EUVIMEDEUVIMED entdecken
Crossref

Deep learning enabled open-set bacteria recognition using surface-enhanced Raman spectroscopy

Hanyu Cao, Jie Cheng, Xing Ma, Shan Liu, Jinhong Guo, Diangeng Li

Biosensors and Bioelectronics · 2025-05 · 276 · 117245

DOI: 10.1016/j.bios.2025.117245 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biosensors and Bioelectronics, 2025-05. Verfasst von Hanyu Cao und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Sensing Science and Engineering, Shanghai Jiao Tong University, 800 Dongchuan RD. Minhang District, Shanghai, 200240, China. Electronic add…. Hauptthemen laut MEDLINE: Spectrum Analysis, Raman, Deep Learning, Bacteria, Biosensing Techniques. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 33 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate bacterial identification is vital in medical and healthcare settings. Traditional methods, though reliable, are often time-consuming, underscoring the need for faster, more efficient alternatives. Deep learning-assisted Surface-enhanced Raman spectroscopy (SERS) offers a rapid and sensitive method, demonstrating high accuracy in bacterial identification. However, current deep learning models for bacterial SERS spectra classification typically operate under a closed-set paradigm, limiting their effectiveness when encountering bacterial species outside the training set. In response to this challenge, we propose a transformer-based neural network for open-set bacterial recognition using SERS spectra. Our model utilizes a combination of classification and reconstruction tasks, rejecting unknown species by analyzing reconstruction errors. Experimental results show that the proposed model outperforms traditional open-set recognition approaches, providing superior accuracy in both classifying known species and rejecting unknown ones. This study addresses the limitations of existing closed-set methods, improving the robustness of bacterial identification in real-world scenarios and demonstrating the potential of integrating SERS with transformer models for medical and healthcare applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Spectrum Analysis, RamanDeep LearningBacteriaBiosensing TechniquesNeural Networks, Computer

Stichwörter der Autor:innen

Bacteria identificationDeep learningOpen-set recognitionSurface-enhanced Raman spectroscopy (SERS)Transformer

Autor:innen und Institutionen

  • School of Sensing Science and Engineering, Shanghai Jiao Tong University, 800 Dongchuan RD. Minhang District, Shanghai, 200240, China. Electronic address: torinonegai@sjtu.edu.cn.
  • School of Sensing Science and Engineering, Shanghai Jiao Tong University, 800 Dongchuan RD. Minhang District, Shanghai, 200240, China. Electronic address: chengjie190@sjtu.edu.cn.
  • School of Integrated Circuits, Harbin Institute of Technology (Shenzhen), HIT Campus of University Town of Shenzhen, Shenzhen, 518055, China. Electronic address: maxing@hit.edu.cn.
  • Department of Laboratory Medicine, Sichuan Academy of Medical Sciences and Sichuan Provincial People's Hospital, University of Electronic Science and Technology, Chengdu, 610072, China. Electronic address: Shanliusyy@16…
  • School of Sensing Science and Engineering, Shanghai Jiao Tong University, 800 Dongchuan RD. Minhang District, Shanghai, 200240, China. Electronic address: guojinhong@sjtu.edu.cn.
  • Department of Academic Research, Beijing Ditan Hospital, Capital Medical University, National Center for Infectious Diseases(BeiJing), 8th Jingshun East Road, Beijing, 100015, China. Electronic address: lidiangeng@126.c…

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Cao, H., Cheng, J., Ma, X., Liu, S., Guo, J., & Li, D. (2025). Deep learning enabled open-set bacteria recognition using surface-enhanced Raman spectroscopy. Biosensors and Bioelectronics, 276, 117245. https://doi.org/10.1016/j.bios.2025.117245

Vancouver

Cao H, Cheng J, Ma X, Liu S, Guo J, Li D. Deep learning enabled open-set bacteria recognition using surface-enhanced Raman spectroscopy. Biosensors and Bioelectronics. 2025;276:117245. doi:10.1016/j.bios.2025.117245

BibTeX
@article{Cao2025,
  author = {Cao, Hanyu and Cheng, Jie and Ma, Xing and Liu, Shan and Guo, Jinhong and Li, Diangeng},
  title = {Deep learning enabled open-set bacteria recognition using surface-enhanced Raman spectroscopy},
  journal = {Biosensors and Bioelectronics},
  year = {2025},
  volume = {276},
  pages = {117245},
  doi = {10.1016/j.bios.2025.117245}
}
Kostenlos starten →