai, Y. Li, Y. Zhou, Q. Li, and P. H. Torr, “Adversarial metric attack and defense for person re-identification,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 6, pp. 2119–2126, 2020.
  22. S. Yang and C. Xu, “One size does not fit all: Data-adaptive adversarial training,” in European Conference on Computer Vision, pp. 70–85, Springer, 2022.
  23. J. Cui, S. Liu, L. Wang, and J. Jia, “Learnable boundary guided adversarial training,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 15721–15730, 2021.
  24. C. Cortes and V. Vapnik, “Support-vector networks,” Machine learning, vol. 20, no. 3, pp. 273–297, 1995.
  25. P. Tschandl, C. Rosendahl, and H. Kittler, “The ham10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions,” Scientific data, vol. 5, no. 1, pp. 1–9, 2018.
  26. A. Margeloiu, N. Simidjievski, M. Jamnik, and A. Weller, “Improving interpretability in medical imaging diagnosis using adversarial training,” arXiv preprint arXiv:2012.01166, 2020.
  27. A. Mustafa, S. H. Khan, M. Hayat, R. Goecke, J. Shen, and L. Shao, “Deeply supervised discriminative learning for adversarial defense,” IEEE transactions on pattern analysis and machine intelligence, vol. 43, no. 9, pp. 3154–3166, 2020.
  28. T. Lei, D. Zhang, X. Du, X. Wang, Y. Wan, and A. K. Nandi, “Semi-supervised medical image segmentation using adversarial consistency learning and dynamic convolution network,” IEEE Transactions on Medical Imaging, 2022.
  29. X. Wang, Y. Chen, and W. Zhu, “A survey on curriculum learning,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021.
  30. Q. Yao, Z. He, H. Han, and S. K. Zhou, “Miss the point: Targeted adversarial attack on multiple landmark detection,” in Medical Image Computing and Computer Assisted Intervention – MICCAI 2020 (A. L. Martel, P. Abolmaesumi, D. Stoyanov, D. Mateus, M. A. Zuluaga, S. K. Zhou, D. Racoceanu, and L. Joskowicz, eds.), (Cham), pp. 692–702, Springer International Publishing, 2020.
  31. R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, “Grad-cam: Visual explanations from deep networks via gradient-based localization,” in Proceedings of the IEEE international conference on computer vision, pp. 618–626, 2017.
  32. A dataset for breast cancer histopathological image classification. Ieee transactions on biomedical engineering, 63(7):1455–1462, 2015.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Shuai Li (295 papers)
  2. Xiaoguang Ma (14 papers)
  3. Shancheng Jiang (2 papers)
  4. Lu Meng (69 papers)

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now