Efficient and real-time polyp segmentation: An empirical evaluation of lightweight Mamba integration strategies
4 affiliations
- 1Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, Malaysia
- 2School of Artificial Intelligence, Guangzhou Institute of Science and Technology, Guangzhou, China
- 3Faculty of Art and Design, Southern University College, Johor Bahru, Malaysia
- 4Faculty of Engineering and Information Technology, Southern University College, Johor Bahru, Malaysia
Abstract
Accurate and efficient polyp segmentation is essential for computer-aided colorectal cancer screening, yet achieving a favorable balance among segmentation accuracy, computational efficiency, and cross-dataset generalization remains challenging. Recent studies suggest that Mamba-based state-space modeling can enhance long-range dependency modeling with relatively low complexity, but how lightweight Mamba integration strategies affect dense prediction frameworks for polyp segmentation remains insufficiently understood. In this study, we present LiteMamba-Seg, a lightweight polyp segmentation framework built on a U-Net-like encoder–decoder architecture with a ResNet34 backbone, and conduct an empirical evaluation of different lightweight Mamba integration strategies. Specifically, we investigate bottleneck-only integration as well as alternative second-stage placements at an encoder-side intermediate stage and a decoder-side reconstruction stage. Experimental results on four public benchmark datasets show that LiteMamba-Seg achieves competitive segmentation performance while maintaining a lightweight design and real-time model-level inference, with 26.81 M parameters, 13.89 GFLOPs, and 167.73 FPS. Further ablation, controlled placement, multi-seed, robustness, boundary, calibration, and false-positive analyses indicate that the effect of Mamba integration depends on its placement within the network. In particular, decoder-side reconstruction-stage integration yields more favorable quantitative and qualitative results than encoder-side intermediate placement across the evaluated benchmarks. These findings suggest that, for lightweight polyp segmentation frameworks, Mamba integration should be considered jointly with placement strategy rather than simply increasing the number of sequence modeling blocks.
Related
- Efficient Uzawa algorithms with projection strategies for geodynamic Stokes flow
- Evaluation of soil degradation caused by wildfire through integration of remote sensing soil quality indices and micromorphological analyses
- Comparative Evaluation of Regeneration Strategies for Rhodamine B Removal Using Raw Date Seeds: Insights into Adsorption Mechanisms
- Development of a lightweight broadband cavity-enhanced spectrometer system for simultaneous monitoring of HONO and NO2
- GFLNet: A lightweight real-time detector with knowledge-guided compression in remote sensing images
BibTeX
@article{chen2026efficient,
title = {{Efficient and real-time polyp segmentation: An empirical evaluation of lightweight Mamba integration strategies}},
author = {Si Chen and Mohd Shafry Mohd Rahim and Hiew Moi Sim and Yee Yong Pang and Pei Kian Teo and Ei Lin Ong and Wei Jer Lim},
journal = {PLOS One},
year = {2026},
month = oct,
doi = {10.1371/journal.pone.0353562},
url = {https://doi.org/10.1371/journal.pone.0353562},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Efficient and real-time polyp segmentation: An empirical evaluation of lightweight Mamba integration strategies
AU - Si Chen
AU - Mohd Shafry Mohd Rahim
AU - Hiew Moi Sim
AU - Yee Yong Pang
AU - Pei Kian Teo
AU - Ei Lin Ong
AU - Wei Jer Lim
PY - 2026
DA - 2026/10/09
JO - PLOS One
DO - 10.1371/journal.pone.0353562
UR - https://doi.org/10.1371/journal.pone.0353562
AB - Accurate and efficient polyp segmentation is essential for computer-aided colorectal cancer screening, yet achieving a favorable balance among segmentation accuracy, computational efficiency, and cross-dataset generalization remains challenging. Recent studies suggest that Mamba-based state-space modeling can enhance long-range dependency modeling with relatively low complexity, but how lightweight Mamba integration strategies affect dense prediction frameworks for polyp segmentation remains insufficiently understood. In this study, we present LiteMamba-Seg, a lightweight polyp segmentation framework built on a U-Net-like encoder–decoder architecture with a ResNet34 backbone, and conduct an empirical evaluation of different lightweight Mamba integration strategies. Specifically, we investigate bottleneck-only integration as well as alternative second-stage placements at an encoder-side intermediate stage and a decoder-side reconstruction stage. Experimental results on four public benchmark datasets show that LiteMamba-Seg achieves competitive segmentation performance while maintaining a lightweight design and real-time model-level inference, with 26.81 M parameters, 13.89 GFLOPs, and 167.73 FPS. Further ablation, controlled placement, multi-seed, robustness, boundary, calibration, and false-positive analyses indicate that the effect of Mamba integration depends on its placement within the network. In particular, decoder-side reconstruction-stage integration yields more favorable quantitative and qualitative results than encoder-side intermediate placement across the evaluated benchmarks. These findings suggest that, for lightweight polyp segmentation frameworks, Mamba integration should be considered jointly with placement strategy rather than simply increasing the number of sequence modeling blocks.
SN - 1932-6203
ER -