3066-280XISSN (Online)
Volume 4 , Issue 1 , PP: 12-20, 2025 | Cite this article as | XML | Html | PDF | Full Length Article
Khaled Sh. Gaber 1 * , Ehsan khodadadi 2
Doi: https://doi.org/10.54216/MOR.040102
Adversarial deep learning has, therefore, been tabled as one of the key research focus areas in neurosciences, and both the opportunities and drawbacks for the operation of deep learning models on neuroimaging and diagnostic jobs have been unveiled. This review examines these models' weaknesses from adversarial attacks, which can severely affect diagnosis and patient care. For example, it has been shown that slight disturbances in the level of EEG signals can confuse more profound learning algorithms employed for the identification of epilepsy, which can lead to severe diagnostic mistakes. In addition, GANs have the dual role of generating realistic neuroimaging data that can improve diagnostic processes while at the same time using adversarial images that expose the deficits of current models. This duality highlights the need to securely defend models against such risks and employ adversarial training and bio-mimic-based resilient neural network techniques. The consequence of these discoveries should not be underestimated because they reveal the necessity of showing further safety in using deep learning techniques in clinical practices. In addressing these weaknesses, the principle goal of this research is not only to help improve the diagnostic systems but also to expand the knowledge on how adversarial deep learning might affect the health, well-being and safety of patients in neuroscience.
Adversarial deep learning , Neuroimaging , Diagnostic accuracy , Generative adversarial networks , Model robustness , Patient safety
[1] Y. Guo, J. Zhang, B. Sun, and Y. Wang, “Adversarial Deep Transfer Learning in Fault Diagnosis: Progress, Challenges, and Future Prospects,” Sensors (Basel), vol. 23, no. 16, p. 7263, Aug. 2023, doi: 10.3390/S23167263.
[2] N. Ghaffari Laleh et al., “Adversarial attacks and adversarial robustness in computational pathology,” Nature Communications, vol. 13, no. 1, pp. 1–10, Sep. 2022, doi: 10.1038/s41467-022-33266-0.
[3] R. Wang et al., “Applications of generative adversarial networks in neuroimaging and clinical neuroscience,” Neuroimage, vol. 269, Apr. 2023, doi: 10.1016/J.NEUROIMAGE.2023.119898.
[4] G. S. Hong et al., “Overcoming the Challenges in the Development and Implementation of Artificial Intelligence in Radiology: A Comprehensive Review of Solutions Beyond Supervised Learning,” Korean J Radiol, vol. 24, no. 11, pp. 1061–1080, Nov. 2023, doi: 10.3348/KJR.2023.0393.
[5] H. Javed, S. El-Sappagh, and T. Abuhmed, “Robustness in deep learning models for medical diagnostics: security and adversarial challenges towards robust AI applications,” Artificial Intelligence Review, vol. 58, no. 1, pp. 1–107, Nov. 2024, doi: 10.1007/S10462-024-11005-9.
[6] I. Y. Chen, E. Pierson, S. Rose, S. Joshi, K. Ferryman, and M. Ghassemi, “Ethical Machine Learning in Healthcare,” Annu Rev Biomed Data Sci, vol. 4, p. 123, May 2021, doi: 10.1146/ANNUREV-BIODATASCI-092820-114757.
[7] H. Arabi, G. Zeng, G. Zheng, and H. Zaidi, “Novel adversarial semantic structure deep learning for MRI-guided attenuation correction in brain PET/MRI,” Eur J Nucl Med Mol Imaging, vol. 46, no. 13, pp. 2746–2759, Dec. 2019, doi: 10.1007/S00259-019-04380-X/TABLES/4.
[8] Y. Li, H. Zhang, C. Bermudez, Y. Chen, B. A. Landman, and Y. Vorobeychik, “Anatomical context protects deep learning from adversarial perturbations in medical imaging,” Neurocomputing, vol. 379, pp. 370–378, Feb. 2020, doi: 10.1016/J.NEUCOM.2019.10.085.
[9] E. Thibeau-Sutre et al., “ClinicaDL: An open-source deep learning software for reproducible neuroimaging processing,” Comput Methods Programs Biomed, vol. 220, p. 106818, Jun. 2022, doi: 10.1016/J.CMPB.2022.106818.
[10] X. Zhang, L. Yao, M. Dong, Z. Liu, Y. Zhang, and Y. Li, “Adversarial Representation Learning for Robust Patient-Independent Epileptic Seizure Detection,” IEEE J Biomed Health Inform, vol. 24, no. 10, pp. 2852–2859, Oct. 2020, doi: 10.1109/JBHI.2020.2971610.
[11] O. Striuk and Y. Kondratenko, “Generative Adversarial Neural Networks and Deep Learning: Successful Cases and Advanced Approaches,” International Journal of Computing, vol. 20, no. 3, pp. 339–349, 2021, doi: 10.47839/ijc.20.3.2278.
[12] H. C. Shin et al., “Medical image synthesis for data augmentation and anonymization using generative adversarial networks,” Lecture Notes in Computer Science, vol. 11037, pp. 1–11, 2018, doi: 10.1007/978-3-030-00536-8_1/TABLES/1.
[13] Y. Yang et al., “High-throughput, high-resolution deep learning microscopy based on registration-free generative adversarial network,” Biomedical Optics Express, vol. 10, no. 3, pp. 1044–1063, Mar. 2019, doi: 10.1364/BOE.10.001044.
[14] T. C. W. Mok and A. C. S. Chung, “Learning data augmentation for brain tumor segmentation with coarse-to-fine generative adversarial networks,” Lecture Notes in Computer Science, vol. 11383, pp. 70–80, 2019, doi: 10.1007/978-3-030-11723-8_7/TABLES/3.
[15] Q. Yao and H. Lu, “Brain functional connectivity augmentation method for mental disease classification with generative adversarial network,” Lecture Notes in Computer Science, vol. 11857, pp. 444–455, 2019, doi 10.1007/978-3-030-31654-9_38/TABLES/4.
[16] X. Gao, H. Liu, F. Shi, D. Shen, and M. Liu, “Brain Status Transferring Generative Adversarial Network for Decoding Individualized Atrophy in Alzheimer’s Disease,” IEEE J Biomed Health Inform, vol. 27, no. 10, pp. 4961–4970, Oct. 2023, doi: 10.1109/JBHI.2023.3304388.
[17] K. Niu et al., “Improving segmentation reliability of multi-scanner brain images using a generative adversarial network,” Quant Imaging Med Surg, vol. 12, no. 3, p. 1775, Mar. 2022, doi: 10.21037/QIMS-21-653.
[18] M. M. Najafabadi, F. Villanustre, T. M. Khoshgoftaar, N. Seliya, R. Wald, and E. Muharemagic, “Deep learning applications and challenges in big data analytics,” J Big Data, vol. 2, no. 1, pp. 1–21, Dec. 2015, doi: 10.1186/S40537-014-0007-7/METRICS.
[19] W. Ko, W. Jung, E. Jeon, and H. Il Suk, “A Deep Generative-Discriminative Learning for Multimodal Representation in Imaging Genetics,” IEEE Trans Med Imaging, vol. 41, no. 9, pp. 2348–2359, Sep. 2022, doi: 10.1109/TMI.2022.3162870.
[20] X. Ma et al., “Understanding adversarial attacks on deep learning based medical image analysis systems,” Pattern Recognit, vol. 110, p. 107332, Feb. 2021, doi: 10.1016/J.PATCOG.2020.107332.
[21] S. Wang, Z. Chen, S. You, B. Wang, Y. Shen, and B. Lei, “Brain stroke lesion segmentation using consistent perception generative adversarial network,” Neural Comput Appl, vol. 34, no. 11, pp. 8657–8669, Jun. 2022, doi: 10.1007/S00521-021-06816-8/METRICS.
[22] P. Chapfuwa et al., “Adversarial Time-to-Event Modeling,” PMLR, Jul. 03, 2018. Accessed: Nov. 12, 2024. [Online]. Available: https://proceedings.mlr.press/v80/chapfuwa18a.html
[23] V. Sovann and C. Thach, “Deep Learning for Neuroimaging: Applications in Brain Disease Diagnosis and Research,” Asian American Research Letters Journal, vol. 1, no. 3, Apr. 2024. Accessed: Nov. 12, 2024. [On
