DLGRAFE-Net: A double loss guided residual attention and feature enhancement network for polyp segmentation
PLOS ONE · 12.09.2024 · 19 (9) · e0308237
DOI: 10.1371/journal.pone.0308237 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 12.09.2024. Verfasst von Jianuo Liu und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, China. Hauptthemen laut MEDLINE: Colonic Polyps, Colonoscopy. Die Arbeit wurde bisher 37-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Technologies Research and Development Program, Tsinghua Precision Medicine Foundation, Bulgarian National Science Fund.
Abstract (Originalsprache)
Colon polyps represent a common gastrointestinal form. In order to effectively treat and prevent complications arising from colon polyps, colon polypectomy has become a commonly used therapeutic approach. Accurately segmenting polyps from colonoscopy images can provide valuable information for early diagnosis and treatment. Due to challenges posed by illumination and contrast variations, noise and artifacts, as well as variations in polyp size and blurred boundaries in polyp images, the robustness of segmentation algorithms is a significant concern. To address these issues, this paper proposes a Double Loss Guided Residual Attention and Feature Enhancement Network (DLGRAFE-Net) for polyp segmentation. Firstly, a newly designed Semantic and Spatial Information Aggregation (SSIA) module is used to extract and fuse edge information from low-level feature graphs and semantic information from high-level feature graphs, generating local loss-guided training for the segmentation network. Secondly, newly designed Deep Supervision Feature Fusion (DSFF) modules are utilized to fuse local loss feature graphs with multi-level features from the encoder, addressing the negative impact of background imbalance caused by varying polyp sizes. Finally, Efficient Feature Extraction (EFE) decoding modules are used to extract spatial information at different scales, establishing longer-distance spatial channel dependencies to enhance the overall network performance. Extensive experiments conducted on the CVC-ClinicDB and Kvasir-SEG datasets demonstrate that the proposed network outperforms all mainstream networks and state-of-the-art networks, exhibiting superior performance and stronger generalization capabilities.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, China.
- Hebei Key Laboratory of Industrial Intelligent Perception, North China University of Science and Technology, Tangshan, China.
- Telecommunications Research Centre (TRC), University of Limerick, Limerick, Ireland.
- Department of Computer Systems, University of Plovdiv "Paisii Hilendarski", Plovdiv, Bulgaria.
- Institute of Mathematics and Informatics-Bulgarian Academy of Sciences, Sofia, Bulgaria.
ORCID-Profile: Ivan Ganchev
Förderung
- Key Technologies Research and Development Program
- Tsinghua Precision Medicine Foundation
- Bulgarian National Science Fund
- Telecommunications Research Centre (TRC) of University of Limerick, Ireland.
Zitieren
APA
Liu, J., Mu, J., Sun, H., Dai, C., Ji, Z., & Ganchev, I. (2024). DLGRAFE-Net: A double loss guided residual attention and feature enhancement network for polyp segmentation. PLOS ONE, 19(9), e0308237. https://doi.org/10.1371/journal.pone.0308237
Vancouver
Liu J, Mu J, Sun H, Dai C, Ji Z, Ganchev I. DLGRAFE-Net: A double loss guided residual attention and feature enhancement network for polyp segmentation. PLOS ONE. 2024;19(9):e0308237. doi:10.1371/journal.pone.0308237
BibTeX
@article{Liu2024,
author = {Liu, Jianuo and Mu, Juncheng and Sun, Haoran and Dai, Chenxu and Ji, Zhanlin and Ganchev, Ivan},
title = {DLGRAFE-Net: A double loss guided residual attention and feature enhancement network for polyp segmentation},
journal = {PLOS ONE},
year = {2024},
volume = {19},
number = {9},
pages = {e0308237},
doi = {10.1371/journal.pone.0308237}
}
EUVIMED