FocusNet: Transformer-enhanced Polyp Segmentation with Local and Pooling Attention
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916696195858432 |
|---|---|
| author | Zeng, Jun Santosh, KC Nayak, Deepak Rajan de Lange, Thomas Varkey, Jonas Berzin, Tyler Jha, Debesh |
| author_facet | Zeng, Jun Santosh, KC Nayak, Deepak Rajan de Lange, Thomas Varkey, Jonas Berzin, Tyler Jha, Debesh |
| contents | Colonoscopy is vital in the early diagnosis of colorectal polyps. Regular screenings can effectively prevent benign polyps from progressing to CRC. While deep learning has made impressive strides in polyp segmentation, most existing models are trained on single-modality and single-center data, making them less effective in real-world clinical environments. To overcome these limitations, we propose FocusNet, a Transformer-enhanced focus attention network designed to improve polyp segmentation. FocusNet incorporates three essential modules: the Cross-semantic Interaction Decoder Module (CIDM) for generating coarse segmentation maps, the Detail Enhancement Module (DEM) for refining shallow features, and the Focus Attention Module (FAM), to balance local detail and global context through local and pooling attention mechanisms. We evaluate our model on PolypDB, a newly introduced dataset with multi-modality and multi-center data for building more reliable segmentation methods. Extensive experiments showed that FocusNet consistently outperforms existing state-of-the-art approaches with a high dice coefficients of 82.47% on the BLI modality, 88.46% on FICE, 92.04% on LCI, 82.09% on the NBI and 93.42% on WLI modality, demonstrating its accuracy and robustness across five different modalities. The source code for FocusNet is available at https://github.com/JunZengz/FocusNet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_13597 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FocusNet: Transformer-enhanced Polyp Segmentation with Local and Pooling Attention Zeng, Jun Santosh, KC Nayak, Deepak Rajan de Lange, Thomas Varkey, Jonas Berzin, Tyler Jha, Debesh Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Colonoscopy is vital in the early diagnosis of colorectal polyps. Regular screenings can effectively prevent benign polyps from progressing to CRC. While deep learning has made impressive strides in polyp segmentation, most existing models are trained on single-modality and single-center data, making them less effective in real-world clinical environments. To overcome these limitations, we propose FocusNet, a Transformer-enhanced focus attention network designed to improve polyp segmentation. FocusNet incorporates three essential modules: the Cross-semantic Interaction Decoder Module (CIDM) for generating coarse segmentation maps, the Detail Enhancement Module (DEM) for refining shallow features, and the Focus Attention Module (FAM), to balance local detail and global context through local and pooling attention mechanisms. We evaluate our model on PolypDB, a newly introduced dataset with multi-modality and multi-center data for building more reliable segmentation methods. Extensive experiments showed that FocusNet consistently outperforms existing state-of-the-art approaches with a high dice coefficients of 82.47% on the BLI modality, 88.46% on FICE, 92.04% on LCI, 82.09% on the NBI and 93.42% on WLI modality, demonstrating its accuracy and robustness across five different modalities. The source code for FocusNet is available at https://github.com/JunZengz/FocusNet. |
| title | FocusNet: Transformer-enhanced Polyp Segmentation with Local and Pooling Attention |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.13597 |