In order to study the influence of tympanic membrane lesion and ossicular erosion caused by otitis media on the hearing compensation performance of round-window stimulation, a human ear finite element model including cochlear asymmetric structure was established by computed tomography (CT) technique and reverse engineering technique. The reliability of the model was verified by comparing with the published experimental data. Based on this model, the tympanic membrane lesion and ossicular erosion caused by otitis media were simulated by changing the corresponding tissue structure. Besides, these simulated diseases’ effects on the round-window stimulation were studied by comparing the corresponding basilar-membrane’s displacement at the frequency-dependent characteristic position. The results show that the thickening and the hardening of the tympanic membrane mainly deteriorated the hearing compensation performance of round-window stimulation in the low frequency; tympanic membrane perforation and the minor erosion of ossicle with ossicular chain connected slightly effected the hearing compensation performance of round-window stimulation. Whereas, different from the influence of the aforementioned lesions, the ossicular erosion involving the ossicular chain detachment increased its influence on performance of round-window stimulation at the low frequency. Therefore, the effect of otitis media on the hearing compensation performance of round-window stimulation should be considered comprehensively when designing its actuator, especially the low-frequency deterioration caused by the thickening and the hardening of the tympanic membrane; the actuator’s low-frequency output should be enhanced accordingly to ensure its postoperative hearing compensation performance.
Otitis media is one of the common ear diseases, and its accurate diagnosis can prevent the deterioration of conductive hearing loss and avoid the overuse of antibiotics. At present, the diagnosis of otitis media mainly relies on the doctor's visual inspection based on the images fed back by the otoscope equipment. Due to the quality of otoscope equipment pictures and the doctor's diagnosis experience, this subjective examination has a relatively high rate of misdiagnosis. In response to this problem, this paper proposes the use of faster region convolutional neural networks to analyze clinically collected digital otoscope pictures. First, through image data enhancement and preprocessing, the number of samples in the clinical otoscope dataset was expanded. Then, according to the characteristics of the otoscope picture, the convolutional neural network was selected for feature extraction, and the feature pyramid network was added for multi-scale feature extraction to enhance the detection ability. Finally, a faster region convolutional neural network with anchor size optimization and hyperparameter adjustment was used for identification, and the effectiveness of the method was tested through a randomly selected test set. The results showed that the overall recognition accuracy of otoscope pictures in the test samples reached 91.43%. The above studies show that the proposed method effectively improves the accuracy of otoscope picture classification, and is expected to assist clinical diagnosis.