Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Chunyu Yuan, Dongfang Zhao, Sos S. Agaian

TL;DR

UCM-Net, a novel skin lesion segmentation model combining Multi-Layer Perceptrons (MLP) and Convolutional Neural Networks (CNN), is introduced, a lightweight, efficient architecture that dramatically reduces computational demands, making it ideal for mobile health applications.

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.

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

TL;DR

UCM-Net, a novel skin lesion segmentation model combining Multi-Layer Perceptrons (MLP) and Convolutional Neural Networks (CNN), is introduced, a lightweight, efficient architecture that dramatically reduces computational demands, making it ideal for mobile health applications.

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.
Paper Structure (9 sections, 16 equations, 8 figures, 6 tables, 1 algorithm)

This paper contains 9 sections, 16 equations, 8 figures, 6 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related works
  3. UCM-Net
  4. Experiments and Results
  5. Experiments Setting
  6. Performance Comparisons
  7. Ablation results
  8. Conclusion
  9. Appendix

Figures (8)

  • Figure 1: Complex skin lesion samples
  • Figure 2: AI diagnose process of skin cancer detection
  • Figure 3: This figure shows the visualization of comparative experimental results on the ISIC2017 dataset. The X-axis represents mDice score (higher is better), while Y-axis represents mIoU (higher is better). The color depth represents the number of parameters (blue is better).
  • Figure 4: UCM-Net Structure
  • Figure 5: Vision performance comparison on samples
  • ...and 3 more figures