Change of Phonation in Canines Without Vocal Fold Paralysis After Vocal Processes Resection.

The effects of the vocal processes resection on phonation in an animal without vocal fold paralysis have not been clarified. The present study used an in vivo animal model with vocal processes resection and excised larynges phonation model to investigate the effects of the vocal processes resection on phonation. Six months after resection of bilateral vocal fold processes, glottal airflow, subglottal air pressure, acoustic signals, and ultra-high-speed video images were recorded in the excised larynges phonation model of canine. Glottal aerodynamic parameters were estimated by calculation of subglottal pressure and glottal flow. Histological analyses of the scarred were assessed for wound healing completion. In the vocal processes resection group, fundamental frequency(F0) and vocal intensity decreased, and the Jitter and Shimmer increased significantly. The phonation threshold power(PTW) of the vocal processes resection was significantly higher than controls. The vibratory amplitude of the vocal fold posterior and visual vocal fold vibration length increased. Expression of collagen I-III in scarred tissue samples in vocal process resection was similar to controlling soft tissue specimens around vocal process cartilage, and collagen fiber formed matured thick bundles. The results suggest that the F0, voice quality, and vocal intensity significantly decreased after complete wound healing of vocal processes resection in canines without vocal folds paralysis. The higher PTW and posterior scarred vocal vibration may be the dynamic reasons.

Automated detection of glottic laryngeal carcinoma in laryngoscopic images from a multicentre database using a convolutional neural network.

OBJECTIVE: Little is known about the efficacy of using artificial intelligence (AI) to identify laryngeal carcinoma from images of vocal lesions taken in different hospitals with multiple laryngoscope systems. This multicentre study aimed to establish an AI system and provide a reliable auxiliary tool to screen for laryngeal carcinoma. STUDY DESIGN: Multicentre case-control study. SETTING: Six tertiary care centres. PARTICIPANTS: Laryngoscopy images were collected from 2179 patients with vocal fold lesions. OUTCOME MEASURES: An automatic detection system of laryngeal carcinoma was established and used to distinguish malignant and benign vocal lesions in 2179 laryngoscopy images acquired from 6 hospitals with 5 types of laryngoscopy systems. Pathological examination was the gold standard for identifying malignant and benign vocal lesions. RESULTS: Out of 89 cases in the malignant group, the classifier was able to correctly identify laryngeal carcinoma in 66 patients (74.16%, sensitivity). Out of 640 cases in the benign group, the classifier was able to accurately assess the laryngeal lesion in 503 cases (78.59%, specificity). Furthermore, the region-based convolutional neural network (R-CNN) classifier achieved an overall accuracy of 78.05%, with a 95.63% negative predictive value and a 32.51% positive predictive value for the testing data set. CONCLUSION: This automatic diagnostic system has the potential to assist clinical laryngeal carcinoma diagnosis which may improve and standardise the diagnostic capacity of laryngologists using different laryngoscopes.