文献速递耳科与耳神经

深度学习辅助鼓膜穿孔图像特征预测气骨导差

Deep Learning-Assisted Prediction of Air-Bone Gap Using Tympanic Membrane Perforation Image Features.
PubMed 文献 · Otolaryngol Head Neck Surg · 2025-11-18

本研究为前瞻性横断面诊断研究,纳入1239张耳内镜图像,训练Mask R-CNN分割鼓膜与穿孔区域并提取特征预测气骨导差(ABG)。分割模型表现良好,ABG预测R²为0.433(理论模型)和0.516(二次模型),RMSE为6.15和5.68 dB,DL辅助模型准确率83%和86%,与人工标注相当。结论提示基于鼓膜图像的DL分析可准确预测ABG,有望在无法进行听力检查的环境中辅助评估传导性听力损失。

要点

  • Mask R-CNN可自动分割鼓膜与穿孔区域,分割Dice系数分别为0.875和0.894。
  • 基于穿孔特征的二次回归模型预测ABG的R²为0.516,RMSE为5.68 dB。
  • DL辅助模型预测ABG准确率达83%和86%,与人工标注相当。

核心结论

  • 基于鼓膜穿孔图像的深度学习分析可准确预测气骨导差,有望作为无法进行听力检查时的可扩展评估工具。

研究设计与样本

  • 前瞻性横断面诊断研究,在三级学术医疗中心收集2019年1月至2023年5月的1239张耳内镜图像。
  • 1014张完整鼓膜图像和150张穿孔鼓膜图像用于模型开发与验证,75张术中穿孔图像用于独立测试。

主要发现

  • 鼓膜分割的类别像素准确率(CPA)、交并比(IoU)和Dice系数分别为0.794、0.702和0.875。
  • 穿孔分割的CPA、IoU和Dice系数分别为0.824、0.729和0.894。
  • ABG预测的理论模型和二次模型R²分别为0.433和0.516,RMSE分别为6.15和5.68 dB。
  • DL辅助模型的准确率分别为83%和86%,与人工标注相当。

关键数值与推荐

  • ABG预测性能以R²、RMSE和预测值在实测ABG 10 dB以内的比例进行评估。

临床怎么用

  • 在缺乏听力检查设备的场景中,可利用鼓膜穿孔图像辅助评估传导性听力损失程度。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

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 R², 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 R² 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.

来源:Otolaryngol Head Neck Surg,查看原文。版权归原作者所有。

引用

  1. Liu TY, Chang HC, Wang PC, et al. Deep Learning-Assisted Prediction of Air-Bone Gap Using Tympanic Membrane Perforation Image Features. Otolaryngol Head Neck Surg. 2025. PMID: 41252627. doi:10.1002/ohn.70074

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。