FOREX Press I. J. of Electrical & Electronics Research
Support Open Access
  • Home/
  • IJEER-130321

Research Article |

Chest X-ray Abnormality Detection Using Convolutional AutoEncoder Combined with Double Generative Adversarial Network (GAN)

Author(s): Tan Yanli1,2, Azliza Mohd Ali2*, Sharifalillah Nordin2, Wang Jin1,2, Li Guoqin1,2

Published In : International Journal of Electrical and Electronics Research (IJEER)        Volume 13, issue 3

Publisher : FOREX Publication

Published : 30 September 2025

e-ISSN : 2347-470X

Page(s) : 563-571

DOI: https://doi.org/10.37391/IJEER.130321

Abstract

The statistical properties of aberrant samples are unstable, and traditional chest X-ray image data is difficult to gather and unevenly distributed. A CAE-D-GAN anomaly detection model based on dual GANs and convolutional autoencoders is proposed in this paper. We employ the DGAN module to obtain clear degraded images, the convolutional autoencoder to extract low-dimensional features from high-dimensional data, and the DDGAN module to learn how to degrade images and recover clearer images from degraded photos during the adversarial process. While the reconstruction error score identifies sample flaws, the network is optimized by the error loss between the original and reconstructed samples. The network just needs normal samples to be trained, and it can reach a maximum AUROC value of 0.86. The findings demonstrate that the CAE-D-GAN model outperforms a number of different anomaly detection models in terms of detection effects and feature reconstruction capabilities. There are special opportunities for using this approach to detect other anomalies in medical images.

Keywords: Abnormal detection, , Autoencoder, CAE-D-GAN, Reconstruction loss, Anomaly score.




Tan Yanli, Department of Electronic Engineering, Taiyuan Institute of Technology, Taiyuan, Shanxi, China; College of Computing, Informatics and Mathematics, Universiti Teknologi MARA, Malaysia; Email: tanyanli@studysedu.cn

Azliza Mohd Ali*, College of Computing, Informatics and Mathematics, Universiti Teknologi MARA, Malaysia; Email: azliza@tmsk.uitm.edu.my

Sharifalillah Nordin, College of Computing, Informatics and Mathematics, Universiti Teknologi MARA, Malaysia

Wang Jin, Department of Electronic Engineering, Taiyuan Institute of Technology, Taiyuan, Shanxi, China; College of Computing, Informatics and Mathematics, Universiti Teknologi MARA, Malaysia

Li Guoqin, Department of Electronic Engineering, Taiyuan Institute of Technology, Taiyuan, Shanxi, China; College of Computing, Informatics and Mathematics, Universiti Teknologi MARA, Malaysia

    [1] Li P, Pei Y, Li J. A comprehensive survey on design and application of autoencoder in deep learning[J]. Applied Soft Computing, 2023, 138: 110176.
    [2] Zhao P, Ding Z, Li Y, et al. SGAD-GAN: Simultaneous Generation and Anomaly Detection for time-series sensor data with Generative Adversarial Networks[J]. Mechanical Systems and Signal Processing, 2024, 210: 111141.
    [3] Liu R, Liu W, Zheng Z, et al. Anomaly-GAN: A data augmentation method for train surface anomaly detection[J]. Expert Systems with Applications, 2023, 228: 120284.
    [4] Lian Y, Geng Y, Tian T. Anomaly detection method for multivariate time series data of oil and gas stations based on digital twin and mtad-gan[J]. Applied Sciences, 2023, 13(3): 1891.
    [5] Torabi H, Mirtaheri S L, Greco S. Practical autoencoder based anomaly detection by using vector reconstruction error[J]. Cybersecurity, 2023, 6(1): 1.
    [6] Mattera G, Vozza M, Polden J, et al. Frequency informed convolutional autoencoder for in situ anomaly detection in wire arc additive manufacturing[J]. Journal of Intelligent Manufacturing, 2024: 1-16.
    [7] Fu H, Liang F, Liang J, et al. Asymmetric learned image compression with multi-scale residual block, importance scaling, and post-quantization filtering[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2023, 33(8): 4309-4321.
    [8] Zhang Z, Wu H, Zhao H, et al. A novel deep learning model for medical image segmentation with convolutional neural network and transformer[J]. Interdisciplinary Sciences: Computational Life Sciences, 2023, 15(4): 663-677.
    [9] Lee J H, Kim J, Kwon S J, et al. Flexround: Learnable rounding based on element-wise division for post-training quantization[C]//International Conference on Machine Learning. PMLR, 2023: 18913-18939.
    [10] Eom K Y, Min B S. Development of deep learning network based low-quality image enhancement techniques for improving foreign object detection performance[J]. Journal of Internet Computing and Services, 2024, 25(1): 99-107.
    [11] Rachmadi M F, Byra M, Skibbe H. A new family of instance-level loss functions for improving instance-level segmentation and detection of white matter hyperintensities in routine clinical brain MRI[J]. Computers in Biology and Medicine, 2024, 174: 108414.
    [12] Chmielewska A, Dean D. The role of stiffness-matching in avoiding stress shielding-induced bone loss and stress concentration-induced skeletal reconstruction device failure[J]. Acta Biomaterialia, 2024, 173: 51-65.
    [13] Szymanowicz S, Rupprecht C, Vedaldi A. Splatter image: Ultra-fast single-view 3d reconstruction[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024: 10208-10217.
    [14] Cai D, Jia T, Wang H, et al. XTM-GAN: Generative Adversarial Networks for Tone Mapping of Dual-Energy X-ray Security Images[C]//2024 IEEE 14th International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER). IEEE, 2024: 416-421.
    [15] Li X, Wu W, Yan W, et al. Randomly-Accessible Active Pixel Sensor with Logarithmic-Exponential Response Enabling Low Dose and Wide Dynamic Range Indirect-Conversion X-ray Imaging[J]. IEEE Sensors Journal, 2024.
    [16] Singh R, Sethi A, Saini K, et al. Attention-guided generator with dual discriminator GAN for real-time video anomaly detection[J]. Engineering Applications of Artificial Intelligence, 2024, 131: 107830.
    [17] Hassan E, Shams M Y, Hikal N A, et al. The effect of choosing optimizer algorithms to improve computer vision tasks: a comparative study[J]. Multimedia Tools and Applications, 2023, 82(11): 16591-16633.
    [18] Shah P S, Hughes E G, Sukhadia S S, et al. Validation and implementation of a somatic-only tumor exome for routine clinical application[J]. The Journal of Molecular Diagnostics, 2024, 26(9): 815-824.
    [19] Hui V, Litton E, Edibam C, et al. Using machine learning to predict bleeding after cardiac surgery[J]. European Journal of Cardio-Thoracic Surgery, 2023, 64(6): ezad297.
    [20] Bakurov I, Buzzelli M, Schettini R, et al. Full-reference image quality expression via genetic programming[J]. IEEE Transactions on Image Processing, 2023, 32: 1458-1473.
    [21] Andono P N, Setiadi D R I M. Quantization selection based on characteristic of cover image for PVD Steganography to optimize imperceptibility and capacity[J]. Multimedia Tools and Applications, 2023, 82(3): 3561-3580.
    [22] Pu B, Lan S, Wang W, et al. GanNeXt: A New Convolutional GAN for Anomaly Detection[C]//International Conference on Artificial Neural Networks. Cham: Springer Nature Switzerland, 2023: 39-49.
    [23] Liu J, Xie G, Wang J, et al. Deep industrial image anomaly detection: A survey[J]. Machine Intelligence Research, 2024, 21(1): 104-135.

Tan Yanli, Azliza Mohd Ali, Sharifalillah Nordin, Wang Jin, and Li Guoqin(2025),Chest X-ray Abnormality Detection Using Convolutional AutoEncoder Combined with Double Generative Adversarial Network (GAN). IJEER 13(3), 563-571. DOI: 10.37391/IJEER.130321.