Medical Anomaly Detection Using Generative Adversarial Network With Self Attention Mechanism
Loading...
Date
Journal Title
Journal ISSN
Volume Title
Publisher
Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh
Abstract
Anomaly detection in medical imaging plays a vital role in assisting early diagnosis
and treatment. Traditional supervised methods rely heavily on annotated abnormal
samples, which are often scarce and diverse, making them impractical for real-world
deployment. This work explores unsupervised anomaly detection using a range of
GAN-based frameworks, where models learn to capture the distribution of normal
data and identify deviations without the need for labeled outliers. Various architec
tures, including reconstruction-based and feature-matching approaches, are evalu
ated and extended with enhancements such as self-attention mechanisms and posi
tional encodings to improve spatial feature learning. Extensive experiments on medi
cal imaging datasets demonstrate that the proposed techniques significantly improve
detection performance, highlighting the effectiveness of adversarial learning for un
supervised medical anomaly detection.
Description
Supervised by
Dr. Md. HasanulKabir,
Professor,
Mr. Md. Bakhtiar Hasan,
Assistant Professor,
Department of Computer Science and Engineering (CSE)
Islamic University of Technology (IUT)
Board Bazar, Gazipur, Bangladesh
This thesis is submitted in partial fulfillment of the requirement for the degree of Bachelor of Science in Computer Science and Engineering, 2025
Keywords
Citation
[1] S.Akcay,A.Atapour-Abarghouei,andT.P.Breckon,“Ganomaly:Semi-supervised anomaly detection via adversarial training,” arXiv preprint arXiv:1805.06725, 2018. [Online]. Available: https://arxiv.org/abs/1805.06725 [2] M. Arjovsky, S. Chintala, and L. Bottou, “Wasserstein generative adversarial networks,” arXiv preprint arXiv:1701.07875, 2017. [Online]. Available: https: //arxiv.org/abs/1701.07875 [3] Z.Dai,Z.Yang,Y.Yang,J.Carbonell,Q.V.Le,andR.Salakhutdinov,Transformer xl: Attentive language models beyond a fixed-length context, 2019. arXiv: 1901. 02860 [cs.LG]. [Online]. Available: https://arxiv.org/abs/1901.02860 [4] P. Isola, J.-Y. Zhu, T. Zhou, and A. A. Efros, “Image-to-image translation with conditional adversarial networks,” arXiv preprint arXiv:1611.07004, 2017. [On line]. Available: https://arxiv.org/abs/1611.07004 [5] O.Press, N. A. Smith, and M. Lewis, Train short, test long: Attention with linear biases enables input length extrapolation, 2022. arXiv: 2108.12409 [cs.CL]. [Online]. Available: https://arxiv.org/abs/2108.12409 [6] A. Radford, L. Metz, and S. Chintala, “Unsupervised representation learning withdeepconvolutionalgenerativeadversarialnetworks,”arXivpreprintarXiv:1511.06434, 2015. [Online]. Available: https://arxiv.org/abs/1511.06434 [7] M.Sabokrou,M.Khalooei, M. Fathy, and E. Adeli, “Adversarially learned one class classifier for novelty detection,” CoRR, vol. abs/1802.09088, 2018. [On line]. Available: http://arxiv.org/abs/1802.09088 [8] T. Salimans, I. Goodfellow, W. Zaremba, V. Cheung, A. Radford, and X. Chen, “Improvedtechniquesfortraininggans,”arXivpreprintarXiv:1606.03498,2016. [Online]. Available: https://arxiv.org/abs/1606.03498 [9] T.Schlegl, P. Seeböck, S. M. Waldstein, U. Schmidt-Erfurth, and G. Langs, “Un supervised anomaly detection with generative adversarial networks to guide marker discovery,” CoRR, vol. abs/1703.05921, 2017. [Online]. Available: http: //arxiv.org/abs/1703.05921 59 [10] M.M.R.Siddiquee, J. Cho, A. K. Mondal, and T. F. Syeda-Mahmood, “Braino maly:Unsupervisedneurologicdiseasedetectionutilizingunannotatedt1-weighted brain mr images,” in Proceedings of the IEEE/CVF Winter Conference on Appli cations of Computer Vision, 2024, pp. 8527–8536. [Online]. Available: https: //pmc.ncbi.nlm.nih.gov/articles/PMC11078334/ [11] J.Su,Y.Lu,S.Pan,A.Murtadha,B.Wen,andY.Liu,Roformer:Enhancedtrans former with rotary position embedding, 2023. arXiv: 2104.09864 [cs.CL]. [On line]. Available: https://arxiv.org/abs/2104.09864 [12] Y.Sun, N.Zhao, and E. Adeli, “Healthygan: Learning from unannotated medi cal images to detect anomalies associated with human disease,” Medical Imag ing with Deep Learning, 2022. [Online]. Available: https://pmc.ncbi.nlm. nih.gov/articles/PMC11062325/ [13] A. Vaswani et al., Attention is all you need, 2023. arXiv: 1706.03762 [cs.CL]. [Online]. Available: https://arxiv.org/abs/1706.03762 [14] H.Zenati, M. Romain, C. S. Foo, B. Lecouat, and V. R. Chandrasekhar, “Adver sarially learned anomaly detection,” CoRR,vol.abs/1812.02288,2018.[Online]. Available: http://arxiv.org/abs/1812.02288 [15] Z.Zhangetal., Spatial-aware attention generative adversarial network for semi supervisedanomalydetectioninmedicalimage,2024.arXiv:2405.12872[eess.IV]. [Online]. Available: https://arxiv.org/abs/2405.12872