BIROn - Birkbeck Institutional Research Online

    Deep learning of brain asymmetry images and transfer learning for early diagnosis of dementia

    Herzog, Nitsa and Magoulas, George (2021) Deep learning of brain asymmetry images and transfer learning for early diagnosis of dementia. In: 22nd International Conference on Engineering Applications of Neural Networks, 25-27 June 2021, Crete, Greece (online).

    [img]
    Preview
    Text
    EANN21-NH-GM-camvers.pdf

    Download (382kB) | Preview
    Official URL: https://www.eann2021.eu/

    Abstract

    Advances in neural networks and deep learning have opened a new era in medical imaging technology, health care data analysis and clinical diagnosis. This paper focuses on the classification of MRI for diagnosis of early and progressive dementia using transfer learning architectures that employ Convolutional Neural Networks-CNNs, as a base model, and fully connected layers of Softmax functions or Support Vector Machines-SVMs. The diagnostic process is based on the analysis of the neurodegenerative changes in the brain using segmented images of brain asymmetry, which has been identified as a predictive imaging source of early dementia. Results from 300 independent simulation runs on a set of four binary and one multiclass MRI classification tasks illustrate that transfer learning of CNN-based models equipped with SVM output layer is capable to produce better performing models within a few training epochs compared to commonly used transfer learning architectures that combine CNN pretrained models with fully connected Softmax layers. However, experimental findings also confirm that longer training sessions appear to compensate for the shortcomings of the fully connected Softmax layers in the long term. Diagnosis of early dementia on un-seen patients’ brain asymmetry MRI data reached an average accuracy of 90.25% with both transfer learning architectures, while progressive dementia was promptly diagnosed with an accuracy that reached 95.90% using a transfer learning architecture that has the SVM layer.

    Metadata

    Item Type: Conference or Workshop Item (Paper)
    Keyword(s) / Subject(s): Convolutional Neural Network, Support Vector Machines, Brain Asymmetry, Neurodegenerative diseases, Transfer Learning, Dementia
    School: School of Business, Economics & Informatics > Computer Science and Information Systems
    Research Centres and Institutes: Birkbeck Knowledge Lab
    Depositing User: George Magoulas
    Date Deposited: 10 May 2022 13:41
    Last Modified: 10 May 2022 21:07
    URI: https://eprints.bbk.ac.uk/id/eprint/44156

    Statistics

    Downloads
    Activity Overview
    11Downloads
    29Hits

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item