EUVIMEDEUVIMED entdecken
Evaluationsstudie

Distinguishing Low‐Grade Chondrosarcoma and Osteochondroma Using Visible–Near Infrared Hyperspectral Spectral Characteristics

Zhihui Gao, Mengqiu Zhang, Nan Liu, Weili Liang, Tiefeng Sun iD

Journal of Biophotonics · 2026

DOI: 10.1002/jbio.202500440 ↗

Kurz gefasst

Evaluationsstudie in der Zeitschrift Journal of Biophotonics, 2026. Verfasst von Zhihui Gao und 4 weiteren Autor:innen. Beteiligte Einrichtung: Shandong Academy of Chinese Medicine, Jinan, China. Hauptthemen laut MEDLINE: Chondrosarcoma, Bone Neoplasms, Osteochondroma, Hyperspectral Imaging. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 14 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shandong Traditional Chinese Medicine Science and Technology Project, Natural Science Foundation of Shandong Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To evaluate visible–near‐infrared hyperspectral imaging (400–1000 nm) combined with a lightweight deep‐learning network for differentiating low‐grade chondrosarcoma (LGC) from osteochondroma (OC).

Methods

Spectra were reflectance‐calibrated, Savitzky–Golay smoothed, and cropped to 420–850 nm. Multi‐level features—single‐band reflectance, key band ratios, and PCA components from biologically informative regions were extracted. We developed ChondroSpecNet , a 1D ‐ CNN coupling multi‐scale convolutions with a residual squeeze‐and‐excitation block for end‐to‐end classification.

Results

ChondroSpecNet yielded AUC 0.92 with 87% accuracy in training, and AUC 0.83 with 86% accuracy on an independent test set. Contribution analysis identified visible‐band troughs—especially 472, 467, and 501 nm—as most discriminative by absolute differences and normalized ratios.

Conclusion

Hyperspectral microscopy plus a compact network enables accurate, efficient LGC–OC discrimination, offering real‐time deployability with robust performance and practical scalability for cartilaginous‐tumor diagnosis in clinical workflows.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ChondrosarcomaBone NeoplasmsOsteochondromaHyperspectral ImagingDeep LearningHumansDiagnosis, DifferentialNeoplasm GradingArea Under CurveConvolutional Neural NetworksSpectroscopy, Near-Infrared

Stichwörter der Autor:innen

cartilaginous tumorshyperspectral imaginglightweight 1D‐CNNlow‐grade chondrosarcomaosteochondromaspectral analysisspectral bands

Autor:innen und Institutionen

  • Shandong Academy of Chinese Medicine, Jinan, China.
  • Weifang Hongjing School of Traditional Chinese Medicine, Jinan, China.
  • Shandong University of Traditional Chinese Medicine, Jinan, China.
  • The Department of Thyroid Surgery, General Surgery, Qilu Hospital of Shandong University, Jinan, China.

ORCID-Profile: Tiefeng Sun

Förderung

  • National Natural Science Foundation of China
  • Shandong Traditional Chinese Medicine Science and Technology Project
  • Natural Science Foundation of Shandong Province

Zitieren

APA

Gao, Z., Zhang, M., Liu, N., Liang, W., & Sun, T. (2026). Distinguishing Low‐Grade Chondrosarcoma and Osteochondroma Using Visible–Near Infrared Hyperspectral Spectral Characteristics. Journal of Biophotonics. https://doi.org/10.1002/jbio.202500440

Vancouver

Gao Z, Zhang M, Liu N, Liang W, Sun T. Distinguishing Low‐Grade Chondrosarcoma and Osteochondroma Using Visible–Near Infrared Hyperspectral Spectral Characteristics. Journal of Biophotonics. 2026. doi:10.1002/jbio.202500440

BibTeX
@article{Gao2026,
  author = {Gao, Zhihui and Zhang, Mengqiu and Liu, Nan and Liang, Weili and Sun, Tiefeng},
  title = {Distinguishing Low‐Grade Chondrosarcoma and Osteochondroma Using Visible–Near Infrared Hyperspectral Spectral Characteristics},
  journal = {Journal of Biophotonics},
  year = {2026},
  doi = {10.1002/jbio.202500440}
}
Kostenlos starten →