Objectives/Hypothesis: There may be an interobserver variation in the diagnosis of laryngeal disease based on laryngoscopic images according to clinical experience. Therefore, this study is aimed to perform computer-assisted diagnosis for common laryngeal diseases using deep learning-based disease classification models.Study Design: Experimental study with retrospective data Methods: A total of 4106 images (cysts, nodules, polyps, leukoplakia, papillomas, Reinke's edema, granulomas, palsies, and normal cases) were analyzed. After equal distribution of diseases into ninefolds, stratified eightfold cross-validation was performed for training, validation process and remaining onefold was used as a test dataset. A trained model was applied to test sets, and model performance was assessed for precision (positive predictive value), recall (sensitivity), accuracy, F1 score, precision-recall (PR) curve, and PR-area under the receiver operating characteristic curve (PR-AUC). Outcomes were compared to those of visual assessments by four trainees.Results: The trained deep neural networks (DNNs) outperformed trainees' visual assessments in discriminating cysts, granulomas, nodules, normal cases, palsies, papillomas, and polyps according to the PR-AUC and F1 score. The lowest F1 score and PR-AUC of DNNs were estimated for Reinke's edema (0.720, 0.800) and nodules (0.730, 0.780) but were comparable to the mean of the two trainees' F1 score with the best performances (0.765 and 0.675, respectively). In discriminating papillomas, the F1 score was much higher for DNNs (0.870) than for trainees (0.685). Overall, DNNs outperformed all trainees (micro-average PR-AUC = 0.95; macro-average PR-AUC = 0.91).Conclusions: DNN technology could be applied to laryngoscopy to supplement clinical assessment of examiners by providing additional diagnostic clues and having a role as a reference of diagnosis.
Objective:The purpose of this study was to evaluate the clinical outcome of surgical decompression and rehabilitation therapy in dogs with thoracolumbar intervertebral disk herniation (IVDH).Materials and Methods:After surgery, physiotherapeutic rehabilitation was performed by a combination of electrotherapy, infrared therapy, training for standing, deep tendon reflex, and aquatic treadmill exercise. A total of 186 dogs were selected from the hospital records and included in two groups: the rehabilitated group (RG, n = 96) and non-rehabilitated group (NRG, n = 90). Dogs in each group were subdivided into three groups based on a pre-operative clinical severity grading system and those in grades 2–4 were included in this study. Post-operative neurologic functions, unassisted standing, walking, and the success rate of both groups were evaluated and comparedResults:Overall, 86.46% (83/96) of dogs had a successful neurologic outcome in the RG group, which was significantly (p < 0.01) higher than the NRG group 52.22% (47/90). Interestingly, the success rate differed when the preoperative grading system was considered. The success rates of grades 2, 3, and 4 were 97.14% (34/35), 97.33% (42/45), and 43.75% (7/16), respectively, in the rehabilitated groups, whereas in the non-rehabilitated groups, success rates were 82.35% (28/34), 51.85% (14/27), and 17.24% (5/29), respectively. The differences in success rates among the groups according to grading were 14.79%, 41.48%, and 26.51%, respectively, indicating that the proposed rehabilitation therapy is remarkably advantageous for increasing the success rate.Conclusion:Rehabilitation therapy after surgical decompression of thoracolumbar IVDH improves neurologic functions and increases the success rate, especially when the preoperative pathological condition is severe.
Dysbiosis of the sinus microbiome affects the pathophysiology of chronic rhinosinusitis with nasal polyps (CRSwNPs). We investigated whether the sinus microbiota in CRSwNPs is associated with eosinophilic inflammation, especially in relation to innate lymphoid cells (ILCs), prognosis, and serum extracellular vesicles (EVs). Middle meatal swabs and serum from 31 CRSwNPs patients and six healthy controls were analyzed by 16S ribosomal RNA sequencing. ILC2s and cytokines from sinonasal tissues were measured by flow cytometry and ELISA, respectively. The relative abundances (RAs) of bacteria were compared based on eosinophilic inflammation and surgical outcome. The correlations between sinus bacteria and ILC2s, cytokines, and serum EVs were analyzed. The compositions of sinus bacteria were different between groups at the genus level. In eosinophilic CRSwNPs patients, the RA of Anaerococcus was significantly decreased ( P = 0.010), whereas that of Lachnoclostridium was significantly increased ( P = 0.038) compared with that in controls. The RA of Lachnoclostridium showed a significant positive correlation with interleukin (IL)-5-producing ILC2 populations ( R = 0.340, P = 0.049), whereas the RA of Anaerococcus showed a negative correlation with IL-5-producing ILC2 populations ( R = −0.332, P = 0.055). The RAs of Corynebacterium , Anaerococcus , and Tepidimonas were significantly decreased in patients with suboptimal outcomes compared with those in patients with optimal outcomes and control subjects. Some sinus bacteria and serum EVs showed positive correlations. CRSwNPs patients showed distinct microbiota compositions based on eosinophilic inflammation in relation to ILC2s and surgical outcome. These findings support a relationship between the microbiota and the host immune response in CRSwNPs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.