Cholesteatoma is a progressive middle ear disease that can only be treated surgically but with a high recurrence rate. Depending on the extent of the disease, a surgical approach, such as microsurgery with a retroarticular incision or transcanal endoscopic surgery, is performed. However, the current examination cannot sufficiently predict the progression before surgery, and changes in approach may be made during the surgery. Large amounts of data are typically required to train deep neural network models; however, the prevalence of cholesteatomas is low (1-in-25, 000). Developing analysis methods that improve the accuracy with such a small number of samples is an important issue for medical artificial intelligence (AI) research. This paper presents an AI-based system to automatically detect mastoid extensions using CT. This retrospective study included 164 patients (80 with mastoid extension and 84 without mastoid extension) who underwent surgery. This study adopted a relatively lightweight neural network model called MobileNetV2 to learn and predict the CT images of 164 patients. The training was performed with eight divided groups for cross-validation and was performed 24 times with each of the eight groups to verify accuracy fluctuations caused by randomly augmented learning. An evaluation was performed by each of the 24 single-trained models, and 24 sets of ensemble predictions with 23 models for 100% original size images and 400% zoomed images. Fifteen otolaryngologists diagnosed the images and compared the results. The average accuracy of predicting 400% zoomed images using ensemble prediction model was 81.14% (sensitivity = 84.95%, specificity = 77.33%). The average accuracy of the otolaryngologists was 73.41% (sensitivity, 83.17%; specificity, 64.13%), which was not affected by their clinical experiences. Noteworthily, despite the small number of cases, we were able to create a highly accurate AI. These findings represent an important first step in the automatic diagnosis of the cholesteatoma extension.

Objective:To analyze the time trends of recidivism of acquired cholesteatoma using the Kaplan-Meier method. Study Design: We conducted a retrospective, observational study of 256 patients having their first cholesteatoma surgery. The cumulative recidivism-free rate was calculated using Kaplan-Meier survival analysis related to the follow-up period, pathophysiology, the extent of the disease, and recidivism pathologies. Results: Pars flacida cholesteatoma with tympanic cavity progression had a high likelihood of recurrence disease. Pars tensa cholesteatoma led to more recurrence of the disease than the residual disease. In both pars flacida and pars tensa cholesteatoma, the incidence of disease recurrence increased even 3 years after surgery. On the contrary, the incidence of residual disease peaked within 3 years after surgery, and thereafter, the incidence of residual disease tended to be small. In particular, pars flacida cholesteatoma extending into the mastoid cavity or tympanic cavity tended to recur up to 5 years postoperatively. Conclusions: We calculated the cumulative recidivism-free rates of 256 patients with cholesteatoma using Kaplan-Meier survival analysis. These results can lead to better estimates of the length of the follow-up period. Level of Evidence: Level IV evidence from case-control studies.

No abstract

No abstract

Human papillomavirus (HPV) is a common sexually transmitted infection worldwide, which spreads via contact with infected genital, anal, and oral/pharyngeal areas (oral sex) owing to diverse manners of sexual intercourse. In this study, we devised an oral HPV detection method using mouthwash waste fluids that causes less psychological resistance to visiting the outpatient otolaryngology departments. We successfully detected only the specific unique reverse sequencing probe (using pyro-genotyping) and identified the nine genotypes of HPV targeted for vaccination by pyrosequencing the mouthwash waste fluids of non-head and neck cancer patient volunteers (n = 52). A relatively large number (11/52) of mouthwash waste fluids tested positive for HPV (21.2%; genotype 6, n = 1; 11, n = 1; 16, n = 1; and 18, n = 8). These results surpassed the sensitivity observed testing the same specimens using the conventional method (1/52, 1.9%). Our method (pyro-genotyping) was developed using nine HPV genotypes targeted for vaccination and the results were highly sensitive compared to those of the conventional method. This less expensive, high-throughput, and simple method can be used for detecting oral HPV infection with fewer socio-psychological barriers.