loading page

A deep learning approach to diagnose atelectasis and attic retraction pocket with otoscopic images
  • +15
  • Junbo Zeng,
  • wenting Deng,
  • Jingang Yu,
  • Lichao Xiao,
  • Suijun Chen,
  • Xueyuan Zhang,
  • Linqi Zeng,
  • Donglang Chen,
  • Peng Li,
  • Yubin Chen,
  • Hongzheng Zhang,
  • Fan Shu,
  • Jinliang Gao,
  • Minjian Wu,
  • Yuejia Su,
  • Yuanqing Li,
  • Yuexin Cai,
  • Yiqing Zheng
Junbo Zeng
Sun Yat-sen Memorial Hospital, Sun Yat-sen University
Author Profile
wenting Deng
Sun Yat-Sen University 2nd Affiliated Hospital
Author Profile
Jingang Yu
South China University of Technology
Author Profile
Lichao Xiao
South China University of Technology
Author Profile
Suijun Chen
Sun Yat-sen Memorial Hospital, Sun Yat-sen University
Author Profile
Xueyuan Zhang
Sun Yat-sen Memorial Hospital of Sun Yat-sen University
Author Profile
Linqi Zeng
4. Zhongshan School of Medicine, Sun Yat-sen University
Author Profile
Donglang Chen
4. Zhongshan School of Medicine, Sun Yat-sen University
Author Profile
Peng Li
the Third Affiliated Hospital of Sun Yat-Sen University
Author Profile
Yubin Chen
the Third Affiliated Hospital of Sun Yat-Sen University
Author Profile
Hongzheng Zhang
Southern Medical University
Author Profile
Fan Shu
Nanfang Hospital, South Medical University
Author Profile
Jinliang Gao
Shenzhen Baoan Women's and Children's Hospital
Author Profile
Minjian Wu
Sun Yat-sen Memorial Hospital, Sun Yat-sen University
Author Profile
Yuejia Su
Sun Yat-Sen Memorial Hospital
Author Profile
Yuanqing Li
South China University of Technology
Author Profile
Yuexin Cai
Sun Yat-sen Memorial Hospital, Sun Yat-sen University
Author Profile
Yiqing Zheng
Sun yatsen university
Author Profile

Abstract

Background: Atelectasis and attic retraction pocket are two common tympanic membranes changes. However, general practitioners, pediatricians and otolaryngologists showed low diagnostic accuracy for these ear diseases. Therefore, there is a need to develop a deep learning model to detect atelectasis and attic retraction pocket automatically. Method: 6393 OME otoscopic images from 3 centers were used to develop and validate a deep learning model to detect atelectasis and attic retraction pocket. 3-fold random cross validation was adopted to divided dataset into training set and validation set. A team of otologists were assigned to diagnose and label. Receiver operating characteristic (ROC) curve, 3-fold average classification accuracy, sensitivity and specificity were used to assess the performance of deep learning model. Class Activation Mapping (CAM) was applied to show the discriminative region in the otoscopic images. Result: Among all the otoscopic images, 3564 (55.74%) images were identified with attic retraction pocket, and 2460 (38.48%) images were identified with atelectasis. The automatically diagnostic model of attic retraction pocket and atelectasis achieved 3-fold cross validation accuracy of 89% and 79%, AUC of 0.89 and 0.87, sensitivity of 0.93 and 0.71, and specificity of 0.62 and 0.84 respectively. Bigger and deeper atelectasis and attic retraction pocket showed more weight with red color in the heat map of CAM. Conclusion: Deep learning algorithm could be used to identify atelectasis and attic retraction pocket, which could be used as a tool to assist general practitioners, pediatricians and otolaryngologists. Key words: deep learning, otoscopic images, atelectasis, attic retraction pocket