Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Jan;38(1):e3530.
doi: 10.1002/cnm.3530. Epub 2021 Dec 18.

Efficient anomaly detection from medical signals and images with convolutional neural networks for Internet of medical things (IoMT) systems

Ali A Khalil  1 , Fatma E Ibrahim  2 , Mohamed Y Abbass  3 , Nehad Haggag  2 , Yasser Mahrous  2 , Ahmed Sedik  4 , Zeinab Elsherbeeny  2 , Ashraf A M Khalaf  1 , Mohamad Rihan  2   5 , Walid El-Shafai  2 , Ghada M El-Banby  6 , Eman Soltan  2 , Naglaa F Soliman  7 , Abeer D Algarni  7 , Waleed Al-Hanafy  2 , Adel S El-Fishawy  2 , El-Sayed M El-Rabaie  2 , Waleed Al-Nuaimy  8 , Moawad I Dessouky  2 , Adel A Saleeb  2 , Nagy W Messiha  2 , Ibrahim M El-Dokany  2 , Mohsen A M El-Bendary  9 , Fathi E Abd El-Samie  2   7
Affiliations

Efficient anomaly detection from medical signals and images with convolutional neural networks for Internet of medical things (IoMT) systems

Ali A Khalil et al. Int J Numer Method Biomed Eng. 2022 Jan.

Abstract

Deep learning is one of the most promising machine learning techniques that revolutionalized the artificial intelligence field. The known traditional and convolutional neural networks (CNNs) have been utilized in medical pattern recognition applications that depend on deep learning concepts. This is attributed to the importance of anomaly detection (AD) in automatic diagnosis systems. In this paper, the AD is performed on medical electroencephalography (EEG) signal spectrograms and medical corneal images for Internet of medical things (IoMT) systems. Deep learning based on the CNN models is employed for this task with training and testing phases. Each input image passes through a series of convolution layers with different kernel filters. For the classification task, pooling and fully-connected layers are utilized. Computer simulation experiments reveal the success and superiority of the proposed models for automated medical diagnosis in IoMT systems.

Keywords: AI; EEG signals; IoMT; anomaly detection (AD); corneal images; deep learning; machine learning; traditional CNNs.

PubMed Disclaimer

References

REFERENCES

    1. Balasubramian M, Louise A, Roger W. Fractal dimension based corneal fungal diagnosis. Proc SPIE. 2006;6312:200-211.
    1. Fabijan A. Corneal endothelium image segmentation using feedforward neural network: Proceedings of the Federated Conference on Computer Science and Information Systems; IEEE Cataloge Number, 2017:629-637.
    1. Bucht CPer S, Göran M. “Fully automated corneal endothelial morphometric of images captured by clinical specular microscopy”. Ophthalmic Technologies XIX. International Society for Optics and Photonics; 2009;7163:125-136.
    1. Tang M, Shekhar R, Huang D. Curvature mapping for detection of corneal shape abnormality. IEEE Trans Med Imaging. 2005;24(3):16-25.
    1. Girisha V, Chandra KV. Machine intelligence on confocal microscope for detection of endothelium layer of corneal disease: Proceedings of IJCTER; 2016:148-211.

Publication types

LinkOut - more resources