Cho YS, et al. J Korean Med Sci. 2021 Dec;37(2):e11. https://doi.org/10.3346/jkms.2022.37.e11

Background: Recently, the analysis of endolymphatic hydropses (EHs) via inner ear magnetic resonance imaging (MRI) for patients with Ménière disease has been attempted in various studies. In addition, artificial intelligence has rapidly been incorporated into the medical field. In our previous studies, an automated algorithm for EH analysis was developed by using a convolutional neural network. However, several limitations existed, and further studies were conducted to compensate for these limitations. Objective: The aim of this study is to develop a fully automated analytic system for measuring EH ratios that enhances EH analysis accuracy and clinical usability when studying Ménière disease via MRI. Methods: We proposed the 3into3Inception and 3intoUNet networks. Their network architectures were based on those of the Inception-v3 and U-Net networks, respectively. The developed networks were trained for inner ear segmentation by using the magnetic resonance images of 124 people and were embedded in a new, automated EH analysis system—inner-ear hydrops estimation via artificial intelligence (INHEARIT)-version 2 (INHEARIT-v2). After fivefold cross-validation, an additional test was performed by using 60 new, unseen magnetic resonance images to evaluate the performance of our system. The INHEARIT-v2 system has a new function that automatically selects representative images from a full MRI stack. Results: The average segmentation performance of the fivefold cross-validation was measured via the intersection of union method, resulting in performance values of 0.743 (SD 0.030) for the 3into3Inception network and 0.811 (SD 0.032) for the 3intoUNet network. The representative magnetic resonance slices (ie, from a data set of unseen magnetic resonance images) that were automatically selected by the INHEARIT-v2 system only differed from a maximum of 2 expert-selected slices. After comparing the ratios calculated by experienced physicians and those calculated by the INHEARIT-v2 system, we found that the average intraclass correlation coefficient for all cases was 0.941; the average intraclass correlation coefficient of the vestibules was 0.968, and that of the cochleae was 0.914. The time required for the fully automated system to accurately analyze EH ratios based on a patient's MRI stack was approximately 3.5 seconds. Conclusions: In this study, a fully automated full-stack magnetic resonance analysis system for measuring EH ratios was developed (named INHEARIT-v2), and the results showed that there was a high correlation between the expert-calculated EH ratio values and those calculated by the INHEARIT-v2 system. The system is an upgraded version of the INHEARIT system; it has higher segmentation performance and automatically selects representative images from an MRI stack. The new model can help clinicians by providing objective analysis results and reducing the workload for interpreting magnetic resonance images.

Objectives. This study was conducted to investigate the electroacoustic characteristics of personal sound amplification products (PSAPs), to identify whether PSAPs provide adequate gain and output for three common hearing loss (HL) configurations, and to compare the benefits of a representative PSAP (RPSAP) and a conventional hearing aid (HA) for clinical hearing outcomes as a pilot study.Methods. The study comprised three phases: electroacoustic analysis, simulated real-ear measurements (REMs), and clinical hearing experiments. Electroacoustic analysis and simulated REMs were performed for three basic PSAPs (BeethoSOL, EarJJang, and Geniesori2) and three high-end PSAPs (Hearing Able, Olive Smart Ear, and SoriIn) using the Aurical Hearing Instrument Test box with a 2-mL coupler. Four electroacoustic characteristics (maximum output sound pressure level at 90 dB SPL, frequency range, equivalent input noise, and total harmonic distortion) were investigated. By simulated REMs, appropriate levels of the six PSAPs for three common HL configurations (mild-to-moderate high-frequency HL, moderate to moderately severe sloping HL, and moderate flat HL) were determined. Clinical experiments compared the performance of RPSAP to HA, both of which were fitted by audiologists using REMs. Clinical experiments were administered using functional gain, a word recognition test, and the Korean version of the Hearing in Noise Test in six participants with bilateral moderate sensorineural HL.Results. The two high-end devices met all tolerances. One basic and two high-end PSAPs showed appropriate levels for three common HL configurations. In the clinical experiments, the RPSAP showed better performance than unaided, but slightly worse than HA under all test conditions.Conclusion. Certain PSAPs met all specified tolerances for electroacoustic analysis and approximated prescriptive targets in well-controlled laboratory conditions. The pilot clinical experiments explored the possibility that the RPSAP could serve as a hearing assistive device for patients with moderate HL.

Kim GY, et al. J Korean Med Sci. 2022 Mar;37(12):e94. https://doi.org/10.3346/jkms.2022.37.e94

Kim GY, et al. Yonsei Med J. 2022 Jun;63(6):570-577. https://doi.org/10.3349/ymj.2022.63.6.570

Objectives. Bone-anchored hearing device (BAHD) is contraindicated in patients younger than 5 years because their calvarial bones are not thick enough to be implanted site. However, it has not been studied in the Korean population. This study was not only to establish a safe guideline for depth of implant device in all age groups who undergo BAHD implant surgery, but also to investigate whether implantation of currently used BAHDs could be done safely in Korean children, especially those younger than 5.Methods. Two hundred eighty patients, who underwent high-resolution temporal bone computed tomography (TBCT) images between August 2010 and October 2018 were randomly enrolled in all ages. We retrospectively reviewed TBCT imaging to measure skull bone thickness at the recommended BAHD implant site.Results. The average skull bone thickness was 2.87 mm in patients younger than 5 years and 6.72 mm in patients older than 5 years, respectively, which conforms to the current guideline. The results indicate nearly 50% of calvarial bone thicknesses were less than 3 mm in patients under 5 years old, while 92.78% of the patients older than 5 years of age showed bone thickness greater than 4 mm. Of note, calvarial bone thickness was thicker than 3 mm in all patients who are older than 6 years.Conclusion. This study confirms that the currently approved BAHD implantation guideline is suitable in the Korean population. For safety, we suggest taking TBCTs prior to surgery, especially in pediatric patients. Besides, noninvasive applications are recommended for patients younger than 5.