EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DBE-Net: Dual Boundary-Guided Attention Exploration Network for Polyp Segmentation

Haichao Ma iD, Chao Xu, Chao Nie, Jubao Han, Yingjie Li, Chuanxu Liu

Diagnostics · 27.02.2023 · 13 (5) · 896

DOI: 10.3390/diagnostics13050896 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 27.02.2023. Verfasst von Haichao Ma und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Integrated Circuits, Anhui University, Hefei 230601, China. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Key Research and Development Program of China, National Key Research and Development Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automatic segmentation of polyps during colonoscopy can help doctors accurately find the polyp area and remove abnormal tissues in time to reduce the possibility of polyps transforming into cancer. However, the current polyp segmentation research still has the following problems: blurry polyp boundaries, multi-scale adaptability of polyps, and close resemblances between polyps and nearby normal tissues. To tackle these issues, this paper proposes a dual boundary-guided attention exploration network (DBE-Net) for polyp segmentation. Firstly, we propose a dual boundary-guided attention exploration module to solve the boundary-blurring problem. This module uses a coarse-to-fine strategy to progressively approximate the real polyp boundary. Secondly, a multi-scale context aggregation enhancement module is introduced to accommodate the multi-scale variation of polyps. Finally, we propose a low-level detail enhancement module, which can extract more low-level details and promote the performance of the overall network. Extensive experiments on five polyp segmentation benchmark datasets show that our method achieves superior performance and stronger generalization ability than state-of-the-art methods. Especially for CVC-ColonDB and ETIS, two challenging datasets among the five datasets, our method achieves excellent results of 82.4% and 80.6% in terms of mDice (mean dice similarity coefficient) and improves by 5.1% and 5.9% compared to the state-of-the-art methods.

Schlagwörter

Stichwörter der Autor:innen

boundary explorationcolonoscopycolorectal cancerdeep learningmedical image analysispolyp segmentation

Autor:innen und Institutionen

  • School of Integrated Circuits, Anhui University, Hefei 230601, China.
  • Anhui Engineering Laboratory of Agro-Ecological Big Data, Hefei 230601, China.

ORCID-Profile: Haichao Ma

Förderung

  • the National Key Research and Development Program of China
  • National Key Research and Development Program of China

Zitieren

APA

Ma, H., Xu, C., Nie, C., Han, J., Li, Y., & Liu, C. (2023). DBE-Net: Dual Boundary-Guided Attention Exploration Network for Polyp Segmentation. Diagnostics, 13(5), 896. https://doi.org/10.3390/diagnostics13050896

Vancouver

Ma H, Xu C, Nie C, Han J, Li Y, Liu C. DBE-Net: Dual Boundary-Guided Attention Exploration Network for Polyp Segmentation. Diagnostics. 2023;13(5):896. doi:10.3390/diagnostics13050896

BibTeX
@article{Ma2023,
  author = {Ma, Haichao and Xu, Chao and Nie, Chao and Han, Jubao and Li, Yingjie and Liu, Chuanxu},
  title = {DBE-Net: Dual Boundary-Guided Attention Exploration Network for Polyp Segmentation},
  journal = {Diagnostics},
  year = {2023},
  volume = {13},
  number = {5},
  pages = {896},
  doi = {10.3390/diagnostics13050896}
}
Kostenlos starten →