Deep Learning‐Assisted Prediction of Air‐Bone Gap Using Tympanic Membrane Perforation Image Features
Otolaryngology–Head and Neck Surgery · 2026
DOI: 10.1002/ohn.70074 ↗At a glance
Journal article in Otolaryngology–Head and Neck Surgery, 2026. Written by Te-Yi Liu and 8 co-authors. Institution: Department of Otolaryngology, Hsinchu Cathay General Hospital, Hsinchu, Taiwan. Major MEDLINE topics: Deep Learning, Tympanic Membrane Perforation, Bone Conduction, Otoscopy. 46 references.
Abstract (original language)
Objective
To evaluate a deep learning (DL)‐based approach for predicting air‐bone gap (ABG) from tympanic membrane (TM) perforation images using automated segmentation and feature extraction, addressing the limitations of audiometry availability in certain populations or settings. Study Design Prospective, cross‐sectional diagnostic study.
Setting
Tertiary academic medical center.
Methods
A total of 1239 otoscopic images were collected between January 2019 and May 2023. Of these, 1014 intact TM images and 150 perforated TM images were used for model development and validation, and 75 intraoperative perforated images were reserved for independent testing. A Mask region‐based convolutional neural network (Mask R‐CNN) model was trained to segment TM and perforation areas. Segmentation performance was evaluated using class pixel accuracy (CPA), intersection over union (IoU), and Dice coefficient. Quantitative features—including perforation ratio and spatial metrics—were extracted to predict ABG using theoretical and quadratic regression models. Model performance was assessed using R ², root mean square error (RMSE), and the proportion of predictions within 10 dB of measured ABG.
Results
TM segmentation achieved CPA, IoU, and Dice scores of 0.794, 0.702, and 0.875; perforation segmentation yielded scores of 0.824, 0.729, and 0.894. ABG prediction showed R ² values of 0.433 (theoretical) and 0.516 (quadratic), with RMSEs of 6.15 and 5.68 dB. Deep learning (DL)‐assisted models achieved accuracy of 83% and 86%, comparable to manual annotation.
Conclusions
DL‐based analysis of TM images enables accurate ABG prediction and may provide a scalable tool to support assessment of conductive hearing loss in environments without access to audiometry.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Otolaryngology, Hsinchu Cathay General Hospital, Hsinchu, Taiwan.
- Department of Biomedical Sciences and Engineering, National Central University, Taoyuan, Taiwan.
- Institute of Population Health Sciences, National Health Research Institutes, 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.
Cite
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 Air‐Bone Gap Using Tympanic Membrane Perforation Image Features. Otolaryngology–Head and Neck Surgery. https://doi.org/10.1002/ohn.70074
Vancouver
Liu TY, Chang HC, Wang PC, Hsu SY, Fang TY, Pham VT, et al. Deep Learning‐Assisted Prediction of Air‐Bone Gap Using Tympanic Membrane Perforation Image Features. Otolaryngology–Head and Neck Surgery. 2026. doi:10.1002/ohn.70074
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 Air‐Bone Gap Using Tympanic Membrane Perforation Image Features},
journal = {Otolaryngology–Head and Neck Surgery},
year = {2026},
doi = {10.1002/ohn.70074}
}
EUVIMED