Abstract
Anomaly detection has been applied in the various disease of medical practice, such as breast cancer, retinal, lung lesion, and skin disease. However, in real-world anomaly detection, there exist a large number of healthy samples, and but very few sick samples. To alleviate the problem of data imbalance in anomaly detection, this paper proposes an unsupervised learning method for deep anomaly detection based on an improved adversarial autoencoder, in which a module called chain of convolutional block (CCB) is employed instead of the conventional skip-connections used in adversarial autoencoder. Such CCB connections provide considerable advantages via direct connections, not only preserving both global and local information but also alleviating the problem of semantic disparity between the encoding features and the corresponding decoding features. The proposed method is thus able to capture the distribution of normal samples within both image space and latent vector space. By means of minimizing the reconstruction error within both spaces during training phase, higher reconstruction error during test phase is indicative of an anomaly. Our method is trained only on the healthy persons in order to learn the distribution of normal samples and can detect sick samples based on high deviation from the distribution of normality in an unsupervised way. Experimental results for multiple datasets from different fields demonstrate that the proposed method yields superior performance to state-of-the-art methods.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Availability of Data and Material
The data used to support the findings of this study are available from http://www.cs.toronto.edu/~kriz/cifar.html (CIFAR-10 dataset), http://medgift.hevs.ch/silverstripe/index.php/team/adrien-depeursinge/multimedia-database-of-interstitial-lung-diseases/ (ILD dataset) and https://www.nature.com/articles/sdata2018161 (HAM10000 dataset).
References
Agrawal R, Kulkarni S, Walambe R, Kotecha K: Assistive Framework for Automatic Detection of All the Zones in Retinopathy of Prematurity Using Deep Learning. J Digit Imaging, 2021
Feng-Ping A, Jun-e L, Jian-rong W: Medical image segmentation algorithm based on positive scaling invariant-self encoding CCA. Biomedical Signal Processing and Control 66:102395, 2021
Qiblawey Y, et al.: Detection and Severity Classification of COVID-19 in CT Images Using Deep Learning. Diagnostics (Basel) 11:893, 2021
Jojoa Acosta MF, Caballero Tovar LY, Garcia-Zapirain MB, Percybrooks WS: Melanoma diagnosis using deep learning techniques on dermatoscopic images. BMC Med Imaging 21:6, 2021
Jian C, et al.: Automatic brain extraction from 3D fetal MR image with deep learning-based multi-step framework. Comput Med Imaging Graph 88:101848, 2021
Muzamil S, Hussain T, Haider A, Waraich U, Ashiq U, Ayguade E: An Intelligent Iris Based Chronic Kidney Identification System. Symmetry-Basel 12:2066, 2020
Rehman MU, Cho S, Kim J, Chong KT: BrainSeg-Net: Brain Tumor MR Image Segmentation via Enhanced Encoder-Decoder Network. Diagnostics (Basel) 11:169, 2021
Nakao T, et al.: Unsupervised Deep Anomaly Detection in Chest Radiographs. J Digit Imaging 34:418-427, 2021
Baur C, Denner S, Wiestler B, Navab N, Albarqouni S: Autoencoders for unsupervised anomaly segmentation in brain MR images: A comparative study. Med Image Anal 69:101952, 2021
Fujioka T, et al.: Efficient Anomaly Detection with Generative Adversarial Network for Breast Ultrasound Imaging. Diagnostics (Basel) 10:456, 2020
Tufail AB, Ma YK, Zhang QN: Binary Classification of Alzheimer's Disease Using sMRI Imaging Modality and Deep Learning. J Digit Imaging 33:1073-1090, 2020
Park B, Park H, Lee SM, Seo JB, Kim N: Lung Segmentation on HRCT and Volumetric CT for Diffuse Interstitial Lung Disease Using Deep Convolutional Neural Networks. J Digit Imaging 32:1019-1026, 2019
Kim GB, et al.: Comparison of Shallow and Deep Learning Methods on Classifying the Regional Pattern of Diffuse Lung Disease. J Digit Imaging 31:415-424, 2018
Erfani SM, Rajasegarar S, Karunasekera S, Leckie C: High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning. Pattern Recogn 58:121-134, 2016
Akcay S, Abarghouei AA, Breckon TP: GANomaly: Semi-supervised Anomaly Detection via Adversarial Training, 2018
Ibtehaz N, Rahman MS: MultiResUNet : Rethinking the U-Net architecture for multimodal biomedical image segmentation. Neural Netw 121:74-87, 2020
Akcay S, Atapour-Abarghouei A, Breckon TP: Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detection, 2019
Zenati H, Romain M, Foo C-S, Lecouat B, Chandrasekhar V: Adversarially Learned Anomaly Detection, 2018
Depeursinge A, Vargas A, Platon A, Geissbuhler A, Poletti PA, Muller H: Building a reference multimedia database for interstitial lung diseases. Comput Med Imaging Graph 36:227-238, 2012
Tschandl P, Rosendahl C, Kittler H: The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci Data 5:180161, 2018
Gribbestad M, Hassan MU, I AH, Sundli K: Health Monitoring of Air Compressors Using Reconstruction-Based Deep Learning for Anomaly Detection with Increased Transparency. Entropy (Basel) 23:83, 2021
Cowton J, Kyriazakis I, Plotz T, Bacardit J: A Combined Deep Learning GRU-Autoencoder for the Early Detection of Respiratory Disease in Pigs Using Multiple Environmental Sensors. Sensors (Basel) 18:2521, 2018
Petrick N, et al.: A primitive study on unsupervised anomaly detection with an autoencoder in emergency head CT volumes, 2018
Kingma D, Welling M: Auto-Encoding Variational Bayes. ICLR, 2013
Gunduz H: An efficient dimensionality reduction method using filter-based feature selection and variational autoencoders on Parkinson's disease classification. Biomedical Signal Processing and Control 66:102452, 2021
Saxena D, Cao J: Generative Adversarial Networks (GANs):Challenges, Solutions, and Future Directions. ACM Computing Surveys 54:1-42, 2021
Goodfellow IJ, et al.: Generative Adversarial Networks. CoRR abs/1406.2661, 2014
Schlegl T, Seeböck P, Waldstein SM, Schmidt-Erfurth U, Langs G: Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery, 2017
Radford A, Metz L, Chintala S: Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks, 2016
Sabokrou M, Khalooei M, Fathy M, Adeli E: Adversarially Learned One-Class Classifier for Novelty Detection, 2018
Ronneberger O, Fischer P, Brox T: U-Net: Convolutional Networks for Biomedical Image Segmentation, 2015
Zongwei Z, Siddiquee MMR, Tajbakhsh N, Jianming L: UNet++: A Nested U-Net Architecture for Medical Image Segmentation, 2018
Wenping G, Zhuoming X, Haibo Z: Interstitial lung disease classification using improved DenseNet. Multimed Tools Appl 78:30615-30626, 2018 https://doi.org/10.1007/s11042-018-6535-y
Perera P, Patel VM: Learning Deep Features for One-Class Classification. IEEE Trans Image Process 28:5450-5463, 2019
Zenati H, Foo CS, Lecouat B, Manek G, Chandrasekhar VR: Efficient GAN-Based Anomaly Detection. CoRR abs/1802.06222, 2018
Funding
This research was funded by research project of Taizhou University (Z2018046), Science and Technology Program of Taizhou (2003gy12, 2003gy04), National Natural Science Foundation of China (61976149), Zhejiang Provincial Natural Science Foundation of China (LZ20F020002), the Humanities and Social Science Project of the Chinese Ministry of Education (20YJAZH033).
Author information
Authors and Affiliations
Contributions
Conceptualization, H.Z. and W.G.; methodology, W.G. and H.Z.; software, H.Z.; validation, H.L., S.Z. and X.Z.; resources, X.Z.; writing–original draft preparation, W.G. and H.Z.; writing–review and editing, H.L., X.Z. and S.Z.; funding acquisition, X.Z. All the authors have read and agreed to the published version of the manuscript.
Corresponding authors
Ethics declarations
Competing Interests
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhang, H., Guo, W., Zhang, S. et al. Unsupervised Deep Anomaly Detection for Medical Images Using an Improved Adversarial Autoencoder. J Digit Imaging 35, 153–161 (2022). https://doi.org/10.1007/s10278-021-00558-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10278-021-00558-8