No abstract

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.

No abstract

Background Tympanoplasty using the interlay technique has rarely been reported in transcanal endoscopic ear surgery, unlike the underlay technique. This is because many surgeons find it challenging to detach the epithelial layer of the tympanic membrane using only one hand. However, the epithelial layer can be easily detached from the inferior part of the tympanic membrane. Another key point is to actively improve anteroinferior visibility even if the overhang is slight because most perforations and postoperative reperforations are found in the anteroinferior quadrant of the tympanic membrane. We report the application of the interlay technique in endoscopic tympanoplasty type I for tympanic perforations. Methods We retrospectively reviewed the medical records of 51 patients who had undergone tympanoplasty using the interlay technique without ossiculoplasty between 2017 and 2020. We then compared the data with those of patients who underwent microscopic surgery (MS) using the underlay technique between 1998 and 2009 (n = 104). No other technique was used in each group during this period. Repair of tympanic membrane perforation and hearing outcomes were assessed for > 1 year postoperatively. Results The perforation sites were limited to the anterior, posterior, and anterior–posterior quadrants in 23, 1, and 27 ears, respectively. Perforations were closed in 50 of the 51 ears (98.0%), and the postoperative hearing was good (average air-bone [A-B] gap was 6.8 ± 5.8 dB). The surgical success rate for the repair of tympanic membrane perforation was not significantly different from the MS group (93.3%, P = 0.15). The average postoperative average A-B gap in the group that underwent the interlay technique was significantly different from that in the MS group (10.1 ± 6.6 dB, P < 0.01). Conclusion The interlay technique should be considered as one of the treatment methods in endoscopic surgery for tympanic perforations. Further study of the postoperative outcomes of this procedure should be conducted to establish the optimal surgical procedure for tympanic perforations. Trial registration: This study was retrospectively approved by the Institutional Review Board of the Jikei University, Tokyo, Japan (approval number: 32-205 10286). Video abstract