Abstract
In recent years, Generative Adversarial Networks (GAN) have underlined the necessity for exercising caution in trusting digital information. Injection and removal of tumorous nodules from medical imaging modalities is one method of maneuvering deepfakes. The inability to acknowledge medical deepfakes can result in a substantial impact on healthcare procedures or even cause of death. With a systematic case study, this work seeks to address the detection of such assaults in lung CT (Computed Tomography) scans generated using CT-GANs. We experiment with machine learning methods and a novel 3-dimensional deep neural architecture on the topic of differentiating between tampered and untampered data. The proposed architecture on the CT-GAN dataset attained a remarkable accuracy of 91.57%, sensitivity of 91.42%, and specificity of 97.20%. Sectioned data cubes containing the affected region of interest seem to perform better compared to raw CT slices with a gain of approximately 20%. Furthermore, 3DCNN outperforms its 2-dimensional counterpart as it extracts temporal features unlike the spatial relationship insufficient for medical data processing. The outcomes of this research reveal that nodule injection and removal manipulations in complicated CT slices may be recognized with a high degree of precision.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)
Suwajanakorn, S., Seitz, S.M., Kemelmacher-Shlizerman, I.: Synthesizing obama: learning lip sync from audio. ACM Trans. Graph. (ToG) 36(4), 1–13 (2017)
Dolhansky, B., et al.: The deepfake detection challenge (dfdc) dataset. arXiv preprint arXiv:2006.07397 (2020)
Ciftci, U.A., Demir, I., Yin, L.: Fakecatcher: Detection of synthetic portrait videos using biological signals. IEEE Trans. Pattern Anal. Mach. Intell. (2020)
Siegel, D., Kraetzer, C., Seidlitz, S., Dittmann, J.: Media forensics considerations on deepfake detection with hand-crafted features. J. Imaging 7(7), 108 (2021)
Mittal, T., Bhattacharya, U., Chandra, R., Bera, A., Manocha, D.: Emotions don’t lie: An audio-visual deepfake detection method using affective cues. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2823–2832 (2020)
Heo, Y.J., Yeo, W.H., Kim, B.G.: Deepfake detection algorithm based on improved vision transformer. Appli. Intell. 1–16 (2022)
Pu, J., Mangaokar, N., Wang, B., Reddy, C.K., Viswanath, B.: Noisescope: detecting deepfake images in a blind setting. In: Annual Computer Security Applications Conference, pp. 913–927 (2020)
Thambawita, V., et al.: Deepfake electrocardiograms using generative adversarial networks are the beginning of the end for privacy issues in medicine. Sci. Rep. 11(1), 1–8 (2021)
Frid-Adar, M., Diamant, I., Klang, E., Amitai, M., Goldberger, J., Greenspan, H.: Gan-based synthetic medical image augmentation for increased cnn performance in liver lesion classification. Neurocomputing 321, 321–331 (2018)
Ghorbani, A., Natarajan, V., Coz, D., Liu, Y.: Dermgan: Synthetic generation of clinical skin images with pathology. In: Machine Learning for Health Workshop, pp. 155–170. PMLR (2020)
Han, C., et al.: Combining noise-to-image and image-to-image gans: Brain mr image augmentation for tumor detection. IEEE Access 7, 156966–156977 (2019)
Levine, A.B., et al.: Synthesis of diagnostic quality cancer pathology images by generative adversarial networks. J. Pathol. 252(2), 178–188 (2020)
Cao, B., Zhang, H., Wang, N., Gao, X., Shen, D.: Auto-gan: self-supervised collaborative learning for medical image synthesis. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 10486–10493 (2020)
Mangaokar, N., Pu, J., Bhattacharya, P., Reddy, C.K., Viswanath, B.: Jekyll: Attacking medical image diagnostics using deep generative models. In: 2020 IEEE European Symposium on Security and Privacy (EuroS &P), pp. 139–157. IEEE (2020)
Mirsky, Y., Mahler, T., Shelef, I., Elovici, Y.: \(\{\)CT-GAN\(\}\): Malicious tampering of 3d medical imagery using deep learning. In: 28th USENIX Security Symposium (USENIX Security 2019), pp. 461–478 (2019)
Solaiyappan, S., Wen, Y.: Machine learning based medical image deepfake detection: A comparative study. Mach. Learn. Appli. 8, 100298 (2022)
Armato, S.G., III., et al.: The lung image database consortium (lidc) and image database resource initiative (idri): a completed reference database of lung nodules on ct scans. Med. Phys. 38(2), 915–931 (2011)
Acknowledgements
The authors would like to thank all members of the MIR (Machine Intelligence Research) group, who have immensely provided all support during the various stages of the study. The authors also thank University of Kerala for providing the infrastructure required for the study.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sharafudeen, M., Vinod Chandra, S.S. (2023). Medical Deepfake Detection using 3-Dimensional Neural Learning. In: El Gayar, N., Trentin, E., Ravanelli, M., Abbas, H. (eds) Artificial Neural Networks in Pattern Recognition. ANNPR 2022. Lecture Notes in Computer Science(), vol 13739. Springer, Cham. https://doi.org/10.1007/978-3-031-20650-4_14
Download citation
DOI: https://doi.org/10.1007/978-3-031-20650-4_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20649-8
Online ISBN: 978-3-031-20650-4
eBook Packages: Computer ScienceComputer Science (R0)