Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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

About

Colonoscopy is a procedure to detect colorectal polyps which are the primary cause for developing colorectal cancer. However, polyp segmentation is a challenging task due to the diverse shape, size, color, and texture of polyps, shuttle difference between polyp and its background, as well as low contrast of the colonoscopic images. To address these challenges, we propose a feature enhancement network for accurate polyp segmentation in colonoscopy images. Specifically, the proposed network enhances the semantic information using the novel Semantic Feature Enhance Module (SFEM). Furthermore, instead of directly adding encoder features to the respective decoder layer, we introduce an Adaptive Global Context Module (AGCM), which focuses only on the encoder's significant and hard fine-grained features. The integration of these two modules improves the quality of features layer by layer, which in turn enhances the final feature representation. The proposed approach is evaluated on five colonoscopy datasets and demonstrates superior performance compared to other state-of-the-art models.

Krushi Patel, Andres M. Bur, Guanghui Wang• 2021

Related benchmarks

TaskDatasetResultRank
Polyp SegmentationETIS (test)
Mean Dice68.7
86
Polyp SegmentationColonDB (test)
DICE0.756
47
Polyp SegmentationKvasir-SEG 100 random images
Dice Coefficient90
27
Polyp SegmentationCVC-ClinicDB 60 random images
mDice90
20
Polyp SegmentationKvasir 33 19 (test)
Dice Coefficient90.8
14
Polyp SegmentationColon 43 (test)
Dice75.6
14
Polyp SegmentationClinic 3 (test)
Dice90.2
14
Polyp SegmentationETIS 40 (test)
Dice68.7
14
Polyp SegmentationKvasir-SEG 13 (test)
mDic0.908
10
Polyp SegmentationClinicDB 8 (test)
mDic90.2
10
Showing 10 of 10 rows

Other info

Follow for update