Related Experiment Video
Updated: Jan 15, 2026
07:54
Surface-enhanced Resonance Raman Scattering Nanoprobe Ratiometry for Detecting Microscopic Ovarian Cancer via Folate Receptor Targeting
Published on: March 25, 2019
8.6K
A machine learning-enhanced gastric cancer diagnostic method based on shell-isolated nanoparticle-enhanced Raman
Mengya Li1,2, Liyi Li3,4, Pan Yang3,4
1Department of Laboratory Medicine, First Affiliated Hospital, Third Military Medical University (Army Medical University), Chongqing 400038, China.
Nanoscale
|October 13, 2025
Summary
This study introduces a new serum test using shell-isolated nanoparticle-enhanced Raman spectroscopy (SHINERS) for early gastric cancer (GC) detection. The SHINERS method combined with machine learning shows promise for rapid, non-invasive gastric cancer screening.
Area of Science:
- Nanotechnology
- Biomedical Diagnostics
- Spectroscopy
Background:
- Gastric cancer (GC) is a leading cause of cancer death globally.
- Early detection is crucial for improving patient outcomes.
- Current diagnostic methods have limitations in efficiency and invasiveness.
Purpose of the Study:
- To develop a non-invasive serum diagnostic approach for early gastric cancer detection.
- To utilize shell-isolated nanoparticle-enhanced Raman spectroscopy (SHINERS) for improved signal enhancement and specificity.
- To evaluate the performance of machine learning models for classifying gastric cancer based on serum spectra.
Main Methods:
- Synthesis of silver-coated silica (Ag@SiO2) core-shell nanoparticles as SHINERS substrates.
- Collection of serum samples from 100 GC patients and 100 healthy controls.
- Analysis of serum samples using SHINERS and development of four machine learning classification models (1D-CNN, RF, SVM, kNN).
Main Results:
- SHINERS provided distinct molecular fingerprint spectra with high signal-to-noise ratios from small serum volumes within a short detection window.
- The Support Vector Machine (SVM) model achieved the highest classification performance, with an area under the ROC curve of 0.9000.
- The SVM model significantly outperformed other tested machine learning algorithms (p < 0.01).
Conclusions:
- The combination of SHINERS and machine learning offers a feasible strategy for reliable, rapid, and minimally invasive gastric cancer screening.
- This approach demonstrates significant potential for clinical diagnostic applications in early gastric cancer detection.
- SHINERS technology effectively overcomes limitations of conventional Raman spectroscopy for biological sample analysis.
