EUVIMEDEUVIMED entdecken
Crossref

E2E-OCT: end-to-end joint learning model using optical coherence tomography images for vocal cord leukoplakia diagnosis

Yu Ban, Yipeng Zhang, Xueying Li, Weili Hong, Shuhua Yue, Xun Chen

Optics Letters · 15.06.2026 · 51 (12) · 3481

DOI: 10.1364/ol.600976 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Optics Letters, online erschienen am 15.06.2026. Verfasst von Yu Ban und 5 weiteren Autor:innen. Hauptthemen laut MEDLINE: Tomography, Optical Coherence, Leukoplakia, Vocal Cords, Machine Learning. Die Arbeit nennt 8 Literaturangaben. Gefördert von: Fundamental Research Funds for the Central Universities, National Natural Science Foundation of China, Beijing Natural Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In our previous study, a home-built handheld OCT system was used to collect OCT images in vocal cord leukoplakia. First, 383 valid OCT images were collected from 12 patients with leukoplakia (including low-risk, high-risk, and malignant types). The best overall accuracy and recall were 92.59% and 93.25% for low-risk, high-risk, and malignant classification, by random forest (RF) model using 5-fold validation. However, low-risk dysplasia with a sensitivity of 87.72% could not meet clinical requirements. Here, we proposed an end-to-end joint learning model using optical coherence tomography (E2E-OCT) images for vocal cord leukoplakia diagnosis. The overall accuracy and recall improved by 5.58% and 4.87%, and especially the sensitivity for low-risk dysplasia improved from 87.72% to 97.48%. Notably, under leave-one-patient-out (LOPO) cross-validation, the model also maintained 96.64% sensitivity for low-risk dysplasia. The ablation experiments and explanation experiments demonstrated the robustness of our model.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tomography, Optical CoherenceLeukoplakiaVocal CordsMachine LearningImage Processing, Computer-AssistedHumans

Förderung

  • Fundamental Research Funds for the Central Universities
  • National Natural Science Foundation of China
  • Beijing Natural Science Foundation

Zitieren

APA

Ban, Y., Zhang, Y., Li, X., Hong, W., Yue, S., & Chen, X. (2026). E2E-OCT: end-to-end joint learning model using optical coherence tomography images for vocal cord leukoplakia diagnosis. Optics Letters, 51(12), 3481. https://doi.org/10.1364/ol.600976

Vancouver

Ban Y, Zhang Y, Li X, Hong W, Yue S, Chen X. E2E-OCT: end-to-end joint learning model using optical coherence tomography images for vocal cord leukoplakia diagnosis. Optics Letters. 2026;51(12):3481. doi:10.1364/ol.600976

BibTeX
@article{Ban2026,
  author = {Ban, Yu and Zhang, Yipeng and Li, Xueying and Hong, Weili and Yue, Shuhua and Chen, Xun},
  title = {E2E-OCT: end-to-end joint learning model using optical coherence tomography images for vocal cord leukoplakia diagnosis},
  journal = {Optics Letters},
  year = {2026},
  volume = {51},
  number = {12},
  pages = {3481},
  doi = {10.1364/ol.600976}
}
Kostenlos starten →