EUVIMEDEUVIMED entdecken
Open Access

Multi‐Class and Multi‐Level Classification for Common Wound Bacteria Based on Reflectance Hyperspectral Imaging

Decheng Wu, Xudong Fu, Wendan Liu, Sheng Yin, Chang Liu, Jiaqi Zhao, Hailin Cao iD, Lianyang Zhang, Zhen Wang, Hao Tang

Journal of Biophotonics · 2026-07 · 19 (7)

DOI: 10.1002/jbio.70318 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Biophotonics, online erschienen am 23.07.2026. Verfasst von Decheng Wu und 9 weiteren Autor:innen. Beteiligte Einrichtung: School of Automation, Chongqing University of Posts and Telecommunications, Chongqing, China. Hauptthemen laut MEDLINE: Bacteria, Hyperspectral Imaging, Image Processing, Computer-Assisted, Wounds and Injuries. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: National Key Research and Development Program of China, Natural Science Foundation of Chongqing, 2025 Chongqing Science and Health Joint Project General Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hyperspectral imaging is an emerging non‐destructive technique for rapid bacterial detection. However, existing methods often inadequately exploit spatial–spectral correlations and lack datasets tailored to clinically relevant scenarios. This work presents a systematic framework integrating a near‐infrared hyperspectral imaging system with a deep learning for accurate classification of common wound bacteria. The multi‐class and multi‐level dataset is first established using a 400–2500 nm halogen‐illuminated system under controlled conditions, comprising 26 056 image patches covering seven bacterial species at five concentration levels, totaling 31 classes. To fully harness spatial and spectral information, the Spatial–Spectral Interactive Selection Network (SSIS‐Net) is proposed. Evaluated on the self‐constructed dataset, SSIS‐Net achieves an overall accuracy of 97.40%, an average accuracy of 97.37%, and a Kappa coefficient of 97.31%, consistently outperforming state‐of‐the‐art methods. These results demonstrate that the proposed system offers a reliable, rapid, and non‐destructive solution for bacterial detection, with strong potential for clinical integration.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BacteriaHyperspectral ImagingImage Processing, Computer-AssistedWounds and InjuriesDeep LearningClassification Algorithms

Stichwörter der Autor:innen

bacteria detectiondeep learninghyperspectral imagingreflectance effect

Autor:innen und Institutionen

  • School of Automation, Chongqing University of Posts and Telecommunications, Chongqing, China.
  • State Key Laboratory of Trauma and Chemical Poisoning, Intensive Care Unit, Daping Hospital, Army Medical University, Chongqing, China.
  • School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, China.

ORCID-Profile: Hailin Cao

Förderung

  • National Key Research and Development Program of China
  • Natural Science Foundation of Chongqing
  • 2025 Chongqing Science and Health Joint Project General Program
  • Chongqing Postgraduate Research and Innovation Project in 2025
  • Chongqing Key Discipline Development Program for Medical Sciences
  • 2025 State Key Laboratory of Trauma and Chemical Poisoning Open Research Project
  • Natural Science Foundation of Chongqing Municipality

Zitieren

APA

Wu, D., Fu, X., Liu, W., Yin, S., Liu, C., Zhao, J., Cao, H., Zhang, L., Wang, Z., & Tang, H. (2026). Multi‐Class and Multi‐Level Classification for Common Wound Bacteria Based on Reflectance Hyperspectral Imaging. Journal of Biophotonics, 19(7). https://doi.org/10.1002/jbio.70318

Vancouver

Wu D, Fu X, Liu W, Yin S, Liu C, Zhao J, et al. Multi‐Class and Multi‐Level Classification for Common Wound Bacteria Based on Reflectance Hyperspectral Imaging. Journal of Biophotonics. 2026;19(7). doi:10.1002/jbio.70318

BibTeX
@article{Wu2026,
  author = {Wu, Decheng and Fu, Xudong and Liu, Wendan and Yin, Sheng and Liu, Chang and Zhao, Jiaqi and Cao, Hailin and Zhang, Lianyang and Wang, Zhen and Tang, Hao},
  title = {Multi‐Class and Multi‐Level Classification for Common Wound Bacteria Based on Reflectance Hyperspectral Imaging},
  journal = {Journal of Biophotonics},
  year = {2026},
  volume = {19},
  number = {7},
  doi = {10.1002/jbio.70318}
}
Kostenlos starten →