Enhanced U-Net: A Feature Enhancement Network for Polyp Segmentation

Patel, Krushi; Bur, Andrés M.; Wang, Guanghui

doi:10.1109/crv52889.2021.00032

Cited by 86 publications

(22 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to further quantitatively analyze the segmentation performance of MGF‐Net, this chapter also introduced ResUnet++, 16 SFANet, 39 ACS‐Net, 40 EU‐Net, 41 TMDUNet, 42 and APSUNet 43 for numerical comparison. Table 1 presents the quantitative results of MGF‐Net and mainstream methods on the Kvasir and CVC‐ClinicDB datasets, where the best metric is marked in red.…”

Section: Resultsmentioning

confidence: 99%

MGF‐net: Multi‐channel group fusion enhancing boundary attention for polyp segmentation

et al. 2023

View full text Add to dashboard Cite

BackgroundColonic polyps are the most prevalent neoplastic lesions detected during colorectal cancer screening, and timely detection and excision of these precursor lesions is crucial for preventing multiple malignancies and reducing mortality rates.PurposeThe pressing need for intelligent polyp detection has led to the development of a high‐precision intelligent polyp segmentation network designed to improve polyp screening rates during colonoscopies.MethodsIn this study, we employed ResNet50 as the backbone network and embedded a multi‐channel grouping fusion encoding module in the third to fifth stages to extract high‐level semantic features of polyps. Receptive field modules were utilized to capture multi‐scale features, and grouping fusion modules were employed to capture salient features in different group channels, guiding the decoder to generate an initial global mapping with improved accuracy. To refine the segmentation of the initial global mapping, we introduced an enhanced boundary weight attention module that adaptively thresholds the initial global mapping using learnable parameters. A self‐attention mechanism was then utilized to calculate the long‐distance dependency relationship of the polyp boundary area, resulting in an output feature map with enhanced boundaries that effectively refines the boundary of the target area.ResultsWe carried out contrast experiments of MGF‐Net with mainstream polyp segmentation networks on five public datasets of ColonDB, CVC‐ColonDB, CVC‐612, Kvasir, and ETIS. The results demonstrate that the segmentation accuracy of MGF‐Net is significantly improved on the datasets. Furthermore, a hypothesis test was conducted to assess the statistical significance of the computed results.ConclusionsOur proposed MGF‐Net outperforms existing mainstream baseline networks and presents a promising solution to the pressing need for intelligent polyp detection. The proposed model is available at https://github.com/xiefanghhh/MGF‐NET.

show abstract

Section: Resultsmentioning

confidence: 99%

MGF‐net: Multi‐channel group fusion enhancing boundary attention for polyp segmentation

et al. 2023

View full text Add to dashboard Cite

show abstract

“…However, the texture of intestinal polyps is similar to its surrounding background tissue, and the size and color of polyps are different, resulting in unsatisfactory segmentation results of these methods. With the rapid development of deep learning technology, U-Net [7] and its variants [13,14,15,16] have been widely used in polyp segmentation tasks. For U-Net, skip connection is used to fuse the encoder features and decoder features at different stages to alleviate the problem of spatial information loss during downsampling.…”

Section: Related Work 21 Polyp Segmentationmentioning

confidence: 99%

MSCFF-Net : Multi-scale context feature fusion network for polyp segmentation

Li,

Zhang,

Yin

et al. 2024

Preprint

View full text Add to dashboard Cite

Accurate segmentation of polyps in colonoscopic images is a key step in computer-aided diagnosis of colorectal cancer. Although the current segmentation algorithm has some achievements in the field of polyp segmentation, there are still some challenges. The size and shape of the polyp area are different, and the boundary with the background is not obvious. In order to solve the above problems, we propose a new multi-scale context information fusion network(MSCFF-Net). Specifically, the network first uses pyramid transformer (PVTv2) as the encoder, and designs a feature interactive decoder (FID) to obtain a rough location map of the polyp area. Then, four multi-stage feature fusion modules (MSFF) are designed to realize the interaction of multi-stage feature information and enrich the scale diversity of polyp features. Finally, multi-scale attention (MSA) is introduced behind the multi-stage fusion module to improve the attention of the model to polyp features. Experiments on two public polyp datasets show that MSCFF-Net is superior to other advanced polyp segmentation methods.

show abstract

“…3) Extensive Evaluation for Polyp Segmentation: We compare our model to the most popular polyp image segmentation models, including ACSNet [49], PraNet [37], MSEG [50], DCRNet [51], EUNet [52], SANet [53] and Polyp-PVT [54].…”

Section: ) Visualized Comparison For Skin Lesion Segmentationmentioning

confidence: 99%

XBound-Former: Toward Cross-scale Boundary Modeling in Transformers

Wang¹,

Chen²,

Ma³

et al. 2022

Preprint

View full text Add to dashboard Cite

Skin lesion segmentation from dermoscopy images is of great significance in the quantitative analysis of skin cancers, which is yet challenging even for dermatologists due to the inherent issues, i.e., considerable size, shape and color variation, and ambiguous boundaries. Recent vision transformers have shown promising performance in handling the variation through global context modeling. Still, they have not thoroughly solved the problem of ambiguous boundaries as they ignore the complementary usage of the boundary knowledge and global contexts. In this paper, we propose a novel cross-scale boundary-aware transformer, XBound-Former, to simultaneously address the variation and boundary problems of skin lesion segmentation. XBound-Former is a purely attention-based network and catches boundary knowledge via three specially designed learners. First, we propose an implicit boundary learner (im-Bound) to constrain the network attention on the points with noticeable boundary variation, enhancing the local context modeling while maintaining the global context. Second, we propose an explicit boundary learner (ex-Bound) to extract the boundary knowledge and convert it into embeddings explicitly. We learn the knowledge at different scales, offering multi-scale perspectives to exploit the boundary representations. Third, based on the learned multi-scale boundary embeddings, we propose a cross-scale boundary learner (X-Bound) to simultaneously address the problem of ambiguous and multi-scale boundaries by using learned boundary embedding from one scale to guide the boundary-aware attention on the other scales. We evaluate the model on two skin lesion datasets, ISIC-2016&PH 2

show abstract

Enhanced U-Net: A Feature Enhancement Network for Polyp Segmentation

Cited by 86 publications

References 34 publications

MGF‐net: Multi‐channel group fusion enhancing boundary attention for polyp segmentation

MGF‐net: Multi‐channel group fusion enhancing boundary attention for polyp segmentation

MSCFF-Net : Multi-scale context feature fusion network for polyp segmentation

XBound-Former: Toward Cross-scale Boundary Modeling in Transformers

Contact Info

Product

Resources

About