What question did this study set out to answer?

The aim is to develop a deep learning method to aid the segmentation of gastric intestinal metaplasia using a new dataset of endoscopic images.

February 14, 2026

A Benchmark Dataset of Endoscopic Images and a Novel Deep Learning Method to Segment Gastric Intestinal Metaplasia Under Linked Color Imaging

Key Points

The aim is to develop a deep learning method to aid the segmentation of gastric intestinal metaplasia using a new dataset of endoscopic images.
Created ZD-LCI-GIM dataset with 1020 GIM and 864 non-GIM images from LCI gastroscopy.
Annotated images with expert input to ensure high-quality data.
Introduced VM-UNetV2, a novel deep learning segmentation model.
Evaluated model performance based on metrics such as IoU, accuracy, F1 score, specificity, and sensitivity.
Achieved a mean Intersection over Union (IoU) of 64.13% for GIM segmentation.
Model accuracy reached 88.79%, with an F1 score of 78.14%.
Demonstrated specificity of 90.96% and sensitivity of 82.06%.
Processed images at 34.61 frames per second on an NVIDIA RTX 4090 GPU.

Abstract

ABSTRACT Endoscopy has become a cornerstone in diagnosing gastrointestinal diseases, notably for gastric intestinal metaplasia (GIM)—a condition that significantly elevates the risk of gastric cancer. Variability in medical expertise and patient‐specific complexities render sole reliance on clinicians for GIM diagnosis a process that is both time‐intensive and challenging. There is an urgent clinical need for advanced deep learning methods to assist in clinical decision‐making, particularly in the identification and quantification of GIM areas. Linked Color Imaging (LCI) represents a pioneering advancement in endoscopic technology, offering distinctive color enhancement capabilities. However, the scarcity of GIM datasets acquired using LCI has hindered extensive exploration of tailored deep learning applications. This study directly addresses these dual challenges through two strategic approaches. Firstly, we meticulously assembled a comprehensive and unique dataset—designated as ZD‐LCI‐GIM—comprising 1020 GIM images from 249 patients and 864 non‐GIM images from 303 patients. Each image was acquired via LCI gastroscopy and meticulously annotated by seasoned gastroenterologists—measures that ensure high‐quality data for analysis. Secondly, we introduce VM‐UNetV2—a deep learning model specifically designed for medical image segmentation tasks. This model achieves impressive performance on the ZD‐LCI‐GIM dataset, with a mean Intersection over Union (IoU) of 64.13%, accuracy of 88.79%, F1 score (Dice Similarity Coefficient, DSC) of 78.14%, specificity of 90.96%, and sensitivity of 82.06% for GIM segmentation. Moreover, the model exhibits exceptional efficiency, processing 34.61 frames per second (FPS) when run on an NVIDIA RTX 4090 GPU. In addition, our algorithm demonstrates superior accuracy and competitive efficiency in comprehensive experiments on the public datasets Endoscene, CVC‐ClinicDB, Kvasir, CVC‐ColonDB, and ETIS‐LaribPolypDB. The code for this work is available at https://github.com/nobodyplayer1/VM‐UNetV2 .

Bookmark

A Benchmark Dataset of Endoscopic Images and a Novel Deep Learning Method to Segment Gastric Intestinal Metaplasia Under Linked Color Imaging

Key Points

Abstract

Cite This Study

Also Consider

Also Consider