Articles producció científica> Enginyeria Informàtica i Matemàtiques

Efficient Stain-Aware Nuclei Segmentation Deep Learning Framework for Multi-Center Histopathological Images

  • Identification data

    Identifier: imarina:9207258
    Authors:
    Hassan, LoayAbdel-Nasser, MohamedSaleh, AdelOmer, Osama APuig, Domenec
    Abstract:
    Existing nuclei segmentation methods have obtained limited results with multi-center and multi-organ whole-slide images (WSIs) due to the use of different stains, scanners, overlapping, clumped nuclei, and the ambiguous boundary between adjacent cell nuclei. In an attempt to address these problems, we propose an efficient stain-aware nuclei segmentation method based on deep learning for multi-center WSIs. Unlike all related works that exploit a single-stain template from the dataset to normalize WSIs, we propose an efficient algorithm to select a set of stain templates based on stain clustering. Individual deep learning models are trained based on each stain template, and then, an aggregation function based on the Choquet integral is employed to combine the segmentation masks of the individual models. With a challenging multi-center multi-organ WSIs dataset, the experimental results demonstrate that the proposed method outperforms the state-of-art nuclei segmentation methods with aggregated Jaccard index (AJI) and F1-scores of 73.23% and 89.32%, respectively, while achieving a lower number of parameters.
  • Others:

    Author, as appears in the article.: Hassan, Loay; Abdel-Nasser, Mohamed; Saleh, Adel; Omer, Osama A; Puig, Domenec
    Department: Enginyeria Informàtica i Matemàtiques
    URV's Author/s: Abdelnasser Mohamed Mahmoud, Mohamed / Puig Valls, Domènec Savi
    Keywords: Whole-slide imaging Nuclei segmentation Deep learning Choquet integral
    Abstract: Existing nuclei segmentation methods have obtained limited results with multi-center and multi-organ whole-slide images (WSIs) due to the use of different stains, scanners, overlapping, clumped nuclei, and the ambiguous boundary between adjacent cell nuclei. In an attempt to address these problems, we propose an efficient stain-aware nuclei segmentation method based on deep learning for multi-center WSIs. Unlike all related works that exploit a single-stain template from the dataset to normalize WSIs, we propose an efficient algorithm to select a set of stain templates based on stain clustering. Individual deep learning models are trained based on each stain template, and then, an aggregation function based on the Choquet integral is employed to combine the segmentation masks of the individual models. With a challenging multi-center multi-organ WSIs dataset, the experimental results demonstrate that the proposed method outperforms the state-of-art nuclei segmentation methods with aggregated Jaccard index (AJI) and F1-scores of 73.23% and 89.32%, respectively, while achieving a lower number of parameters.
    Thematic Areas: Signal processing Physics, applied Hardware and architecture Engineering, electrical & electronic Engenharias iv Electrical and electronic engineering Control and systems engineering Computer science, information systems Computer networks and communications
    licence for use: https://creativecommons.org/licenses/by/3.0/es/
    Author's mail: mohamed.abdelnasser@urv.cat domenec.puig@urv.cat
    Author identifier: 0000-0002-1074-2441 0000-0002-0562-4205
    Record's date: 2024-10-12
    Journal volume: 10
    Papper version: info:eu-repo/semantics/publishedVersion
    Link to the original source: https://www.mdpi.com/2079-9292/10/8/954
    Licence document URL: https://repositori.urv.cat/ca/proteccio-de-dades/
    Papper original source: Electronics. 10 (8): 954-
    APA: Hassan, Loay; Abdel-Nasser, Mohamed; Saleh, Adel; Omer, Osama A; Puig, Domenec (2021). Efficient Stain-Aware Nuclei Segmentation Deep Learning Framework for Multi-Center Histopathological Images. Electronics, 10(8), 954-. DOI: 10.3390/electronics10080954
    Article's DOI: 10.3390/electronics10080954
    Entity: Universitat Rovira i Virgili
    Journal publication year: 2021
    Publication Type: Journal Publications
  • Keywords:

    Computer Networks and Communications,Computer Science, Information Systems,Control and Systems Engineering,Electrical and Electronic Engineering,Engineering, Electrical & Electronic,Hardware and Architecture,Physics, Applied,Signal Processing
    Whole-slide imaging
    Nuclei segmentation
    Deep learning
    Choquet integral
    Signal processing
    Physics, applied
    Hardware and architecture
    Engineering, electrical & electronic
    Engenharias iv
    Electrical and electronic engineering
    Control and systems engineering
    Computer science, information systems
    Computer networks and communications
  • Documents:

  • Cerca a google

    Search to google scholar