English

UCM-Net: A Lightweight and Efficient Solution for Skin Lesion Segmentation using MLP and CNN

Image and Video Processing 2024-06-26 v4 Computer Vision and Pattern Recognition

Abstract

Skin cancer poses a significant public health challenge, necessitating efficient diagnostic tools. We introduce UCM-Net, a novel skin lesion segmentation model combining Multi-Layer Perceptrons (MLP) and Convolutional Neural Networks (CNN). This lightweight, efficient architecture, deviating from traditional UNet designs, dramatically reduces computational demands, making it ideal for mobile health applications. Evaluated on PH2, ISIC 2017, and ISIC 2018 datasets, UCM-Net demonstrates robust performance with fewer than 50KB parameters and requires less than 0.05 Giga Operations Per Second (GLOPs). Moreover, its minimal memory requirement is just 1.19MB in CPU environment positions. It is a potential benchmark for efficiency in skin lesion segmentation, suitable for deployment in resource-constrained settings. In order to facilitate accessibility and further research in the field, the UCM-Net source code is https://github.com/chunyuyuan/UCM-Net.

Keywords

Cite

@article{arxiv.2310.09457,
  title  = {UCM-Net: A Lightweight and Efficient Solution for Skin Lesion Segmentation using MLP and CNN},
  author = {Chunyu Yuan and Dongfang Zhao and Sos S. Agaian},
  journal= {arXiv preprint arXiv:2310.09457},
  year   = {2024}
}

Comments

17 pages, accepted by Journal of Biomedical Signal Processing and Control

R2 v1 2026-06-28T12:50:28.251Z