DEAMNet: a dual-branch mamba-CNN encoder with wavelet boundary awareness for colorectal polyp segmentation
Biomedical Signal Processing and Control · 2027-02 · 130 · 111584
DOI: 10.1016/j.bspc.2026.111584 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biomedical Signal Processing and Control, 2027-02. Verfasst von Weiwei Kong und 2 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
To address the challenge of simultaneously capturing global contextual information and local boundary details in colorectal polyp segmentation, this paper introduces a dual-branch edge-aware Mamba network (DEAMNet) built upon the effective integration of established visual recognition components. Drawing upon the prevalent Mamba-CNN hybrid paradigm, a Mamba-CNN dual encoder (MCDE) is constructed, where the state space branch captures global contextual information and the convolutional branch extracts local boundary details, with cross-attention employed to align and complementarily fuse heterogeneous features. Furthermore, by integrating data-driven learned boundaries with prior knowledge-guided wavelet boundaries, a wavelet fusion edge extraction module (WFEEM) is formulated to provide enhanced supervision for boundary segmentation, with boundary-aware cross-layer feature alignment leveraged to improve feature representation. Comparative experiments against nine state-of-the-art methods on five benchmark datasets demonstrate that DEAMNet achieves favorable performance in 13 out of 15 comparisons on both in-domain and out-of-domain datasets, indicating the practical effectiveness of this task-oriented architectural adaptation for colorectal polyp segmentation.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Kong, W., Wang, Y., & Lei, Y. (2027). DEAMNet: a dual-branch mamba-CNN encoder with wavelet boundary awareness for colorectal polyp segmentation. Biomedical Signal Processing and Control, 130, 111584. https://doi.org/10.1016/j.bspc.2026.111584
Vancouver
Kong W, Wang Y, Lei Y. DEAMNet: a dual-branch mamba-CNN encoder with wavelet boundary awareness for colorectal polyp segmentation. Biomedical Signal Processing and Control. 2027;130:111584. doi:10.1016/j.bspc.2026.111584
BibTeX
@article{Kong2027,
author = {Kong, Weiwei and Wang, Yuchen and Lei, Yang},
title = {DEAMNet: a dual-branch mamba-CNN encoder with wavelet boundary awareness for colorectal polyp segmentation},
journal = {Biomedical Signal Processing and Control},
year = {2027},
volume = {130},
pages = {111584},
doi = {10.1016/j.bspc.2026.111584}
}
EUVIMED