HSNet: An adaptive fusion network based on laryngoscope–speech multimodal data for laryngeal disease classification
The proposed HSNet effectively integrates hierarchical features from laryngoscope images and voice modalities, enabling accurate classification of six laryngeal diseases. This method holds significant potential for clinical applications.
Authors
- Zhang Xiu (ORCID: https://orcid.org/0000-0003-3817-0227)
- Zhitao Xiao (ORCID: https://orcid.org/0000-0003-2444-9198)
- Yanbei Liu
- Wei Wang (ORCID: https://orcid.org/0000-0001-5268-3374)
- Lei Geng (ORCID: https://orcid.org/0000-0002-5010-2596)
- Mei Wei
Institutions
- Tianjin University (CN)
- Tiangong University (CN)
- Tianjin First Center Hospital (CN)
- Tianjin Medical University (CN)
Publication Details
- Journal
- American Journal of Otolaryngology
- Published
- 2025-10-21
- DOI
- https://doi.org/10.1016/j.amjoto.2025.104731
- Primary Topic
- Voice and Speech Disorders
- Type
- article
- Field-Weighted Citation Impact
- 0.00