DKNET: A Hybrid Model with Enhanced Attention and Multi-level Fusion for Accurate Early Polyp Segmentation.
Saved in:
| Title: | DKNET: A Hybrid Model with Enhanced Attention and Multi-level Fusion for Accurate Early Polyp Segmentation. |
|---|---|
| Authors: | Dehong Kong1 1839079041@qq.com, Jie Liu2 17359111@qq.com, Xiang Zhou3 702603395@qq.com, Wenyu Zhang4 zhangwenyu8518@126.com, Yixiao Sun3 robinsunyixiao@163.com, Jieyi Xu3 232081203006@stu.ustl.edu.cn, Qinghong Zeng5 1600250563@qq.com |
| Source: | Engineering Letters. Dec2025, Vol. 33 Issue 12, p5003-5014. 12p. |
| Subjects: | Image segmentation, Colon polyps, Artificial neural networks, Cancer prevention, Deep learning |
| Abstract: | Colorectal polyps are gastrointestinal growths that may develop into colorectal cancer, so the early detection and removal of these polyps are crucial for cancer prevention. In recent years, deep-learning techniques have made significant progress in colorectal polyp image segmentation, significantly enhancing segmentation accuracy and automation. However, early-stage polyps are often small, irregularly shaped, and typically hidden within larger organs or complex backgrounds, making them difficult to detect and segment. Existing segmentation models face challenges in effectively handling such polyps due to the lack of specialized structures for small-scale targets and the inability to integrate local detail information with global context effectively. In this paper, we propose the DKNET model, which leverages an enhanced attention mechanism (the DCE module) and a multi-level fusion strategy (the K-Fusion module) to tackle the challenges posed by small-scale polyps and complex segmentation tasks. Experimental results demonstrate that the proposed model performs well across multiple polyp datasets. Notably, on datasets with a high prevalence of small-scale polyps, such as CVC-ColonDB and Kvasir, the model achieves DICE scores of 82.68% and 92.39%, and mIoU scores of 74.75% and 87.27%, respectively, showcasing its effectiveness in handling challenging cases with small-scale targets. Compared to the state-of-the-art segmentation model PVT-GCASCAD, the proposed model achieves notable gains of 1.2% and 0.34% in DICE scores, and 1.1% and 0.36% in mIoU scores on CVC-ColonDB and Kvasir datasets, respectively. Additionally, its strong generalization capability is demonstrated by favorable performance on other datasets within this domain. [ABSTRACT FROM AUTHOR] |
| Copyright of Engineering Letters is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Links: – Type: pdflink Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 189696749 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: DKNET: A Hybrid Model with Enhanced Attention and Multi-level Fusion for Accurate Early Polyp Segmentation. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Dehong+Kong%22">Dehong Kong</searchLink><relatesTo>1</relatesTo><i> 1839079041@qq.com</i><br /><searchLink fieldCode="AR" term="%22Jie+Liu%22">Jie Liu</searchLink><relatesTo>2</relatesTo><i> 17359111@qq.com</i><br /><searchLink fieldCode="AR" term="%22Xiang+Zhou%22">Xiang Zhou</searchLink><relatesTo>3</relatesTo><i> 702603395@qq.com</i><br /><searchLink fieldCode="AR" term="%22Wenyu+Zhang%22">Wenyu Zhang</searchLink><relatesTo>4</relatesTo><i> zhangwenyu8518@126.com</i><br /><searchLink fieldCode="AR" term="%22Yixiao+Sun%22">Yixiao Sun</searchLink><relatesTo>3</relatesTo><i> robinsunyixiao@163.com</i><br /><searchLink fieldCode="AR" term="%22Jieyi+Xu%22">Jieyi Xu</searchLink><relatesTo>3</relatesTo><i> 232081203006@stu.ustl.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Qinghong+Zeng%22">Qinghong Zeng</searchLink><relatesTo>5</relatesTo><i> 1600250563@qq.com</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Engineering+Letters%22">Engineering Letters</searchLink>. Dec2025, Vol. 33 Issue 12, p5003-5014. 12p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Image+segmentation%22">Image segmentation</searchLink><br /><searchLink fieldCode="DE" term="%22Colon+polyps%22">Colon polyps</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Cancer+prevention%22">Cancer prevention</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Colorectal polyps are gastrointestinal growths that may develop into colorectal cancer, so the early detection and removal of these polyps are crucial for cancer prevention. In recent years, deep-learning techniques have made significant progress in colorectal polyp image segmentation, significantly enhancing segmentation accuracy and automation. However, early-stage polyps are often small, irregularly shaped, and typically hidden within larger organs or complex backgrounds, making them difficult to detect and segment. Existing segmentation models face challenges in effectively handling such polyps due to the lack of specialized structures for small-scale targets and the inability to integrate local detail information with global context effectively. In this paper, we propose the DKNET model, which leverages an enhanced attention mechanism (the DCE module) and a multi-level fusion strategy (the K-Fusion module) to tackle the challenges posed by small-scale polyps and complex segmentation tasks. Experimental results demonstrate that the proposed model performs well across multiple polyp datasets. Notably, on datasets with a high prevalence of small-scale polyps, such as CVC-ColonDB and Kvasir, the model achieves DICE scores of 82.68% and 92.39%, and mIoU scores of 74.75% and 87.27%, respectively, showcasing its effectiveness in handling challenging cases with small-scale targets. Compared to the state-of-the-art segmentation model PVT-GCASCAD, the proposed model achieves notable gains of 1.2% and 0.34% in DICE scores, and 1.1% and 0.36% in mIoU scores on CVC-ColonDB and Kvasir datasets, respectively. Additionally, its strong generalization capability is demonstrated by favorable performance on other datasets within this domain. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Engineering Letters is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=189696749 |
| RecordInfo | BibRecord: BibEntity: Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 12 StartPage: 5003 Subjects: – SubjectFull: Image segmentation Type: general – SubjectFull: Colon polyps Type: general – SubjectFull: Artificial neural networks Type: general – SubjectFull: Cancer prevention Type: general – SubjectFull: Deep learning Type: general Titles: – TitleFull: DKNET: A Hybrid Model with Enhanced Attention and Multi-level Fusion for Accurate Early Polyp Segmentation. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Dehong Kong – PersonEntity: Name: NameFull: Jie Liu – PersonEntity: Name: NameFull: Xiang Zhou – PersonEntity: Name: NameFull: Wenyu Zhang – PersonEntity: Name: NameFull: Yixiao Sun – PersonEntity: Name: NameFull: Jieyi Xu – PersonEntity: Name: NameFull: Qinghong Zeng IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 12 Text: Dec2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 1816093X Numbering: – Type: volume Value: 33 – Type: issue Value: 12 Titles: – TitleFull: Engineering Letters Type: main |
| ResultId | 1 |
