Multi‐Classification of Vocal Cord Masses via Local‐Higher Order Graph Neural Network on Voice Data
The Laryngoscope · 2026-12 · 136 (12) · 5474-5481
DOI: 10.1002/lary.70800 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Laryngoscope, online erschienen am 10.08.2026. Verfasst von Tuanjie Wang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Otorhinolaryngology, Head and Neck Surgery, The Second Hospital of Jilin University, Changchun, China. Hauptthemen laut MEDLINE: Vocal Cords, Graph Neural Networks, Laryngeal Neoplasms, Polyps. Die Arbeit nennt 40 Literaturangaben. Gefördert von: Science and Technology Development Plan Project of Jilin Province.
Abstract (Originalsprache)
Objective
To develop an intelligent diagnostic model based on a Local‐Higher Order Graph Neural Network (LHGNN) to achieve noninvasive auxiliary multi‐class pathological classification of vocal fold tumors by analyzing Mel‐spectrograms of voice data.
Methods
Patients with pathologically confirmed vocal fold polyps ( n = 1272), premalignant lesions ( n = 180), and malignant tumors ( n = 197) were retrospectively identified. Patients were divided into training and validation sets in a ratio of 8:2. The patient's vowel and continuous sentence audio were collected, and the audio was segmented and converted into Mel‐spectrograms. The data was enhanced by random occlusion, adding noise and time shifting. We used a convolutional backbone network‐based LHGNN architecture, whose core consists of multiple cascaded LHG modules. The model was evaluated using metrics including accuracy, recall, F 1‐score, and the area under the curve (AUC) value.
Results
The final dataset comprised 4745 audio samples after balanced sampling (1603 vocal fold polyps, 1598 premalignant lesions, 1544 vocal fold carcinomas). The validation set achieved optimal performance after 461 training epochs: overall accuracy of 92.94%, F 1‐score of 0.9289, recall of 0.9281, and AUC of 0.9877. The multi‐class confusion matrix demonstrated identification accuracies of 91.35% for vocal fold polyps, 90.99% for premalignant lesions, and 94.05% for malignant tumors.
Conclusion
This study successfully validated the high efficacy of the LHGNN model in the multi‐class classification of vocal fold tumors. Its excellent performance highlights the significant potential of deep learning in vocal pathological analysis. The model provides a new tool for the noninvasive preliminary screening of vocal fold tumors. Level of Evidence 3.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Otorhinolaryngology, Head and Neck Surgery, The Second Hospital of Jilin University, Changchun, China.
ORCID-Profile: Tuanjie Wang, Shuang Li
Förderung
- Science and Technology Development Plan Project of Jilin Province
Zitieren
APA
Wang, T., Zhao, X., Li, S., Guo, H., Zheng, L., & Yu, D. (2026). Multi‐Classification of Vocal Cord Masses via Local‐Higher Order Graph Neural Network on Voice Data. The Laryngoscope, 136(12), 5474-5481. https://doi.org/10.1002/lary.70800
Vancouver
Wang T, Zhao X, Li S, Guo H, Zheng L, Yu D. Multi‐Classification of Vocal Cord Masses via Local‐Higher Order Graph Neural Network on Voice Data. The Laryngoscope. 2026;136(12):5474-5481. doi:10.1002/lary.70800
BibTeX
@article{Wang2026,
author = {Wang, Tuanjie and Zhao, Xue and Li, Shuang and Guo, Haixian and Zheng, Linlin and Yu, Dan},
title = {Multi‐Classification of Vocal Cord Masses via Local‐Higher Order Graph Neural Network on Voice Data},
journal = {The Laryngoscope},
year = {2026},
volume = {136},
number = {12},
pages = {5474--5481},
doi = {10.1002/lary.70800}
}
EUVIMED