Articles producció científica> Enginyeria Informàtica i Matemàtiques

Efficient Staining-Invariant Nuclei Segmentation Approach Using Self-Supervised Deep Contrastive Network

  • Identification data

    Identifier: imarina:9297800
    Authors:
    Abdel-Nasser, MohamedSingh, Vivek KumarMohamed, Ehab Mahmoud
    Abstract:
    Existing nuclei segmentation methods face challenges with hematoxylin and eosin (H&E) whole slide imaging (WSI) due to the variations in staining methods and nuclei shapes and sizes. Most existing approaches require a stain normalization step that may cause losing source information and fail to handle the inter-scanner feature instability problem. To mitigate these issues, this article proposes an efficient staining-invariant nuclei segmentation method based on self-supervised contrastive learning and an effective weighted hybrid dilated convolution (WHDC) block. In particular, we propose a staining-invariant encoder (SIE) that includes convolution and transformers blocks. We also propose the WHDC block allowing the network to learn multi-scale nuclei-relevant features to handle the variation in the sizes and shapes of nuclei. The SIE network is trained on five unlabeled WSIs datasets using self-supervised contrastive learning and then used as a backbone for the downstream nuclei segmentation network. Our method outperforms existing approaches in challenging multiple WSI datasets without stain color normalization.
  • Others:

    Author, as appears in the article.: Abdel-Nasser, Mohamed; Singh, Vivek Kumar; Mohamed, Ehab Mahmoud
    Department: Enginyeria Informàtica i Matemàtiques
    URV's Author/s: Abdelnasser Mohamed Mahmoud, Mohamed
    Keywords: Whole slide imaging Stain color normalization Nuclei segmentation Images Hematoxylin and eosin (h&e) Hematoxylin and eosin (h&ampe) Hematoxylin and eosin (h&e) Deep learning
    Abstract: Existing nuclei segmentation methods face challenges with hematoxylin and eosin (H&E) whole slide imaging (WSI) due to the variations in staining methods and nuclei shapes and sizes. Most existing approaches require a stain normalization step that may cause losing source information and fail to handle the inter-scanner feature instability problem. To mitigate these issues, this article proposes an efficient staining-invariant nuclei segmentation method based on self-supervised contrastive learning and an effective weighted hybrid dilated convolution (WHDC) block. In particular, we propose a staining-invariant encoder (SIE) that includes convolution and transformers blocks. We also propose the WHDC block allowing the network to learn multi-scale nuclei-relevant features to handle the variation in the sizes and shapes of nuclei. The SIE network is trained on five unlabeled WSIs datasets using self-supervised contrastive learning and then used as a backbone for the downstream nuclei segmentation network. Our method outperforms existing approaches in challenging multiple WSI datasets without stain color normalization.
    Thematic Areas: Medicine, general & internal Internal medicine Clinical biochemistry
    licence for use: https://creativecommons.org/licenses/by/3.0/es/
    Author's mail: mohamed.abdelnasser@urv.cat
    Author identifier: 0000-0002-1074-2441
    Record's date: 2024-10-12
    Papper version: info:eu-repo/semantics/publishedVersion
    Link to the original source: https://www.mdpi.com/2075-4418/12/12/3024
    Licence document URL: https://repositori.urv.cat/ca/proteccio-de-dades/
    Papper original source: Diagnostics. 12 (12): 3024-
    APA: Abdel-Nasser, Mohamed; Singh, Vivek Kumar; Mohamed, Ehab Mahmoud (2022). Efficient Staining-Invariant Nuclei Segmentation Approach Using Self-Supervised Deep Contrastive Network. Diagnostics, 12(12), 3024-. DOI: 10.3390/diagnostics12123024
    Article's DOI: 10.3390/diagnostics12123024
    Entity: Universitat Rovira i Virgili
    Journal publication year: 2022
    Publication Type: Journal Publications
  • Keywords:

    Clinical Biochemistry,Medicine, General & Internal
    Whole slide imaging
    Stain color normalization
    Nuclei segmentation
    Images
    Hematoxylin and eosin (h&e)
    Hematoxylin and eosin (h&e)
    Hematoxylin and eosin (h&e)
    Deep learning
    Medicine, general & internal
    Internal medicine
    Clinical biochemistry
  • Documents:

  • Cerca a google

    Search to google scholar