SLSNet: Skin lesion segmentation using a lightweight generative adversarial network

Md Mostafa Kamal Sarker*, Hatem A. Rashwan, Farhan Akram, Vivek Kumar Singh, Syeda Furruka Banu, Forhad U.H. Chowdhury, Kabir Ahmed Choudhury, Sylvie Chambon, Petia Radeva, Domenec Puig, Mohamed Abdel-Nasser

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

44 Citations (Scopus)
10 Downloads (Pure)

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.

Original languageEnglish
Article number115433
JournalExpert Systems with Applications
Volume183
DOIs
Publication statusPublished - 30 Nov 2021
Externally publishedYes

Bibliographical note

Funding Information:
This research is funded by the program “Martí i Franquès” under the agreement between Universitat Rovira Virgili and Fundacio Catalunya La Pedrera , projects RTI2018-095232-B-C2 , SGR 1742 , CERCA, Nestore Horizon2020 SC1-PM-15-2017 (n 769643 ), EIT Health Validithi project. The authors acknowledge the support of the NVIDIA Corporation who donated several Titan Xp GPU used for this research. M. Abdel-Nasser, Hatem A. Rashwan and D. Puig are partially supported by the Spanish Government under project PID2019-105789RB-I00 .

Publisher Copyright:
© 2021

Fingerprint

Dive into the research topics of 'SLSNet: Skin lesion segmentation using a lightweight generative adversarial network'. Together they form a unique fingerprint.

Cite this