Lightweight deep learning model for gastrointestinal precancerous lesion screening with attention enhancement

Shuai Chen, Jingyao Cai, Zhixiang Wu, Xiangyu Liu, Qing Wang, Liming Zhou · 2026

Read Lightweight deep learning model for gastrointestinal precancerous lesion screening with attention enhancement by Shuai Chen, Jingyao Cai, Zhixiang Wu, Xiangyu Liu, Qing Wang, Liming Zhou (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/pmc-13276617.txt.

Description

Shuai Chen and colleagues present a lightweight AI model for screening gut lesions in endoscopy images, published in 2026. Precancerous growths such as colorectal polyps need early spotting, yet heavy models strain clinic hardware. Their design aims for accuracy, small size, and decisions doctors can inspect.

An attention module was added to a compact MobileNetV3 network to weight location and channel information together. The model trained on three thousand Kvasir images across normal tissue, polyps, and ulcerative colitis. Overall accuracy reached just over ninety-nine percent, with perfect precision on polyps. Heat maps confirmed the model looked at the lesion itself, and the whole model fits in about four megabytes.

Catalog record

CREATORShuai Chen, Jingyao Cai, Zhixiang Wu, Xiangyu Liu, Qing Wang, Liming Zhou
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE59 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13276617

Browse the full library · About the Tower of Babel