Two-stage U-Net++ for Medical Image Segmentation

Abdulla Al Suman, Shubham Sarda, Md Asikuzzaman, Alexandra Louise Webb, M. Perriman Diana, Murat Tahtali, Antonio Di Ieva, Mark R. Pickering

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    2 Citations (Scopus)

    Abstract

    Convolutional neural networks (CNNs) have achieved expert-level performance in many image processing applications. However, CNNs face the vanishing gradient problem when the number of layers are increased beyond a certain threshold. In this paper, a new two-stage U-Net++ (TS-UNet++) architecture is proposed to address the vanishing gradient problem. The new architecture uses two different types of deep CNNs rather than a traditional multi-stage network, the U-Net++ and U-Net architectures in the first and second stages respectively. An extra convolutional block is added before the output layer of the multi-stage network to better extract high-level features. A new concatenation-based fusion structure is incorporated in this architecture to enable deep supervision. More convolutional layers are added after each concatenation of the fusion structure to extract more representative features. The performance of the proposed method is compared with the U-Net, U-Net++ and two-stage U-Net (TS-UNet) architectures for the problem of segmenting neck muscles in a clinical MRI dataset. The architectures were evaluated using the dice similarity coefficient (DSC) and directed Hausdorff distance (DHD) measures and the results demonstrate the superior performance of the new architecture.

    Original languageEnglish
    Title of host publicationDICTA 2021 - 2021 International Conference on Digital Image Computing
    Subtitle of host publicationTechniques and Applications
    EditorsJun Zhou, Olivier Salvado, Ferdous Sohel, Paulo Vinicius K. Borges, Shilin Wang
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    ISBN (Electronic)9781665417099
    DOIs
    Publication statusPublished - 2021
    Event2021 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2021 - Gold Coast, Australia
    Duration: 29 Nov 20211 Dec 2021

    Publication series

    NameDICTA 2021 - 2021 International Conference on Digital Image Computing: Techniques and Applications

    Conference

    Conference2021 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2021
    Country/TerritoryAustralia
    CityGold Coast
    Period29/11/211/12/21

    Fingerprint

    Dive into the research topics of 'Two-stage U-Net++ for Medical Image Segmentation'. Together they form a unique fingerprint.

    Cite this