EUVIMEDScopri EUVIMED
Multizentrische Studie

A Clinically Inspired Deep Learning Framework for Laryngeal Cancer Detection and Malignancy Transformation Risk Assessment

Yifan Kang iD, Binbin Hu, Kai Xu, Lanjun Cai, Wei Li, Suguang Sun, Yinhao Liu, Xiang Lu

Otolaryngology–Head and Neck Surgery · 2026

DOI: 10.1002/ohn.70075 ↗

At a glance

Multizentrische Studie in Otolaryngology–Head and Neck Surgery, 2026. Written by Yifan Kang and 7 co-authors. Institution: Department of Otolaryngology Head and Neck Surgery, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 43…. Major MEDLINE topics: Deep Learning, Laryngeal Neoplasms, Laryngoscopy, Cell Transformation, Neoplastic. 35 references.

AbstractSubjectsDati bibliograficiCiteRelated studies

Abstract (original language)

Objective

Laryngeal cancer (LCA) is a prevalent head and neck malignancy. However, laryngoscopic image interpretation remains experience‐dependent, resulting in diagnostic variability, particularly in resource‐limited settings. This study aimed to develop a deep learning model to enhance lesion detection, guide biopsies, and streamline diagnostic processes. Study Design Retrospective study of a classification network.

Setting

Five medical centers in China.

Methods

A dataset comprising 16,587 laryngoscopic images from 2585 patients representing 10 distinct laryngeal lesions was established. First, TransCL was developed and validated on multiple independent test sets in comparison with existing models. Second, the model was evaluated on unseen lesion types to assess its generalizability. Third, its ability to predict malignant transformation in benign lesions was assessed against expert annotations. Finally, TransCL predictions were compared with diagnoses made by laryngologists.

Results

TransCL demonstrated outstanding performance across all test sets, achieving an area under the curve of 0.978 (0.974‐0.982), accuracy of 0.942 (0.938‐0.945), F1‐score of 0.961 (0.959‐0.963), and Matthews Correlation Coefficient of 0.843 (0.831‐0.855) in the internal validation. Performance remained robust in external validations, outperforming existing models. The model demonstrated strong generalization to unseen lesion types and reliably predicted malignant transformation risk in benign lesions. Compared with human experts, TransCL outperformed junior laryngologists and several senior laryngologists, achieving performance achieving performance comparable to that of top senior laryngologists.

Conclusions

TransCL demonstrated high robustness, accuracy, and generalizability, with diagnostic performance comparable to that of experienced clinicians in LCA detection and lesion risk assessment, suggesting its potential for clinical applications.

Subjects

MeSH terms (MEDLINE)

Deep LearningLaryngeal NeoplasmsLaryngoscopyCell Transformation, NeoplasticHumansRetrospective StudiesRisk AssessmentMaleFemaleMiddle AgedChina

Author keywords

Swin Transformerclinical‐grade AIcontrastive learninglaryngeal cancerweakly supervised learning

Authors and institutions

  • Department of Otolaryngology Head and Neck Surgery, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430030, China.
  • Engineering and Technology Institute Groningen, Faculty of Science and Engineering, University of Groningen, Groningen, 9747AG, The Netherlands.
  • Department of Otolaryngology Head and Neck Surgery, Wuhan Asia General Hospital, Wuhan, 430056, China.
  • Department of Otolaryngology Head and Neck Surgery, Wuhan Sixth Hospital, Wuhan, 430015, China.

ORCID profiles: Yifan Kang

Cite

APA

Kang, Y., Hu, B., Xu, K., Cai, L., Li, W., Sun, S., Liu, Y., & Lu, X. (2026). A Clinically Inspired Deep Learning Framework for Laryngeal Cancer Detection and Malignancy Transformation Risk Assessment. Otolaryngology–Head and Neck Surgery. https://doi.org/10.1002/ohn.70075

Vancouver

Kang Y, Hu B, Xu K, Cai L, Li W, Sun S, et al. A Clinically Inspired Deep Learning Framework for Laryngeal Cancer Detection and Malignancy Transformation Risk Assessment. Otolaryngology–Head and Neck Surgery. 2026. doi:10.1002/ohn.70075

BibTeX
@article{Kang2026,
  author = {Kang, Yifan and Hu, Binbin and Xu, Kai and Cai, Lanjun and Li, Wei and Sun, Suguang and Liu, Yinhao and Lu, Xiang},
  title = {A Clinically Inspired Deep Learning Framework for Laryngeal Cancer Detection and Malignancy Transformation Risk Assessment},
  journal = {Otolaryngology–Head and Neck Surgery},
  year = {2026},
  doi = {10.1002/ohn.70075}
}
Start for free →