DTONet a Lightweight Model for Melanoma Segmentation

Article Properties
  • Language
    English
  • Publication Date
    2024/04/18
  • Journal
  • Indian UGC (Journal)
  • Refrences
    35
  • Shengnan Hao Hebei Key Laboratory of Industrial Intelligent Perception, North China University of Science and Technology, Tangshan 063210, China
  • Hongzan Wang Hebei Key Laboratory of Industrial Intelligent Perception, North China University of Science and Technology, Tangshan 063210, China
  • Rui Chen Changgeng Hospital, Institute for Precision Medicine, Tsinghua University, Beijing 100084, China
  • Qinping Liao Changgeng Hospital, Institute for Precision Medicine, Tsinghua University, Beijing 100084, China
  • Zhanlin Ji Hebei Key Laboratory of Industrial Intelligent Perception, North China University of Science and Technology, Tangshan 063210, ChinaCollege of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, China ORCID (unauthenticated)
  • Tao Lyu Changgeng Hospital, Institute for Precision Medicine, Tsinghua University, Beijing 100084, China
  • Li Zhao Beijing National Research Center for Information Science and Technology, Institute for Precision Medicine, Tsinghua University, Beijing 100084, China ORCID (unauthenticated)
Abstract
Cite
Hao, Shengnan, et al. “DTONet a Lightweight Model for Melanoma Segmentation”. Bioengineering, vol. 11, no. 4, 2024, p. 390, https://doi.org/10.3390/bioengineering11040390.
Hao, S., Wang, H., Chen, R., Liao, Q., Ji, Z., Lyu, T., & Zhao, L. (2024). DTONet a Lightweight Model for Melanoma Segmentation. Bioengineering, 11(4), 390. https://doi.org/10.3390/bioengineering11040390
Hao S, Wang H, Chen R, Liao Q, Ji Z, Lyu T, et al. DTONet a Lightweight Model for Melanoma Segmentation. Bioengineering. 2024;11(4):390.
Journal Categories
Medicine
Medicine (General)
Medical technology
Science
Biology (General)
Technology
Technology
Chemical technology
Biotechnology
Technology
Engineering (General)
Civil engineering (General)
Description

Can deep learning accurately detect melanoma with limited computing power? This paper introduces DTONet (double-tailed octave network), a lightweight deep learning network specifically designed for melanoma segmentation. It is able to achieve high segmentation accuracy with minimal resource consumption. The model addresses the challenge of deploying effective diagnostic tools in resource-constrained environments, such as hospitals with limited hardware. With just 30,859 computational parameters, DTONet achieves superior performance compared to other models, with significant improvement in IOU, demonstrating good accuracy. To validate the generalization capability of this model, we conducted tests on the PH2 dataset, and the results still outperformed existing models. Its parameter count is only 1/256th of the mainstream UNet model. Therefore, the proposed DTONet network exhibits excellent generalization ability and is sufficiently outstanding. DTONet offers a promising solution for accurate and efficient melanoma segmentation, particularly in settings where computational resources are limited.

This paper aligns with Bioengineering's focus on engineering principles in biological systems. Presenting a lightweight deep learning network for melanoma segmentation, the study fits within the journal's scope, addressing the need for efficient diagnostic tools in healthcare using bioengineering approaches. The study is relevant to biomedical engineers seeking to develop practical solutions for medical imaging.

Refrences