Deep learning algorithm for the automated detection and classification of nasal cavity mass in nasal endoscopic images.

Nasal endoscopy is routinely performed to distinguish the pathological types of masses. There is a lack of studies on deep learning algorithms for discriminating a wide range of endoscopic nasal cavity mass lesions. Therefore, we aimed to develop an endoscopic-examination-based deep learning model to detect and classify nasal cavity mass lesions, including nasal polyps (NPs), benign tumors, and malignant tumors. The clinical feasibility of the model was evaluated by comparing the results to those of manual assessment. Biopsy-confirmed nasal endoscopic images were obtained from 17 hospitals in South Korea. Here, 400 images were used for the test set. The training and validation datasets consisted of 149,043 normal nasal cavity, 311,043 NP, 9,271 benign tumor, and 5,323 malignant tumor lesion images. The proposed Xception architecture achieved an overall accuracy of 0.792 with the following class accuracies on the test set: normal = 0.978 ± 0.016, NP = 0.790 ± 0.016, benign = 0.708 ± 0.100, and malignant = 0.698 ± 0.116. With an average area under the receiver operating characteristic curve (AUC) of 0.947, the AUC values and F1 score were highest in the order of normal, NP, malignant tumor, and benign tumor classes. The classification performances of the proposed model were comparable with those of manual assessment in the normal and NP classes. The proposed model outperformed manual assessment in the benign and malignant tumor classes (sensitivities of 0.708 ± 0.100 vs. 0.549 ± 0.172, 0.698 ± 0.116 vs. 0.518 ± 0.153, respectively). In urgent (malignant) versus nonurgent binary predictions, the deep learning model achieved superior diagnostic accuracy. The developed model based on endoscopic images achieved satisfactory performance in classifying four classes of nasal cavity mass lesions, namely normal, NP, benign tumor, and malignant tumor. The developed model can therefore be used to screen nasal cavity lesions accurately and rapidly.

The Relationship Between Lateral Nasal Wall Collapse and Nasal Obstruction.

OBJECTIVES: In clinical practice, lateral nasal wall collapse during forced inspiration is widely regarded as a sign of nasal obstruction or criterion indicating nasal valve surgery. This study aims to evaluate the relationship between the degree of lateral nasal wall collapse and subjective nasal obstruction. In addition, factors related to lateral nasal wall collapse were also investigated. METHODS: In this study, lateral nasal wall collapse is determined by the degree of lateral nasal wall triangle (LNWT) area reduction on frontal view during forced inspiration compared to quiet inspiration. LNWT area ratio of the patient and control groups was compared. The relationship between the lateral nasal wall collapse and clinical factors including symptom scores, nasal valve angles, skin thickness were evaluated. RESULTS: The average LNWT area ratio of the patient (n = 24) and control groups (n = 27) was 0.96 and 0.83 respectively (P = .001). Symptom score (NOSE and VAS) is not related to the degree of lateral nasal wall collapse. Moreover, nasal valve angle and skin thickness were also not related to the degree of lateral nasal wall collapse. In 14 of the 19 patients, the more obstructed side corresponded to the side of narrower nasal valve angle, and 5 were not. CONCLUSION: Lateral nasal wall collapse is not related to a patients' nasal obstruction.

Effect of olfactory bulb atrophy on the success of olfactory training.

PURPOSE: To evaluate the success of olfactory training in patients with olfactory loss and olfactory bulb (OB) atrophy detected on magnetic resonance imaging (MRI) and other characteristics. METHODS: This study included 48 patients with olfactory loss who underwent a nasal endoscopic examination and MRI before olfactory training. The Korean Version of the Sniffin' Sticks Test was performed before and after training. The olfactory training success was defined as an improvement of more than 6 points in the Threshold-Discrimination-Identification (TDI) score. Patient characteristics and OB atrophy pre-training were compared between successful and unsuccessful groups. RESULTS: The etiology of olfactory loss included respiratory viral infection in 30 (62.5%), trauma in 10 (20.8%), and idiopathic loss in 8 (16.7%) patients. Twenty-three (47.9%) of 48 patients exhibited successful olfactory training. Etiology, age, gender, and symptom duration were not different between unsuccessful and successful groups. Pre-training discrimination, identification, and TDI scores were significantly different between unsuccessful and successful groups (P < 0.05). Success rate of patients with bilateral OB atrophy was significantly lower than that of patients with unilateral OB atrophy and normal morphology (P = 0.006). OB height was significantly lower in the unsuccessful group than in the successful group (P < 0.05). Bilateral OB atrophy was an independent risk factor for failure of olfactory training according to the multivariate analysis. CONCLUSION: Olfactory loss patients with bilateral OB atrophy may not be able to improve olfactory function after olfactory training.

Hypochlorous Acid Versus Saline Nasal Irrigation in Allergic Rhinitis: A Multicenter, Randomized, Double-Blind, Placebo-controlled Study.

BACKGROUND: Low concentrations of hypochlorous acid (HOCl) have proven antipruritic, anti-inflammatory, and antimicrobial effects without toxicity, although the mechanism has not been fully elucidated. OBJECTIVE: The aim of this study was to evaluate the effectiveness of HOCl nasal irrigation to reduce allergic rhinitis (AR) symptoms compared with saline nasal irrigation. METHODS: This was multicenter, randomized, double-blind, placebo-controlled study. Initially, 139 patients with perennial AR were enrolled; however, 25 did not successfully complete the study. Patients were randomly assigned to the nasal irrigation with low-concentration HOCl (n = 55) or normal saline (n = 59) treatment groups for the 4-week study period. Participants completed the Rhinoconjunctivitis Quality of Life Questionnaire (RQLQ) at every visit (baseline, Weeks 2 and 4), and Total Nasal Symptom Score (TNSS) was determined before and after nasal irrigation every morning and evening. RESULTS: We found that RQLQ scores significantly decreased after 4 weeks in the HOCl and placebo groups, but the decrement of the RQLQ score was similar between the 2 groups. Additionally, TNSS improved in both groups between baseline and Week 4, whereas there were no significant differences in the change of TNSS between the 2 groups. The HOCl group did not show any clinical side effects related to nasal irrigation. CONCLUSION: Allergic symptoms significantly decreased with low-concentration HOCl nasal irrigation, without significant adverse events. However, HOCl showed no additional improvement in symptoms compared with saline nasal irrigation for patients with perennial AR.

Reconstruction of a Severely Damaged Cartilaginous Septum with a Bypass L-Strut Graft using Costal Cartilage.

OBJECTIVE: Reconstruction of a weakened septal cartilage is a key procedure for the correction of deformed noses. However, when septal mucoperichondrium dissection is technically challenging, reconstruction of the lower two-thirds of the nose should be performed bypassing the damaged septal cartilage and mucosa. This article summarizes our experience with treating patients with severely damaged septal cartilage with bypass L-strut graft using costal cartilage. METHODS: We retrospectively reviewed 26 patients who underwent rhinoplasty using bypass L-strut graft. Autologous costal cartilage was used for creating L-strut in two different ways: (1) by fashioning the L-shaped graft as one unit using the sixth rib cartilage and (2) by integrating a dorsal strut with a columellar strut using slices of the seventh rib cartilage. The caudal strut is fixated to the anterior nasal spine; the dorsal L-strut is placed on the nasal dorsum with no fixation to the nasal bone. Medical records were assessed for demographic, clinical, and treatment information. RESULTS: One-piece-type L-strut graft was used for 11 patients and integrated-type L-strut graft was used for 15 patients. No statistical differences were found in postoperative aesthetic outcomes between the two groups. The postoperative assessment of surgical outcomes was excellent in 10 patients, good in 10, fair in 6, and poor in none. Functionally, all 26 patients experienced improvements in nasal breathing. CONCLUSION: Bypass L-strut graft using costal cartilage is a useful surgical maneuver of septal reconstruction in particular nasal deformity when the creation of the septal mucoperichondrial pocket is difficult or better to be avoided.

Assessment of Objective Audiometry to Predict Subjective Satisfaction in Patients With Hearing Aids.

OBJECTIVES: To investigate the correlation of objective audiometry with user satisfaction as measured with the questionnaire scores. METHODS: Twenty patients with hearing loss, who agreed to wear a hearing aid and were referred for hearing aid fitting, were included in this prospective clinical study. All patients used the in-the-canal type of Wide7 hearing aid provided by BSL Co., Ltd. We performed the Korean version of the Hearing Handicap Inventory for the Elderly (K-HHIE) and the International Outcome Inventory for Hearing Aids (K-IOI-HA) before and 1, 3, and 6 months after wearing the hearing aid. We also performed pure tone audiometry (PTA), speech audiometry (SA), functional gain (FG), hearing in noise test (HINT), and central auditory processing disorder tests, such as frequency pattern test (CA-f), duration pattern test (CA-d), and dichotic test (CA-Di). Patients were divided into two groups (group A-HHIE, improved; group B-HHIE, same or worse) by comparing the score of K-HHIE before and 6 months after wearing the hearing aid. In the 6-month K-IOI-HA questionnaire, 21 points were considered as the average score. Based on this, we further divided patients into two groups (group A-IOI, >21 points; group B-IOI, ≤21 points). RESULTS: Group A-HHIE included six patients and group B-HHIE included 14 patients. In PTA, SA, HINT, CA-d, and CA-Di, group A-HHIE showed higher improvements than group B-HHIE, which were not statistically significant. Group A-IOI included 12 patients and group B-IOI included eight patients. No statistically significant difference was noted in the improvement of audiometric results over a period of 6 months after wearing the hearing aid between groups A-IOI and B-IOI. CONCLUSION: There were no significant and consistent audiometric results to reflect patient's satisfaction with the hearing aid. Therefore, when analyzing the hearing aid-fitting outcome, both the objective audiometric tests and subjective questionnaire should be performed together for validating hearing aid performance.

Multifocality of papillary thyroid carcinoma as a risk factor for disease recurrence.

OBJECTIVES: Tumor multifocality or bilaterality is associated with increased risk of papillary thyroid carcinoma (PTC) recurrence. However, its prognostic value in clinical outcomes remains controversial. This study aimed to evaluate the association of multifocality or bilaterality with recurrence and survival after total thyroidectomy. METHODS: This was a retrospective study of 2390 consecutive patients with pathologically confirmed PTC who underwent total thyroidectomy. Multifocality and bilaterality were decided based on the final pathology results, that is, if there were two or more tumor foci and bilateral location, respectively. Primary outcomes were recurrence-free survival (RFS). Cox proportional hazards regression analyses were used to assess the associations of multifocality, bilaterality, and other clinicopathological factors with RFS. RESULTS: Multifocal and bilateral PTC were found in 892 (37.3%) and 593 (24.8%) patients, respectively. Multivariate analyses showed that multifocality, lymphovascular invasion, N category, and number of positive lymph node (>5) were significant independent variables predictive of RFS (all P < 0.05). Multifocality was associated with adjusted hazard ratios for RFS of 1.93 (95% confidence interval = 1.33-2.80; P = 0.001). In a subset analysis, the prognostic value of multifocality was found to be significant in those patients with PTC > 1 cm, but not in papillary thyroid microcarcinoma. CONCLUSIONS: Tumor multifocality is an independent risk factor of PTC recurrence after total thyroidectomy. This indicate a more progressive state of disease, being included in risk stratification.

Metabolic tumor volume and total lesion glycolysis predict tumor progression and survival after salvage surgery for recurrent oral cavity squamous cell carcinoma.

BACKGROUND: This study evaluated the prognostic role of Fluorine 18-fluorodeoxyglucose positron emission tomography/CT (18 F-FDG PET/CT) parameters quantitatively measured in patients with recurrent oral cavity cancer. METHODS: Cox proportional hazards regression analyses were used to assess the associations between quantitative 18 F-FDG PET/CT parameters and other clinicopathological factors and progression-free survival (PFS) and overall survival (OS). RESULTS: All of the 18 F-FDG PET parameters (SUVmax , SUVmean , SUVpeak , metabolic tumor volume [MTV], and total lesion glycolysis [TLG]) were significantly associated with poor PFS and OS outcomes after salvage treatment (P < .01). In multivariate analyses, Karnofsky performance score, recurrence site, MTV, and TLG were independent variables predictive of both PFS and OS (P < .05). High MTV (>8.8 mL) or TLG (>29.4 g) values at recurrent lesions were associated with >5-fold increased risk for tumor progression and mortality after salvage surgery. CONCLUSIONS: The PET parameters of MTV and TLG measured at recurrent lesions may predict tumor progression and survival after salvage treatment. CONDENSED ABSTRACT: This study examined the role of 18 F-FDG PET/CT at recurrent staging for predicting tumor progression and survival in 71 consecutive patients with recurrent oral cavity squamous cell carcinomas. Of 18 F-FDG parameters, metabolic tumor volume and total lesion glycolysis were independent factors predictive of tumor progression and survival after salvage treatment.

Reliability and validity of the Korean version of the Questionnaire of Olfactory Disorders.

BACKGROUND: The Questionnaire of Olfactory Disorders (QOD) is a self-report questionnaire that provides subjective information about olfactory dysfunction. The QOD is widely used in clinical practice because of its high level of reliability and efficacy in Western countries. In this study we evaluated the reliability and validity of the Korean version of the QOD. METHODS: A total of 213 patients with subjective olfactory dysfunction completed 2 different surveys (the QOD and the 36-item Short-Form Health Survey [SF-36]). Patients' olfactory function was evaluated by a screening cross-cultural smell identification test or the Korean version of the Sniffin' Sticks (KVSS) II Test. The Korean version of the QOD was evaluated for split-half reliability and internal consistency. Criterion validity of QOD was determined by comparing with the SF-36. RESULTS: The split-half reliability was 0.967. Cronbach α coefficients for internal consistency of the QOD parosmia statements (QOD-P), QOD life quality statements (QOD-LQ), QOD sincerity statements (QOD-S), and QOD visual analog scale statements (QOD-VAS) were 0.705, 0.909, 0.243, and 0.953, respectively. There were statistically significant correlations between the SF-36 and the QOD-P, QOD-LQ, QOD-S, and QOD-VAS scores. There were no significant differences in QOD scores among patients with anosmia, hyposmia, and normosmia on the olfactory function test. Mean scores on the QOD-P, QOD-LQ, and QOD-VAS were significantly higher in 15 patients with normosmia on the olfactory function test when compared with 13 healthy controls. CONCLUSION: The Korean version of the QOD has proven to be a generally reliable and valid questionnaire to assess the degree of subjective olfactory dysfunction in the evaluation of Korean patients suspected of having olfactory dysfunction.

Changes of video head impulse test results in lateral semicircular canal plane by different peak head velocities in patients with vestibular neuritis.

BACKGROUND: The peak head velocity influences on the video head impulse test (vHIT) results, but it has been not known how much the difference is. AIMS: To evaluate the clinical evidence for the superiority of high-velocity compared to low-velocity vHIT. MATERIAL AND METHODS: vHIT was performed in 30 patients with vestibular neuritis using two peak head velocities (mean 80 vs. 240°/s). vHIT gains and parameters of corrective saccades (CSs) were compared. A vHIT gain of ≤0.8 or a peak CS velocity of ≥100°/s was considered pathologic. RESULTS: The vHIT gains were significantly lower (mean 0.5 vs. 0.6), and GA was larger (35 vs. 25%) at high-velocity vHIT, compared to low-velocity vHIT. CSs were significantly more frequent (100 vs. 80%) and peak CS velocities were larger (252 vs. 112°/s) at high-velocity vHIT. The abnormal rates based on vHIT gains were higher (90% vs. 73%) and CSs occurred more frequently (100% vs. 80%) at high-velocity vHIT. The abnormal rates based on the peak CS velocity were significantly higher at high-velocity vHIT (100% vs. 57%). CONCLUSION: High-velocity vHIT is superior to low-velocity vHIT with a difference of 17-20% based on pathologic vHIT gains and presence of CSs.