Search

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., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2024 Kwon et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Background/objective: There have been several operative techniques for adenoidectomy and their efficacy and morbidity are different according to the technique. This prospective multicenter study was aimed to compare the efficacy and morbidity of coblation adenoidectomy (CA) with those of power-assisted adenoidectomy., Study Design: Prospective multi-institutional study., Methods: Children who underwent CA, power-assisted adenoidectomy with cauterization (PAA+C) or without cauterization (PAA-C) due to adenoid hypertrophy were enrolled from 13 hospitals between July 2013 and June 2014. Mean operation time, degree of intraoperative bleeding and postoperative bleeding rate were evaluated., Results: A total of 388 children (mean age ± standard deviation = 6.6 ± 2.5 years; 245 males and 143 females) were included. According to the adenoidectomy technique, the children were classified into 3 groups: (1) CA (n = 116); (2) PAA+C (n = 153); and (3) PAA-C (n = 119). Significant differences were not found in age and sex among three groups. In the CA group, mean operation time was significantly shorter (P < 0.001) and degree of intraoperative bleeding was significantly less (P < 0.001) compared to PAA+C or PAA-C group. Delayed postoperative bleeding rate of PAA-C group was significantly higher than that of CA or PAA+C group (P = 0.016)., Conclusions: This prospective multicenter study showed that CA was superior to PAA in terms of mean operation time and degree of intraoperative bleeding.

Background: It has been well known that pediatric allergic rhinitis was associated with poor performance at school due to attention deficit. However, there were no cohort studies for the effect of treatment of allergic rhinitis on attention performance in pediatric population. Thus, the aim of this study was to investigate whether attention performance was improved after treatment in children with allergic rhinitis., Methods: In this ARCO-Kids (Allergic Rhinitis Cohort Study for Kids), consecutive pediatric patients with rhinitis symptoms underwent a skin prick test and computerized comprehensive attention test. According to the skin prick test results, the children were diagnosed as allergic rhinitis or non- allergic rhinitis. All of the patients were regularly followed up and treated with oral medication or intranasal corticosteroid sprays. The comprehensive attention tests consisted of sustained and divided attention tasks. Each of the tasks was assessed by the attention score which was calculated by the number of omission and commission errors. The comprehension attention test was repeated after 1 year., Results: A total of 797 children with allergic rhinitis and 239 children with non-allergic rhinitis were included. Initially, the attention scores of omission and commission errors on divided attention task were significantly lower in children with allergic rhinitis than in children with non-allergic rhinitis. After 1 year of treatment, children with allergic rhinitis showed improvement in attention: commission error of sustained (95.6±17.0 vs 97.0±16.6) and divided attention task (99.1±15.8 vs 91.8±23.5). Meanwhile, there was no significant difference of attention scores in children with non-allergic rhinitis., Conclusions: Our study showed that management of allergic rhinitis might be associated with improvement of attention.