Arrêt de service lundi 11 juillet de 12h30 à 13h : tous les sites du CCSD (HAL, EpiSciences, SciencesConf, AureHAL) seront inaccessibles (branchement réseau à modifier)
Accéder directement au contenu Accéder directement à la navigation
Article dans une revue

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

Abstract : 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
Type de document :
Article dans une revue
Liste complète des métadonnées
Contributeur : IMVIA - université de Bourgogne Connectez-vous pour contacter le contributeur
Soumis le : mercredi 30 octobre 2019 - 17:03:26
Dernière modification le : jeudi 3 mars 2022 - 13:38:04

Lien texte intégral




Vivek Kumar Singh, Mohamed Abdel-Nasser, Hatem Rashwan, Farhan Akram, Nidhi Pandey, et al.. FCA-Net: Adversarial Learning for Skin Lesion Segmentation Based on Multi-Scale Features and Factorized Channel Attention. IEEE Access, IEEE, 2019, 7, pp.130552-130565. ⟨10.1109/ACCESS.2019.2940418⟩. ⟨hal-02340216⟩



Consultations de la notice