Articles producció científica> Enginyeria Informàtica i Matemàtiques

SLSNet: Skin lesion segmentation using a lightweight generative adversarial network

  • Identification data

    Identifier: imarina:9227047
    Authors:
    Sarker, Md Mostafa KamalRashwan, Hatem AAkram, FarhanSingh, Vivek KumarBanu, Syeda FurrukaChowdhury, Forhad U HChoudhury, Kabir AhmedChambon, SylvieRadeva, PetiaPuig, DomenecAbdel-Nasser, Mohamed
    Abstract:
    The determination of precise skin lesion boundaries in dermoscopic images using automated methods faces many challenges, most importantly, the presence of hair, inconspicuous lesion edges and low contrast in dermoscopic images, and variability in the color, texture and shapes of skin lesions. Existing deep learning-based skin lesion segmentation algorithms are expensive in terms of computational time and memory. Consequently, running such segmentation algorithms requires a powerful GPU and high bandwidth memory, which are not available in dermoscopy devices. Thus, this article aims to achieve precise skin lesion segmentation with minimum resources: a lightweight, efficient generative adversarial network (GAN) model called SLSNet, which combines 1-D kernel factorized networks, position and channel attention, and multiscale aggregation mechanisms with a GAN model. The 1-D kernel factorized network reduces the computational cost of 2D filtering. The position and channel attention modules enhance the discriminative ability between the lesion and non-lesion feature representations in spatial and channel dimensions, respectively. A multiscale block is also used to aggregate the coarse-to-fine features of input skin images and reduce the effect of the artifacts. SLSNet is evaluated on two publicly available datasets: ISBI 2017 and the ISIC 2018. Although SLSNet has only 2.35 million parameters, the experimental results demonstrate that it achieves segmentation results on a par with the state-of-the-art skin lesion segmentation methods with an accuracy of 97.61%, and Dice and Jaccard similarity coefficients of 90.63% and 81.98%, respectively. SLSNet can run at more than 110 frames per second (FPS) in a single GTX1080Ti GPU, which is faster than well-known deep learning-based im
  • Others:

    Author, as appears in the article.: Sarker, Md Mostafa Kamal; Rashwan, Hatem A; Akram, Farhan; Singh, Vivek Kumar; Banu, Syeda Furruka; Chowdhury, Forhad U H; Choudhury, Kabir Ahmed; Chambon, Sylvie; Radeva, Petia; Puig, Domenec; Abdel-Nasser, Mohamed
    Department: Enginyeria Informàtica i Matemàtiques
    URV's Author/s: Abdellatif Fatahallah Ibrahim Mahmoud, Hatem / Abdelnasser Mohamed Mahmoud, Mohamed / AKRAM, FARHAN / Banu, Syeda Furruka / Puig Valls, Domènec Savi
    Keywords: Textures Skin lesion segmentation Skin lesion Segmentation algorithms Position attention Lesion segmentations Image segmentation Diagnosis Dermoscopic images Dermatology Deep learning Deep generative adversarial network Deep Classification Channel attention Adversarial networks 1-d kernel factorized network
    Abstract: The determination of precise skin lesion boundaries in dermoscopic images using automated methods faces many challenges, most importantly, the presence of hair, inconspicuous lesion edges and low contrast in dermoscopic images, and variability in the color, texture and shapes of skin lesions. Existing deep learning-based skin lesion segmentation algorithms are expensive in terms of computational time and memory. Consequently, running such segmentation algorithms requires a powerful GPU and high bandwidth memory, which are not available in dermoscopy devices. Thus, this article aims to achieve precise skin lesion segmentation with minimum resources: a lightweight, efficient generative adversarial network (GAN) model called SLSNet, which combines 1-D kernel factorized networks, position and channel attention, and multiscale aggregation mechanisms with a GAN model. The 1-D kernel factorized network reduces the computational cost of 2D filtering. The position and channel attention modules enhance the discriminative ability between the lesion and non-lesion feature representations in spatial and channel dimensions, respectively. A multiscale block is also used to aggregate the coarse-to-fine features of input skin images and reduce the effect of the artifacts. SLSNet is evaluated on two publicly available datasets: ISBI 2017 and the ISIC 2018. Although SLSNet has only 2.35 million parameters, the experimental results demonstrate that it achieves segmentation results on a par with the state-of-the-art skin lesion segmentation methods with an accuracy of 97.61%, and Dice and Jaccard similarity coefficients of 90.63% and 81.98%, respectively. SLSNet can run at more than 110 frames per second (FPS) in a single GTX1080Ti GPU, which is faster than well-known deep learning-based image segmentation models, such as FCN. Therefore, SLSNet can be used for practical dermoscopic applications.
    Thematic Areas: Química Operations research & management science Medicina iii Medicina ii Medicina i Materiais Matemática / probabilidade e estatística Interdisciplinar Geociências General engineering Farmacia Engineering, electrical & electronic Engineering (miscellaneous) Engineering (all) Engenharias iv Engenharias iii Engenharias ii Engenharias i Enfermagem Educação Economia Direito Computer science, artificial intelligence Computer science applications Ciências sociais aplicadas i Ciências biológicas iii Ciências biológicas ii Ciências biológicas i Ciências ambientais Ciências agrárias i Ciência da computação Biotecnología Biodiversidade Astronomia / física Artificial intelligence Arquitetura, urbanismo e design Administração, ciências contábeis e turismo Administração pública e de empresas, ciências contábeis e turismo
    licence for use: https://creativecommons.org/licenses/by/3.0/es/
    Author's mail: mohamed.abdelnasser@urv.cat hatem.abdellatif@urv.cat syedafurruka.banu@estudiants.urv.cat domenec.puig@urv.cat
    Author identifier: 0000-0002-1074-2441 0000-0001-5421-1637 0000-0002-5624-1941 0000-0002-0562-4205
    Record's date: 2024-09-21
    Papper version: info:eu-repo/semantics/publishedVersion
    Link to the original source: https://www.sciencedirect.com/science/article/pii/S0957417421008496
    Licence document URL: https://repositori.urv.cat/ca/proteccio-de-dades/
    Papper original source: Expert Systems With Applications. 183 115433-
    APA: Sarker, Md Mostafa Kamal; Rashwan, Hatem A; Akram, Farhan; Singh, Vivek Kumar; Banu, Syeda Furruka; Chowdhury, Forhad U H; Choudhury, Kabir Ahmed; Cha (2021). SLSNet: Skin lesion segmentation using a lightweight generative adversarial network. Expert Systems With Applications, 183(), 115433-. DOI: 10.1016/j.eswa.2021.115433
    Article's DOI: 10.1016/j.eswa.2021.115433
    Entity: Universitat Rovira i Virgili
    Journal publication year: 2021
    Publication Type: Journal Publications
  • Keywords:

    Artificial Intelligence,Computer Science Applications,Computer Science, Artificial Intelligence,Engineering (Miscellaneous),Engineering, Electrical & Electronic,Operations Research & Management Science
    Textures
    Skin lesion segmentation
    Skin lesion
    Segmentation algorithms
    Position attention
    Lesion segmentations
    Image segmentation
    Diagnosis
    Dermoscopic images
    Dermatology
    Deep learning
    Deep generative adversarial network
    Deep
    Classification
    Channel attention
    Adversarial networks
    1-d kernel factorized network
    Química
    Operations research & management science
    Medicina iii
    Medicina ii
    Medicina i
    Materiais
    Matemática / probabilidade e estatística
    Interdisciplinar
    Geociências
    General engineering
    Farmacia
    Engineering, electrical & electronic
    Engineering (miscellaneous)
    Engineering (all)
    Engenharias iv
    Engenharias iii
    Engenharias ii
    Engenharias i
    Enfermagem
    Educação
    Economia
    Direito
    Computer science, artificial intelligence
    Computer science applications
    Ciências sociais aplicadas i
    Ciências biológicas iii
    Ciências biológicas ii
    Ciências biológicas i
    Ciências ambientais
    Ciências agrárias i
    Ciência da computação
    Biotecnología
    Biodiversidade
    Astronomia / física
    Artificial intelligence
    Arquitetura, urbanismo e design
    Administração, ciências contábeis e turismo
    Administração pública e de empresas, ciências contábeis e turismo
  • Documents:

  • Cerca a google

    Search to google scholar