Efficient and real-time polyp segmentation: An empirical evaluation of lightweight Mamba integration strategies
Si Chen, Mohd Shafry Mohd Rahim, Hiew Moi Sim, Yee Yong Pang, Pei Kian Teo, Ei Lin Ong, Wei Jer Lim · 2026
Read Efficient and real-time polyp segmentation: An empirical evaluation of lightweight Mamba integration strategies by Si Chen, Mohd Shafry Mohd Rahim, Hiew Moi Sim, Yee Yong Pang, Pei Kian Teo, Ei Lin Ong, Wei Jer Lim (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0353562.txt.
Description
Si Chen and co-authors evaluated in 2026 lightweight ways of adding a newer sequence model, called Mamba, to the task of outlining polyps in colonoscopy images. Polyp segmentation, drawing the exact boundary of a growth in the colon, helps doctors find and remove growths before they can turn cancerous. The software must run in real time during the procedure, on hardware a clinic can afford, which is why light weight matters in their tests.
Their empirical evaluation compares several strategies for integrating the model and measures the trade off between accuracy and speed. Endoscopy is one of the clearest cases where artificial intelligence can earn its place beside the doctor, and studies like this decide which designs are practical enough to try.
Catalog record
| CREATOR | Si Chen, Mohd Shafry Mohd Rahim, Hiew Moi Sim, Yee Yong Pang, Pei Kian Teo, Ei Lin Ong, Wei Jer Lim |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 60942 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |