Articles producció científica> Enginyeria Informàtica i Matemàtiques

FCA-Net: Adversarial Learning for Skin Lesion Segment Lion Based on Multi-Scale Features and Factorized Channel Attention

  • Datos identificativos

    Identificador: imarina:5880918
    Autores:
    Singh, Vivek KumarAbdel-Nasser, MohamedRashwan, Hatem AAkram, FarhanPandey, NidhiLalande, AlainPresles, BenoitRomani, SantiagoPuig, Domenec
    Resumen:
    Skin lesion segmentation in dermoscopic images is still a challenge due to the low contrast and fuzzy boundaries of lesions. Moreover, lesions have high similarity with the healthy regions in terms of appearance. In this paper, we propose an accurate skin lesion segmentation model based on a modified conditional generative adversarial network (cGAN). We introduce a new block in the encoder of cGAN called factorized channel attention (FCA), which exploits both channel attention mechanism and residual 1-D kernel factorized convolution. The channel attention mechanism increases the discriminability between the lesion and non-lesion features by taking feature channel interdependencies into account. The 1-D factorized kernel block provides extra convolutions layers with a minimum number of parameters to reduce the computations of the higher-order convolutions. Besides, we use a multi-scale input strategy to encourage the development of filters which are scale-variant (i.e., constructing a scale-invariant representation). The proposed model is assessed on three skin challenge datasets: ISBI2016, ISBI2017, and ISIC2018. It yields competitive results when compared to several state-of-the-art methods in terms of Dice coefficient and intersection over union (IoU) score. The codes of the proposed model are publicly available at https://github.com/vivek231/Skin-Project.
  • Otros:

    Autor según el artículo: Singh, Vivek Kumar; Abdel-Nasser, Mohamed; Rashwan, Hatem A; Akram, Farhan; Pandey, Nidhi; Lalande, Alain; Presles, Benoit; Romani, Santiago; Puig, Domenec
    Departamento: Enginyeria Informàtica i Matemàtiques
    Autor/es de la URV: Abdellatif Fatahallah Ibrahim Mahmoud, Hatem / Abdelnasser Mohamed Mahmoud, Mohamed / AKRAM, FARHAN / Pandey, Nidhi / Puig Valls, Domènec Savi / Romaní Also, Santiago
    Palabras clave: Skin lesion Residual convolution Gradient vector flow Factorized kernel Dermoscopy images Conditional generative adversarial network Channel attention
    Resumen: Skin lesion segmentation in dermoscopic images is still a challenge due to the low contrast and fuzzy boundaries of lesions. Moreover, lesions have high similarity with the healthy regions in terms of appearance. In this paper, we propose an accurate skin lesion segmentation model based on a modified conditional generative adversarial network (cGAN). We introduce a new block in the encoder of cGAN called factorized channel attention (FCA), which exploits both channel attention mechanism and residual 1-D kernel factorized convolution. The channel attention mechanism increases the discriminability between the lesion and non-lesion features by taking feature channel interdependencies into account. The 1-D factorized kernel block provides extra convolutions layers with a minimum number of parameters to reduce the computations of the higher-order convolutions. Besides, we use a multi-scale input strategy to encourage the development of filters which are scale-variant (i.e., constructing a scale-invariant representation). The proposed model is assessed on three skin challenge datasets: ISBI2016, ISBI2017, and ISIC2018. It yields competitive results when compared to several state-of-the-art methods in terms of Dice coefficient and intersection over union (IoU) score. The codes of the proposed model are publicly available at https://github.com/vivek231/Skin-Project.
    Áreas temáticas: Telecommunications Materials science (miscellaneous) Materials science (all) General materials science General engineering General computer science Engineering, electrical & electronic Engineering (miscellaneous) Engineering (all) Engenharias iv Engenharias iii Electrical and electronic engineering Computer science, information systems Computer science (miscellaneous) Computer science (all) Ciência da computação
    Acceso a la licencia de uso: https://creativecommons.org/licenses/by/3.0/es/
    ISSN: 21693536
    Direcció de correo del autor: mohamed.abdelnasser@urv.cat hatem.abdellatif@urv.cat santiago.romani@urv.cat domenec.puig@urv.cat
    Identificador del autor: 0000-0002-1074-2441 0000-0001-5421-1637 0000-0001-6673-9615 0000-0002-0562-4205
    Fecha de alta del registro: 2024-09-21
    Versión del articulo depositado: info:eu-repo/semantics/publishedVersion
    Enlace a la fuente original: https://ieeexplore.ieee.org/document/8832175
    URL Documento de licencia: https://repositori.urv.cat/ca/proteccio-de-dades/
    Referencia al articulo segun fuente origial: Ieee Access. 7 130552-130565
    Referencia de l'ítem segons les normes APA: Singh, Vivek Kumar; Abdel-Nasser, Mohamed; Rashwan, Hatem A; Akram, Farhan; Pandey, Nidhi; Lalande, Alain; Presles, Benoit; Romani, Santiago; Puig, Do (2019). FCA-Net: Adversarial Learning for Skin Lesion Segment Lion Based on Multi-Scale Features and Factorized Channel Attention. Ieee Access, 7(), 130552-130565. DOI: 10.1109/ACCESS.2019.2940418
    DOI del artículo: 10.1109/ACCESS.2019.2940418
    Entidad: Universitat Rovira i Virgili
    Año de publicación de la revista: 2019
    Tipo de publicación: Journal Publications
  • Palabras clave:

    Computer Science (Miscellaneous),Computer Science, Information Systems,Engineering (Miscellaneous),Engineering, Electrical & Electronic,Materials Science (Miscellaneous),Telecommunications
    Skin lesion
    Residual convolution
    Gradient vector flow
    Factorized kernel
    Dermoscopy images
    Conditional generative adversarial network
    Channel attention
    Telecommunications
    Materials science (miscellaneous)
    Materials science (all)
    General materials science
    General engineering
    General computer science
    Engineering, electrical & electronic
    Engineering (miscellaneous)
    Engineering (all)
    Engenharias iv
    Engenharias iii
    Electrical and electronic engineering
    Computer science, information systems
    Computer science (miscellaneous)
    Computer science (all)
    Ciência da computação
  • Documentos:

  • Cerca a google

    Search to google scholar