Papers › Multi Kernel Positional Embedding ConvNeXt for Polyp Segmentation
Multi Kernel Positional Embedding ConvNeXt for Polyp Segmentation
Trong-Hieu Nguyen Mau, Quoc-Huy Trinh, Nhat-Tan Bui, Minh-Triet Tran, Hai-Dang Nguyen
Medical image segmentation is the technique that helps doctor view and has a precise diagnosis, particularly in Colorectal Cancer. Specifically, with the increase in cases, the diagnosis and identification need to be faster and more accurate for many patients; in endoscopic images, the segmentation task has been vital to helping the doctor identify the position of the polyps or the ache in the system correctly. As a result, many efforts have been made to apply deep learning to automate polyp segmentation, mostly to ameliorate the U-shape structure. However, the simple skip connection scheme in UNet leads to deficient context information and the semantic gap between feature maps from the encoder and decoder. To deal with this problem, we propose a novel framework composed of ConvNeXt backbone and Multi Kernel Positional Embedding block. Thanks to the suggested module, our method can attain better accuracy and generalization in the polyps segmentation task. Extensive experiments show that our model achieves the Dice coefficient of 0.8818 and the IOU score of 0.8163 on the Kvasir-SEG dataset. Furthermore, on various datasets, we make competitive achievement results with other previous state-of-the-art methods.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Medical Image Segmentation | Endotect Polyp Segmentation Challenge Dataset | PEFNet | DSC | 0.8565 | #2 of 2 | Archive leaderboard | report |
| Medical Image Segmentation | Endotect Polyp Segmentation Challenge Dataset | PEFNet | mIoU | 0.7967 | #2 of 2 | Archive leaderboard | report |
| Medical Image Segmentation | Kvasir-SEG | PEFNet | mIoU | 0.8163 | #46 of 58 | Archive leaderboard | report |
| Medical Image Segmentation | Kvasir-SEG | PEFNet | mean Dice | 0.8818 | #46 of 58 | Archive leaderboard | report |
| Polyp Segmentation | Kvasir-SEG | PEFNet | mDice | 0.8818 | #4 of 8 | Archive leaderboard | report |
| Polyp Segmentation | Kvasir-SEG | PEFNet | mIoU | 0.8163 | #4 of 8 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections