EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Deep Learning-Assisted Prediction of Hearing Outcomes After Anatomically Successful Type I Tympanoplasty

Te-Yi Liu iD, Hsiang-Chih Chang iD, Pa-Chun Wang, Su-Yi Hsu, Te-Yung Fang, Van-Truong Pham, Thi-Thao Tran iD, Chen Lin, Men-Tzung Lo

Journal of Otolaryngology - Head & Neck Surgery · 2026-07 · 55

DOI: 10.1177/19160216261450491 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Otolaryngology - Head & Neck Surgery, online erschienen am 07.07.2026. Verfasst von Te-Yi Liu und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Otolaryngology, Hsinchu Cathay General Hospital, Hsinchu, Taiwan. Hauptthemen laut MEDLINE: Tympanoplasty, Tympanic Membrane Perforation, Deep Learning, Hearing. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Importance: Type I tympanoplasty restores hearing in patients with simple tympanic membrane (TM) perforations, but reliable tools to predict postoperative outcomes remain limited.

Objective

To develop and evaluate a deep learning-assisted model integrating automated TM image features and clinical data to predict postoperative air-bone gap (ABG) closure and residual ABG.

Design

Diagnostic and prognostic model development and validation study.

Setting

A tertiary referral medical center in northern Taiwan.

Participants

A total of 1285 otoendoscopic images were collected, of which 1014 intact and 150 perforated TMs were used to train the mask region-based convolutional neural network (Mask R-CNN) segmentation model. Prognostic analysis included 121 patients with simple perforations and anatomically successful type I tympanoplasty (complete TM closure), with 83 preoperative images for training and 38 for independent internal testing. Demographic, clinical, and audiometric data were recorded. Intervention or Exposures: Automated image features extracted by Mask R-CNN, combined with clinical and audiometric variables, were used to develop prognostic models. Main Outcome Measures: Segmentation performance was evaluated using class pixel accuracy (CPA). Prognostic model performance was assessed using the coefficient of determination (R 2 ), root mean square error (RMSE), mean absolute error, and predictive accuracy, defined as a predicted ABG within 10 and 5 dB of the measured value.

Results

The segmentation model achieved a CPA of 0.884 for TM detection and 0.901 for perforation detection. The prognostic models yielded R 2 values of 0.418 for ABG closure and 0.363 for residual ABG, with corresponding RMSEs of 4.39 and 4.36 dB. Prediction accuracy reached 97% within 10 dB and 74% within 5 dB, significantly outperforming baseline mean-value prediction (P < .05).

Conclusions

Deep learning-assisted analysis of TM images showed modest predictive ability for hearing outcomes after anatomically successful type I tympanoplasty. Relevance: This image-based approach may modestly assist preoperative counseling in otologic practice.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

TympanoplastyTympanic Membrane PerforationDeep LearningHearingHumansFemalePrognosisMalePredictive Learning ModelsAdultConvolutional Neural NetworksTreatment OutcomeOtoscopyAuditory Acuity

Stichwörter der Autor:innen

air-bone gapconductive hearing lossdecision support techniquesdeep learninghearing outcomesimage segmentationmachine learningprognosistympanic membrane perforationtympanoplasty

Autor:innen und Institutionen

  • Department of Otolaryngology, Hsinchu Cathay General Hospital, Hsinchu, Taiwan.
  • Department of Biomedical Sciences and Engineering, National Central University, Taoyuan City, Taiwan.
  • Institute of Population Health Sciences, National Health Research Institutes, Zhunan Township, Miaoli County, Taiwan.
  • Department of Otolaryngology, Cathay General Hospital, Taipei, Taiwan.
  • School of Medicine, Fu-Jen Catholic University, New Taipei City, Taiwan.
  • School of Medicine, National Tsing Hua University, Hsinchu, Taiwan.

ORCID-Profile: Te-Yi Liu, Hsiang-Chih Chang, Thi-Thao Tran

Zitieren

APA

Liu, T. Y., Chang, H. C., Wang, P. C., Hsu, S. Y., Fang, T. Y., Pham, V. T., Tran, T. T., Lin, C., & Lo, M. T. (2026). Deep Learning-Assisted Prediction of Hearing Outcomes After Anatomically Successful Type I Tympanoplasty. Journal of Otolaryngology - Head & Neck Surgery, 55. https://doi.org/10.1177/19160216261450491

Vancouver

Liu TY, Chang HC, Wang PC, Hsu SY, Fang TY, Pham VT, et al. Deep Learning-Assisted Prediction of Hearing Outcomes After Anatomically Successful Type I Tympanoplasty. Journal of Otolaryngology - Head & Neck Surgery. 2026;55. doi:10.1177/19160216261450491

BibTeX
@article{Liu2026,
  author = {Liu, Te-Yi and Chang, Hsiang-Chih and Wang, Pa-Chun and Hsu, Su-Yi and Fang, Te-Yung and Pham, Van-Truong and Tran, Thi-Thao and Lin, Chen and Lo, Men-Tzung},
  title = {Deep Learning-Assisted Prediction of Hearing Outcomes After Anatomically Successful Type I Tympanoplasty},
  journal = {Journal of Otolaryngology - Head & Neck Surgery},
  year = {2026},
  volume = {55},
  doi = {10.1177/19160216261450491}
}
Kostenlos starten →