Deep learning-assisted metabolic fingerprint profiling based on V-groove and wrinkle-shaped 3D surface-enhanced Raman scattering substrate for early colorectal cancer diagnosis
Biosensors and Bioelectronics · 2026-02 · 294 · 118183
DOI: 10.1016/j.bios.2025.118183 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biosensors and Bioelectronics, 2026-02. Verfasst von Chengpeng Zhang und 10 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of High Efficiency and Clean Mechanical Manufacture of Ministry of Education, School of Mechanical Engineering, Shandong University, J…. Hauptthemen laut MEDLINE: Colorectal Neoplasms, Spectrum Analysis, Raman, Biosensing Techniques. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Youth Innovation Technology Project of Higher School in Shandong Province, Shandong Province Natural Science Foundation, Key Technology Research and Development Program of Shandong Province.
Abstract (Originalsprache)
Colorectal cancer (CRC) remains one of the leading causes of cancer-related mortality worldwide, yet more than 90 % of deaths are preventable through early detection. Here, we presented a high-performance surface-enhanced Raman scattering (SERS) substrate featuring a three-dimensional superstructure composed of micro V-groove arrays, wrinkle patterns, and silver nanoparticles (VGA/WS/AgNPs 3D-SERS), capable of detection with a sensitivity as low as 10-14 M. Using this platform, we acquired distinctive SERS fingerprints of serum metabolites associated with early CRC (eCRC), including corticosterone, homogentisic acid, and 5,6-dimethyl-4-oxo-4H-pyran-2-carboxylic acid. By integrating these metabolic signatures with a Convolutional Neural Network (CNN), we established a SERS-based eCRC Metabolites Model (SCMM), which robustly discriminated eCRC patients from healthy controls with an area under the curve (AUC) of 0.98 in the test set. The model achieved an accuracy of 0.944 and a specificity of 1.0. Notably, SCMM also demonstrated a 92.73 % positive detection rate among patients who were carcinoembryonic antigen (CEA) negative. Collectively, this work introduced a powerful platform for precise identification of eCRC patients, providing a valuable complement to conventional CEA-based diagnostics.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Key Laboratory of High Efficiency and Clean Mechanical Manufacture of Ministry of Education, School of Mechanical Engineering, Shandong University, Jinan, 250061, China; National Demonstration Center for Experimental Me…
- Department of Clinical Laboratory, The Second Qilu Hospital of Shandong University, Jinan, 250033, China.
- Department of Clinical Laboratory, Qilu Hospital of Shandong University, Jinan, 250012, China.
- Department of Clinical Laboratory, The Second Qilu Hospital of Shandong University, Jinan, 250033, China; Shandong Provincial Key Laboratory of Innovation Technology in Laboratory Medicine, Jinan, 250033, China; Shandon…
- Department of Clinical Laboratory, Qilu Hospital of Shandong University, Jinan, 250012, China; Shandong Provincial Key Laboratory of Innovation Technology in Laboratory Medicine, Jinan, 250033, China; Shandong Provincia…
Förderung
- Youth Innovation Technology Project of Higher School in Shandong Province
- Shandong Province Natural Science Foundation
- Key Technology Research and Development Program of Shandong Province
- Shandong University
- National Natural Science Foundation of China
- Taishan Scholar Foundation of Shandong Province
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Zhang, C., Tong, Y., Wang, H., Zhang, S., Li, Y., Niu, D., Liu, S., Luan, D., Li, P., Li, J., & Du, L. (2026). Deep learning-assisted metabolic fingerprint profiling based on V-groove and wrinkle-shaped 3D surface-enhanced Raman scattering substrate for early colorectal cancer diagnosis. Biosensors and Bioelectronics, 294, 118183. https://doi.org/10.1016/j.bios.2025.118183
Vancouver
Zhang C, Tong Y, Wang H, Zhang S, Li Y, Niu D, et al. Deep learning-assisted metabolic fingerprint profiling based on V-groove and wrinkle-shaped 3D surface-enhanced Raman scattering substrate for early colorectal cancer diagnosis. Biosensors and Bioelectronics. 2026;294:118183. doi:10.1016/j.bios.2025.118183
BibTeX
@article{Zhang2026,
author = {Zhang, Chengpeng and Tong, Yao and Wang, Hu and Zhang, Shujun and Li, Yanru and Niu, Dun and Liu, Shaojun and Luan, Dongrui and Li, Peilong and Li, Juan and Du, Lutao},
title = {Deep learning-assisted metabolic fingerprint profiling based on V-groove and wrinkle-shaped 3D surface-enhanced Raman scattering substrate for early colorectal cancer diagnosis},
journal = {Biosensors and Bioelectronics},
year = {2026},
volume = {294},
pages = {118183},
doi = {10.1016/j.bios.2025.118183}
}
EUVIMED