Real-time diagnosis of gastric neoplasia using a probe-based Raman spectroscopy artificial intelligence system: a proof-of-concept, multicenter prospective cohort study

Raman spectroscopy is a novel technology that enables real-time assessment of tissue biomolecular alterations correlated with histopathologic changes. We prospectively evaluated SPECTRA IMDx, a fiber-optic Raman spectroscopy–AI system, for the in vivo diagnosis of high-risk gastric neoplasia. In this two-center study, 198 patients with 238 gastric lesions underwent routine white-light endoscopy (WLE) followed by SPECTRA IMDx assessment, with histopathology serving as the reference standard. In the full cohort, SPECTRA IMDx showed higher sensitivity (90.0% vs. 58.0%), specificity (81.4% vs. 58.5%), and accuracy (83.2% vs. 58.4%) than routine WLE (all P < 0.001). Of particular clinical relevance, in the paired analysis of 131 lesions, SPECTRA IMDx and WLE + BLI each achieved 79.4% accuracy. Sensitivity was 88.5% versus 80.8%, specificity 77.1% versus 79.0%, and NPV 96.4% versus 94.3%, respectively; paired comparisons of accuracy, sensitivity, and specificity were not statistically significant. These findings warrant further evaluation of automated Raman-based lesion characterization and its potential added value alongside image-enhanced endoscopy.

Authors

Institutions

Publication Details

Journal
BMC Gastroenterology
Published
2026-11-18
DOI
https://doi.org/10.1186/s12876-026-05584-w
Primary Topic
Spectroscopy Techniques in Biomedical and Chemical Research
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Real-time diagnosis of gastric neoplasia using a probe-based Raman spectroscopy artificial intelligence system: a proof-of-concept, multicenter prospective cohort study

Khek Yu Ho, Calvin Jianyi Koh, Hongzhi Xu, Shuntian Cai et al.
1 links
BMC Gastroenterology
Spectroscopy Techniques in Biomedical and Chemical Research
article

Real-time diagnosis of gastric neoplasia using a probe-based Raman spectroscopy artificial intelligence system: a proof-of-concept, multicenter prospective cohort study

Khek Yu Ho, Calvin Jianyi Koh, Hongzhi Xu, Shuntian Cai, Kun Xia, Mengjie Lin, Yapi Lu, Xiaoning Yang, Yanyun Fan, Jianlin Ren, Xunting Lin
article en

Abstract

Raman spectroscopy is a novel technology that enables real-time assessment of tissue biomolecular alterations correlated with histopathologic changes. We prospectively evaluated SPECTRA IMDx, a fiber-optic Raman spectroscopy–AI system, for the in vivo diagnosis of high-risk gastric neoplasia. In this two-center study, 198 patients with 238 gastric lesions underwent routine white-light endoscopy (WLE) followed by SPECTRA IMDx assessment, with histopathology serving as the reference standard. In the full cohort, SPECTRA IMDx showed higher sensitivity (90.0% vs. 58.0%), specificity (81.4% vs. 58.5%), and accuracy (83.2% vs. 58.4%) than routine WLE (all P < 0.001). Of particular clinical relevance, in the paired analysis of 131 lesions, SPECTRA IMDx and WLE + BLI each achieved 79.4% accuracy. Sensitivity was 88.5% versus 80.8%, specificity 77.1% versus 79.0%, and NPV 96.4% versus 94.3%, respectively; paired comparisons of accuracy, sensitivity, and specificity were not statistically significant. These findings warrant further evaluation of automated Raman-based lesion characterization and its potential added value alongside image-enhanced endoscopy.

BMC Gastroenterology
Hong Kong Polytechnic University (HK), National University of Singapore (SG), Xiamen University (CN), Zhongshan Hospital of Xiamen University (CN)
Natural Science Foundation of Xiamen City, Natural Science Foundation of Fujian Province
Good health and well-being
Spectroscopy Techniques in Biomedical and Chemical Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon