Deep Learning Techniques for Ear Diseases Based on Segmentation of the Normal Tympanic Membrane

다국어 초록 (Multilingual Abstract)

Objectives. Otitis media is a common infection worldwide. Owing to the limited number of ear specialists and rapid devel-opment of telemedicine, several trials have been conducted to develop novel diagnostic strategies to improve the di-agnostic accuracy and screening of patients with otologic diseases based on abnormal otoscopic findings. Althoughthese strategies have demonstrated high diagnostic accuracy for the tympanic membrane (TM), the insufficient ex-plainability of these techniques limits their deployment in clinical practice.
Methods. We used a deep convolutional neural network (CNN) model based on the segmentation of a normal TM into fivesubstructures (malleus, umbo, cone of light, pars flaccida, and annulus) to identify abnormalities in otoscopic ear im-ages. The mask R-CNN algorithm learned the labeled images. Subsequently, we evaluated the diagnostic performanceof combinations of the five substructures using a three-layer fully connected neural network to determine whetherear disease was present.
Results. We obtained the receiver operating characteristic (ROC) curve of the optimal conditions for the presence or ab-sence of eardrum diseases according to each substructure separately or combinations of substructures. The highestarea under the curve (0.911) was found for a combination of the malleus, cone of light, and umbo, compared withthe corresponding areas under the curve of 0.737–0.873 for each substructure. Thus, an algorithm using these fiveimportant normal anatomical structures could prove to be explainable and effective in screening abnormal TMs.
Conclusion. This automated algorithm can improve diagnostic accuracy by discriminating between normal and abnormalTMs and can facilitate appropriate and timely referral consultations to improve patients’ quality of life in the contextof primary care.

참고문헌 (Reference)

1 Rosenfeld RM, "clinical practice guideline : otitis media with effusion(update)" 154 (154): S1-41, 2016

2 Anantharaman R, "Utilizing Mask R-CNN for detection and segmentation of oral diseases" 2197-2204, 2018

3 Demant MN, "Smartphone otoscopy by non-specialist health workers in rural Greenland : a cross-sectional study" 126 : 109628-, 2019

4 Myburgh HC, "Otitis media diagnosis for developing countries using tympanic membrane image-analysis" 5 : 156-160, 2016

5 Peng J, "Medical image segmentation with limited supervision : a review of deep network models" 9 : 36827-36851, 2021

6 He K, "Mask R-CNN" 2980-2988, 2017

7 Zhao C, "Lung nodule detection via 3D U-Net and contextual convolutional neural network" 356-361, 2018

8 Mulay S, "Liver segmentation from multimodal images using HED-Mask R-CNN" 68-75, 2019

9 Russell BC, "LabelMe : a database and web-based tool for image annotation" 77 (77): 157-173, 2008

10 Singh A, "Explainable deep learning models in medical image analysis" 6 (6): 52-, 2020

11 Zeng X, "Efficient and accurate identification of ear diseases using an ensemble deep learning model" 11 (11): 10839-, 2021

12 Lee SH, "Effects of reactive oxygen species generation induced by Wonju City particulate matter on mitochondrial dysfunction in human middle ear cell" 28 (28): 49244-49257, 2021

13 Aggarwal R, "Diagnostic accuracy of deep learning in medical imaging : a systematic review and meta-analysis" 4 (4): 65-, 2021

14 Sanna M, "Color atlas of endo-otoscopy" 2017

15 Prajapati SA, "Classification of dental diseases using CNN and transfer learning" 70-74, 2017

16 Liu Y, "Automatic segmentation of cervical nuclei based on deep learning and a conditional random field" 6 : 53709-53721, 2018

17 Wang G, "Automatic brain tumor segmentation using cascaded anisotropic convolutional neural networks" Springer 10670-, 2017

18 Cha D, "Automated diagnosis of ear disease using ensemble deep learning with a big otoendoscopy image database" 45 : 606-614, 2019

19 Pichichero ME, "Assessing diagnostic accuracy and tympanocentesis skills in the management of otitis media" 155 (155): 1137-1142, 2001

20 Shu JH, "An improved mask R-CNN model for multiorgan segmentation" 2020 : 8351725-, 2020

21 Liu X, "A review of deep-learning-based medical image segmentation methods" 13 (13): 1224-, 2021

22 Joe H, "A newly designed tympanostomy stent with TiO2 coating to reduce Pseudomonas aeruginosa biofilm formation" 33 (33): 599-605, 2018