Search

Background: The indications for transcanal endoscopic ear surgery (TEES) for middle ear cholesteatoma have expanded for cases involving mastoid extension. However, TEES is not indicated for all cases with mastoid extension. In addition, predicting the extent of external auditory canal (EAC) removal needed for cholesteatoma resection is not always easy. The purpose of this study was to use augmented reality (AR) to project the lesion onto an intraoperative endoscopic image to predict EAC removal requirements and select an appropriate surgical approach. Methods: In this study, patients showing mastoid extension were operated on using a navigation system with an AR function (Stryker). Results: The results showed that some cases with lesions slightly extending into the antrum required extensive resection of the EAC, while cases with lesions extending throughout the antrum required smaller resection of the EAC, indicating TEES. Conclusions: By predicting the extent of the needed EAC removal, it is possible to determine whether TEES (a retrograde approach) or canal wall-up mastoidectomy, which preserves as much of the EAC as possible, should be performed. We believe that our findings will contribute to the success of middle ear surgeries and the implementation of robotic surgery in the future. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]