Search

Background: This study aimed to develop and validate a deep learning (DL) model to identify atelectasis and attic retraction pocket in cases of otitis media with effusion (OME) using multi-center otoscopic images. Method: A total of 6393 OME otoscopic images from three centers were used to develop and validate a DL model for detecting atelectasis and attic retraction pocket. A threefold random cross-validation procedure was adopted to divide the dataset into training validation sets on a patient level. A team of otologists was assigned to diagnose and characterize atelectasis and attic retraction pocket in otoscopic images. Receiver operating characteristic (ROC) curves, including area under the ROC curve (AUC), accuracy, sensitivity, and specificity were used to assess the performance of the DL model. Class Activation Mapping (CAM) illustrated the discriminative regions in the otoscopic images. Results: Among all OME otoscopic images, 3564 (55.74%) were identified with attic retraction pocket, and 2460 (38.48%) with atelectasis. The diagnostic DL model of attic retraction pocket and atelectasis achieved a threefold cross-validation accuracy of 89% and 79%, AUC of 0.89 and 0.87, a sensitivity of 0.93 and 0.71, and a specificity of 0.62 and 0.84, respectively. Larger and deeper cases of atelectasis and attic retraction pocket showed greater weight, based on the red color depicted in the heat map of CAM. Conclusion: The DL algorithm could be employed to identify atelectasis and attic retraction pocket in otoscopic images of OME, and as a tool to assist in the accurate diagnosis of OME. [ABSTRACT FROM AUTHOR]

The purpose of this study was to investigate the effect of symmetrical, asymmetrical and unilateral hearing impairment on music quality perception. Six validated music pieces in the categories of classical music, folk music and pop music were used to assess music quality in terms of its 'pleasantness', 'naturalness', 'fullness', 'roughness' and 'sharpness'. 58 participants with sensorineural hearing loss [20 with unilateral hearing loss (UHL), 20 with bilateral symmetrical hearing loss (BSHL) and 18 with bilateral asymmetrical hearing loss (BAHL)] and 29 normal hearing (NH) subjects participated in the present study. Hearing impaired (HI) participants had greater difficulty in overall music quality perception than NH participants. Participants with BSHL rated music pleasantness and naturalness to be higher than participants with BAHL. Moreover, the hearing thresholds of the better ears from BSHL and BAHL participants as well as the hearing thresholds of the worse ears from BSHL participants were negatively correlated to the pleasantness and naturalness perception. HI participants rated the familiar music pieces higher than unfamiliar music pieces in the three music categories. Music quality perception in participants with hearing impairment appeared to be affected by symmetry of hearing loss, degree of hearing loss and music familiarity when they were assessed using the music quality rating test (MQRT). This indicates that binaural symmetrical hearing is important to achieve a high level of music quality perception in HI listeners. This emphasizes the importance of provision of bilateral hearing assistive devices for people with asymmetrical hearing impairment. [ABSTRACT FROM AUTHOR]

The objective of the study was to elucidate the characteristics of spatial distribution of nasal polyps in the ostiomeatal complex (OMC) and the corresponding correlation with long-term quality of life in patients who underwent endoscopic sinus surgery. 107 patients with unilateral or bilateral nasal polyps who had undergone functional endoscopic sinus surgery from September 2009 to June 2010 were enrolled in this study. Distribution of nasal polyps in the study subjects was documented. Long-term quality of life assessment was carried out at 1-year after surgery by SNOT-20 analysis. Observation of a total of 214 sides of rhinal cavities revealed that nasal polyps were distributed inside the OMC at 573 sites out of the total 635 sites (90.2 %), and predominantly distributed at the middle turbinate, the ethmoid sinus, the middle meatus, the uncinate process, the maxillary sinus, and the ethmoid bulla and significantly differed from the nasal polyps which were found outside the OMC ( P < 0.01). Statistical analysis indicated that pre-operative Sinonasal Outcome Test 20 (SNOT-20) scores and 1-year post-operative scores were statistically significant ( P < 0.05). The score changes of the left maxillary sinus, both sides ethmoid bulla were significant, respectively ( P < 0.05). Nasal polyps predominantly distribute in the OMC. The differences among the sites of nasal polyps do not significantly impact the long-term score for quality of life except for the maxillary sinus and ethmoid bulla. [ABSTRACT FROM AUTHOR]

This study aimed at investigating the survival rate and prognostic factors of laryngeal carcinoma patients in the absence of the use of laryngectomy, radiotherapy, and chemotherapy. A total of 167 cases of laryngeal carcinoma without the use of laryngectomy, radiotherapy, or chemotherapy were analyzed retrospectively. Surveyed items included age, smoking history, tumor family history, tuberculosis history, primary site, pathological grade, T-stage, N-stage, clinical stage, and whether tracheotomy had been performed. Survival rates were calculated using the Kaplan-Meier method. For univariate analysis, comparison among/between groups was performed using the log-rank test. Multivariate analysis was carried out using the Cox proportional hazard model. Overall median survival time was 16 ± 1.44 months, and overall 1- and 2-year survival rates were 56.4 and 26.5%, respectively. No patient survived over 5 years in cases diagnosed for more than 5 years (except for cases that were lost). The median survival time of clinical stage 0/I/II was 28 ± 3.81 months, and 1- and 2-year survival rates were 79.3 and 59.3%, respectively; the median survival time of III/IV clinical stages was 11 ± 1.32 months, and 1- and 2-year survival rates were 45.5 and 10.6%, respectively. Univariate analysis showed that primary site, pathological grade, T-stage, N-stage, and clinical stage were significant prognostic factors for the survival of the patients ( P < 0.05). Whether tracheotomy had been performed was not significant for affecting survival rates. Multivariate analysis showed survival rates were statistically correlated with T-stage and N-stage ( P < 0.05). The development of laryngeal carcinoma course was faster, without treatment to the tumor itself, even if palliative surgery such as tracheostomy would not improve the survival rate. In laryngeal carcinoma patients with no surgery, radiotherapy or chemotherapy, the factors affecting the survival rates include primary site, pathological grade, T-stage, N-stage, and clinical stage, and of them, T-stage and N-stage are the independent prognostic factors. [ABSTRACT FROM AUTHOR]