EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MASDF-Net: A Multi-Attention Codec Network with Selective and Dynamic Fusion for Skin Lesion Segmentation

Jinghao Fu, Hongmin Deng

Sensors · 20.08.2024 · 24 (16) · 5372

DOI: 10.3390/s24165372 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 20.08.2024. Verfasst von Jinghao Fu und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronics and Information Engineering, Sichuan University, Chengdu 610065, China. Hauptthemen laut MEDLINE: Algorithms, Neural Networks, Computer. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Sichuan Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automated segmentation algorithms for dermoscopic images serve as effective tools that assist dermatologists in clinical diagnosis. While existing deep learning-based skin lesion segmentation algorithms have achieved certain success, challenges remain in accurately delineating the boundaries of lesion regions in dermoscopic images with irregular shapes, blurry edges, and occlusions by artifacts. To address these issues, a multi-attention codec network with selective and dynamic fusion (MASDF-Net) is proposed for skin lesion segmentation in this study. In this network, we use the pyramid vision transformer as the encoder to model the long-range dependencies between features, and we innovatively designed three modules to further enhance the performance of the network. Specifically, the multi-attention fusion (MAF) module allows for attention to be focused on high-level features from various perspectives, thereby capturing more global contextual information. The selective information gathering (SIG) module improves the existing skip-connection structure by eliminating the redundant information in low-level features. The multi-scale cascade fusion (MSCF) module dynamically fuses features from different levels of the decoder part, further refining the segmentation boundaries. We conducted comprehensive experiments on the ISIC 2016, ISIC 2017, ISIC 2018, and PH2 datasets. The experimental results demonstrate the superiority of our approach over existing state-of-the-art methods.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsNeural Networks, ComputerHumansDeep LearningDermoscopyImage Processing, Computer-AssistedSkinImage Interpretation, Computer-Assisted

Stichwörter der Autor:innen

multi-scaleskin lesion segmentationskip connectionvision transformer

Autor:innen und Institutionen

  • School of Electronics and Information Engineering, Sichuan University, Chengdu 610065, China.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Sichuan Province

Zitieren

APA

Fu, J., & Deng, H. (2024). MASDF-Net: A Multi-Attention Codec Network with Selective and Dynamic Fusion for Skin Lesion Segmentation. Sensors, 24(16), 5372. https://doi.org/10.3390/s24165372

Vancouver

Fu J, Deng H. MASDF-Net: A Multi-Attention Codec Network with Selective and Dynamic Fusion for Skin Lesion Segmentation. Sensors. 2024;24(16):5372. doi:10.3390/s24165372

BibTeX
@article{Fu2024,
  author = {Fu, Jinghao and Deng, Hongmin},
  title = {MASDF-Net: A Multi-Attention Codec Network with Selective and Dynamic Fusion for Skin Lesion Segmentation},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {16},
  pages = {5372},
  doi = {10.3390/s24165372}
}
Kostenlos starten →