Abstract
Early detection and appropriate medical treatment are of great use for ear disease. However, a new diagnostic strategy is necessary for the absence of experts and relatively low diagnostic accuracy, in which deep learning plays an important role. This paper puts forward a mechanic learning model which uses abundant otoscope image data gained in clinical cases to achieve an automatic diagnosis of ear diseases in real time. A total of 20,542 endoscopic images were employed to train nine common deep convolution neural networks. According to the characteristics of the eardrum and external auditory canal, eight kinds of ear diseases were classified, involving the majority of ear diseases, such as normal, Cholestestoma of the middle ear, Chronic suppurative otitis media, External auditory cana bleeding, Impacted cerumen, Otomycosis external, Secretory otitis media, Tympanic membrane calcification. After we evaluate these optimization schemes, two best performance models are selected to combine the ensemble classifiers with real-time automatic classification. Based on accuracy and training time, we choose a transferring learning model based on DensNet-BC169 and DensNet-BC1615, getting a result that each model has obvious improvement by using these two ensemble classifiers, and has an average accuracy of 95.59%. Considering the dependence of classifier performance on data size in transfer learning, we evaluate the high accuracy of the current model that can be attributed to large databases. Current studies are unparalleled regarding disease diversity and diagnostic precision. The real-time classifier trains the data under different acquisition conditions, which is suitable for real cases. According to this study, in the clinical case, the deep learning model is of great use in the early detection and remedy of ear diseases.
Highlights
Detection and appropriate medical treatment are of great use for ear disease
In order to test the stability of the model, the 12 models which we have been trained were evaluated by 10 percent of the sample which collected randomly from the training set
One-way ANOVA indicated that the DensNet-BC1615 and DensNet-BC169 increased more significantly than other models except for the Inception-ResNet-V2
Summary
Detection and appropriate medical treatment are of great use for ear disease. a new diagnostic strategy is necessary for the absence of experts and relatively low diagnostic accuracy, in which deep learning plays an important role. According to the characteristics of the eardrum and external auditory canal, eight kinds of ear diseases were classified, involving the majority of ear diseases, such as normal, Cholestestoma of the middle ear, Chronic suppurative otitis media, External auditory cana bleeding, Impacted cerumen, Otomycosis external, Secretory otitis media, Tympanic membrane calcification After we evaluate these optimization schemes, two best performance models are selected to combine the ensemble classifiers with real-time automatic classification. Research of Pichichero, Poole[3], for example, found that the average accuracy of otitis media diagnosed by 514 pediatricians was only 50% Such low diagnostic accuracy hinted that, without the assistance of supplementary resources, testing the diagnosis of ear disease will be difficult, even for experts. What’s more, deep learning has been widely applied in ear and hearing disease classification[8,9,10] In these deep learning applications, deep convolutional neural networks (CNNs)[4] is playing a very important role in image recognition or classification. Based on the assessment results, two best models among 12 models were chosen to build an ensemble classifier which can design and accomplish a real-time automatic identification of ear diseases system
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
