In order to study the effect of middle ear malformations on energy absorbance, we constructed a mechanical model that can simulate the energy absorbance of the human ear based on our previous human ear finite element model. The validation of this model was confirmed by two sets of experimental data. Based on this model, three common types of middle ear malformations, i.e. incudostapedial joint defect, incus fixation and malleus fixation, and stapes fixation, were simulated by changing the structure and material properties of the corresponding tissue. Then, the effect of these three common types of middle ear malformations on energy absorbance was investigated by comparing the corresponding energy absorbance. The results showed that the incudostapedial joint defect significantly increased the energy absorbance near 1 000 Hz. The incus fixation and malleus fixation dramatically reduced the energy absorbance in the low frequency, which made the energy absorbance less than 10% at frequencies lower than 1 000 Hz. At the same time, the peak of energy absorbance shifted to the higher frequency. These two kinds of middle ear malformations had obvious characteristics in the wideband acoustic immittance test. In contrast, the stapes fixation only reduced the energy absorbance in the low frequency and increased energy absorbance in the middle frequency slightly, which had no obvious characteristic in the wideband acoustic immittance test. These results provide a theoretical reference for the wideband acoustic immittance diagnosis of middle ear malformations in clinic.
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.