Literature DB >> 35304042

Detection of Vocal Fold Image Obstructions in High-Speed Videoendoscopy During Connected Speech in Adductor Spasmodic Dysphonia: A Convolutional Neural Networks Approach.

Ahmed M Yousef1, Dimitar D Deliyski1, Stephanie R C Zacharias2, Maryam Naghibolhosseini3.   

Abstract

OBJECTIVE: Adductor spasmodic dysphonia (AdSD) is a neurogenic voice disorder, affecting the intrinsic laryngeal muscle control. AdSD leads to involuntary laryngeal spasms and only reveals during connected speech. Laryngeal high-speed videoendoscopy (HSV) coupled with a flexible fiberoptic endoscope provides a unique opportunity to study voice production and visualize the vocal fold vibrations in AdSD during speech. The goal of this study is to automatically detect instances during which the image of the vocal folds is optically obstructed in HSV recordings obtained during connected speech.
METHODS: HSV data were recorded from vocally normal adults and patients with AdSD during reading of the "Rainbow Passage", six CAPE-V sentences, and production of the vowel /i/. A convolutional neural network was developed and trained as a classifier to detect obstructed/unobstructed vocal folds in HSV frames. Manually labelled data were used for training, validating, and testing of the network. Moreover, a comprehensive robustness evaluation was conducted to compare the performance of the developed classifier and visual analysis of HSV data.
RESULTS: The developed convolutional neural network was able to automatically detect the vocal fold obstructions in HSV data in vocally normal participants and AdSD patients. The trained network was tested successfully and showed an overall classification accuracy of 94.18% on the testing dataset. The robustness evaluation showed an average overall accuracy of 94.81% on a massive number of HSV frames demonstrating the high robustness of the introduced technique while keeping a high level of accuracy.
CONCLUSIONS: The proposed approach can be used for efficient analysis of HSV data to study laryngeal maneuvers in patients with AdSD during connected speech. Additionally, this method will facilitate development of vocal fold vibratory measures for HSV frames with an unobstructed view of the vocal folds. Indicating parts of connected speech that provide an unobstructed view of the vocal folds can be used for developing optimal passages for precise HSV examination during connected speech and subject-specific clinical voice assessment protocols.
Copyright © 2022 The Voice Foundation. Published by Elsevier Inc. All rights reserved.

Entities:  

Keywords:  Laryngeal imaging—Connected speech—High-speed videoendoscopy—Adductor spasmodic dysphonia—Vocal fold obstruction—Convolutional neural network

Year:  2022        PMID: 35304042      PMCID: PMC9474736          DOI: 10.1016/j.jvoice.2022.01.028

Source DB:  PubMed          Journal:  J Voice        ISSN: 0892-1997            Impact factor:   2.300


  32 in total

1.  Observation and analysis of in vivo vocal fold tissue instabilities produced by nonlinear source-filter coupling: a case study.

Authors:  Matías Zañartu; Daryush D Mehta; Julio C Ho; George R Wodicka; Robert E Hillman
Journal:  J Acoust Soc Am       Date:  2011-01       Impact factor: 1.840

2.  Diagnostic Accuracies of Laryngeal Diseases Using a Convolutional Neural Network-Based Image Classification System.

Authors:  Won Ki Cho; Yeong Ju Lee; Hye Ah Joo; In Seong Jeong; Yeonjoo Choi; Soon Yuhl Nam; Sang Yoon Kim; Seung-Ho Choi
Journal:  Laryngoscope       Date:  2021-05-17       Impact factor: 3.325

3.  Deep Learning-A Technology With the Potential to Transform Health Care.

Authors:  Geoffrey Hinton
Journal:  JAMA       Date:  2018-09-18       Impact factor: 56.272

4.  Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images.

Authors:  Toshiaki Hirasawa; Kazuharu Aoyama; Tetsuya Tanimoto; Soichiro Ishihara; Satoki Shichijo; Tsuyoshi Ozawa; Tatsuya Ohnishi; Mitsuhiro Fujishiro; Keigo Matsuo; Junko Fujisaki; Tomohiro Tada
Journal:  Gastric Cancer       Date:  2018-01-15       Impact factor: 7.370

5.  Automated measurement of vocal fold vibratory asymmetry from high-speed videoendoscopy recordings.

Authors:  Daryush D Mehta; Dimitar D Deliyski; Thomas F Quatieri; Robert E Hillman
Journal:  J Speech Lang Hear Res       Date:  2010-08-10       Impact factor: 2.297

6.  Temporal Segmentation for Laryngeal High-Speed Videoendoscopy in Connected Speech.

Authors:  Maryam Naghibolhosseini; Dimitar D Deliyski; Stephanie R C Zacharias; Alessandro de Alarcon; Robert F Orlikoff
Journal:  J Voice       Date:  2017-06-21       Impact factor: 2.009

7.  Automatic Recognition of Laryngoscopic Images Using a Deep-Learning Technique.

Authors:  Jianjun Ren; Xueping Jing; Jing Wang; Xue Ren; Yang Xu; Qiuyun Yang; Lanzhi Ma; Yi Sun; Wei Xu; Ning Yang; Jian Zou; Yongbo Zheng; Min Chen; Weigang Gan; Ting Xiang; Junnan An; Ruiqing Liu; Cao Lv; Ken Lin; Xianfeng Zheng; Fan Lou; Yufang Rao; Hui Yang; Kai Liu; Geoffrey Liu; Tao Lu; Xiujuan Zheng; Yu Zhao
Journal:  Laryngoscope       Date:  2020-02-18       Impact factor: 3.325

8.  Automated acoustic analysis of task dependency in adductor spasmodic dysphonia versus muscle tension dysphonia.

Authors:  Nelson Roy; Alqhazo Mazin; Shaheen N Awan
Journal:  Laryngoscope       Date:  2013-10-01       Impact factor: 3.325

Review 9.  Muscle misuse voice disorders: description and classification.

Authors:  M D Morrison; L A Rammage
Journal:  Acta Otolaryngol       Date:  1993-05       Impact factor: 1.494

10.  Comparative analysis of high-speed videolaryngoscopy images and sound data simultaneously acquired from rigid and flexible laryngoscope: a pilot study.

Authors:  Wioletta Pietruszewska; Marcin Just; Joanna Morawska; Jakub Malinowski; Joanna Hoffman; Anna Racino; Magda Barańska; Magdalena Kowalczyk; Ewa Niebudek-Bogusz
Journal:  Sci Rep       Date:  2021-10-14       Impact factor: 4.379

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.