EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Edge-Enhanced Network for Polyp Segmentation

Yao Tong iD, Ziqi Chen, Zuojian Zhou, Yun Hu, Xin Li iD, Xuebin Qiao

Bioengineering · 25.09.2024 · 11 (10) · 959

DOI: 10.3390/bioengineering11100959 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 25.09.2024. Verfasst von Yao Tong und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine, Nanjing 210023, China. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Development Plan of Traditional Chinese Medicine (TCM) in Jiangsu Province, Jiangsu Province Engineering Research Center of TCM Intelligence Health Service, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Colorectal cancer remains a leading cause of cancer-related deaths worldwide, with early detection and removal of polyps being critical in preventing disease progression. Automated polyp segmentation, particularly in colonoscopy images, is a challenging task due to the variability in polyp appearance and the low contrast between polyps and surrounding tissues. In this work, we propose an edge-enhanced network (EENet) designed to address these challenges by integrating two novel modules: the covariance edge-enhanced attention (CEEA) and cross-scale edge enhancement (CSEE) modules. The CEEA module leverages covariance-based attention to enhance boundary detection, while the CSEE module bridges multi-scale features to preserve fine-grained edge details. To further improve the accuracy of polyp segmentation, we introduce a hybrid loss function that combines cross-entropy loss with edge-aware loss. Extensive experiments show that the EENet achieves a Dice score of 0.9208 and an IoU of 0.8664 on the Kvasir-SEG dataset, surpassing state-of-the-art models such as Polyp-PVT and PraNet. Furthermore, it records a Dice score of 0.9316 and an IoU of 0.8817 on the CVC-ClinicDB dataset, demonstrating its strong potential for clinical application in polyp segmentation. Ablation studies further validate the contribution of the CEEA and CSEE modules.

Schlagwörter

Stichwörter der Autor:innen

attention mechanismconvolutional neural networkedge enhancementpolyp segmentation

Autor:innen und Institutionen

  • School of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine, Nanjing 210023, China.
  • Jiangsu Province Engineering Research Center of TCM Intelligence Health Service, Nanjing University of Chinese Medicine, Nanjing 210023, China.
  • Vanke School of Public Health, Tsinghua University, Beijing 100084, China.
  • College of Computer Science and Software Engineering, Hohai University, Nanjing 211100, China.
  • School of Elderly Care Services and Management, Nanjing University of Chinese Medicine, Nanjing 210023, China.

ORCID-Profile: Yao Tong, Xin Li

Förderung

  • the Development Plan of Traditional Chinese Medicine (TCM) in Jiangsu Province
  • Jiangsu Province Engineering Research Center of TCM Intelligence Health Service
  • National Natural Science Foundation of China
  • Development Plan of Traditional Chinese Medicine (TCM) in Jiangsu Province
  • Natural Science Foundation of China

Zitieren

APA

Tong, Y., Chen, Z., Zhou, Z., Hu, Y., Li, X., & Qiao, X. (2024). An Edge-Enhanced Network for Polyp Segmentation. Bioengineering, 11(10), 959. https://doi.org/10.3390/bioengineering11100959

Vancouver

Tong Y, Chen Z, Zhou Z, Hu Y, Li X, Qiao X. An Edge-Enhanced Network for Polyp Segmentation. Bioengineering. 2024;11(10):959. doi:10.3390/bioengineering11100959

BibTeX
@article{Tong2024,
  author = {Tong, Yao and Chen, Ziqi and Zhou, Zuojian and Hu, Yun and Li, Xin and Qiao, Xuebin},
  title = {An Edge-Enhanced Network for Polyp Segmentation},
  journal = {Bioengineering},
  year = {2024},
  volume = {11},
  number = {10},
  pages = {959},
  doi = {10.3390/bioengineering11100959}
}
Kostenlos starten →