Automatic diagnosis of vocal fold paresis by employing phonovibrogram features and machine learning methods

Voigt, Daniel; Döllinger, Michael; Yang, Anxiong; Eysholdt, Ulrich; Lohscheller, Jörg

doi:10.1016/j.cmpb.2010.01.004

Cited by 41 publications

(39 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The analysis of vocal fold dynamics presented here is performed by extracting in a first step the vibrating vocal fold edges from the HSV stream (33) and condensing the extracted vocal fold dynamics into PVGs (27,28). Former studies already showed that PVGs are principally suitable for detecting even slight inter-and intraindividual changes of vocal fold dynamics (29,35).…”

Section: Discussionmentioning

confidence: 99%

“…A, PVGs shown from the healthy subject H9 (top) and the subject C4 with a T1 carcinoma on the left vocal fold (bottom). B, a wavelet-based analysis was applied (29) to extract the recurring geometric PVG pattern for left and right vocal fold separately. C, the geometric contour patterns can be quantified adequately with merely three coefficients for each vocal fold side obtained from principal component analysis as described previously (29).…”

Section: Analysis Proceduresmentioning

confidence: 99%

“…B, a wavelet-based analysis was applied (29) to extract the recurring geometric PVG pattern for left and right vocal fold separately. C, the geometric contour patterns can be quantified adequately with merely three coefficients for each vocal fold side obtained from principal component analysis as described previously (29). The Euclidian distance between the eigenvalues of the left and right side provides a measure of lateral asymmetry of oscillation modes, which is considerably increased for the subject C4.…”

Section: Analysis Proceduresmentioning

confidence: 99%

“…For this purpose, the geometric shape of the PVG structures are extracted and quantitatively described using image processing and machine-learning approaches. Voigt and colleagues demonstrated the applicability of PVGs for the discrimination of healthy and paralytic larynges (29), as well as healthy and functional voice disorders (30). In this first approach, a high number of more than 300 features were extracted from the PVG that are, however, rather difficult to interpret in the clinical context.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Noninvasive Procedure for Early-Stage Discrimination of Malignant and Precancerous Vocal Fold Lesions Based on Laryngeal Dynamics Analysis

et al. 2015

Self Cite

View full text Add to dashboard Cite

About two thirds of laryngeal cancers originate at the vocal cords. Early-stage detection of malignant vocal fold alterations, including a discrimination of premalignant lesions, represents a major challenge in laryngology as precancerous vocal fold lesions and small carcinomas are difficult to distinguish by means of regular endoscopy only. We report a procedure to discriminate between malignant and precancerous lesions by measuring the characteristics of vocal fold dynamics by means of a computerized analysis of laryngeal high-speed videos. Ten patients with squamous cell T1a carcinoma, ten with precancerous lesions with hyperkeratosis, and ten subjects without laryngeal disease underwent high-speed laryngoscopy yielding 4,000 images per second. By means of wavelet-based phonovibrographic analysis, a set of three clinically meaningful vibratory measures was extracted from the videos comprising a total number of 15,000 video frames. Statistical analysis (ANOVA with post hoc two-sided t tests, P < 0.05) revealed that vocal fold dynamics is significantly affected in the presence of precancerous lesions and T1a carcinoma. On the basis of the three measures, a discriminating pattern was extracted using a support vector machine-learning algorithm performing an individual classification in respect to the different clinical groups. By applying a leave-one-out cross-validation strategy, we could show that the proposed measures discriminate with a very high performance between precancerous lesions and T1a carcinoma (sensitivity, 100%; specificity, 100%). Although a large-scale study will be necessary to confirm clinical significance, the set of vibratory measures derived in this study may be applicable to improve the accuracy and reliability of noninvasive diagnostics of vocal fold lesions. Cancer Res; 75(1); 31-39. Ó2014 AACR.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Analysis Proceduresmentioning

confidence: 99%

Section: Analysis Proceduresmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Noninvasive Procedure for Early-Stage Discrimination of Malignant and Precancerous Vocal Fold Lesions Based on Laryngeal Dynamics Analysis

et al. 2015

Self Cite

View full text Add to dashboard Cite

show abstract

“…It has been proposed as a useful diagnostic tool for vocal fold paresis [33] and a method for automatic diagnosis of vocal fold paresis has been developed by use of image-analysis technology based on high-speed imaging [34]. Although high-speed imaging offers many exciting possibilities in the evaluation of dysphonic patients, currently the expense of the equipment prevents widespread use in everyday practice, and its clinical utility in vocal fold motion impairment remains to be seen.…”

Section: Videostroboscopy and High-speed Imagingmentioning

confidence: 99%

Evaluation of Unilateral Vocal Fold Immobility

Kupfer

Meyer

2014

Curr Otorhinolaryngol Rep

View full text Add to dashboard Cite

Unilateral vocal fold immobility (UFVI) is a highly variable clinical entity that may be neurogenic or mechanical in origin. Patients with UVFI have varying degrees of voice, swallowing, and airway disturbance. The patient should be carefully evaluated, including thorough history, head, neck, and neurologic examination, and laryngoscopy, to determine the etiology of UFVI and the current level of laryngeal function. If the etiology cannot be determined, cross sectional imaging of the skull base through the mediastinum is recommended to evaluate the underlying cause. Laryngeal electromyography is most useful for predicting poor functional recovery and may affect the decision to proceed with early definitive surgical management. Formal swallowing testing is indicated for patients with dysphagia to identify aspiration.

show abstract

Spatiotemporal analysis of vocal fold vibrations between children and adults

2012

Self Cite

View full text Add to dashboard Cite

Objectives/Hypothesis Aim of the study is to quantify differences in spatiotemporal features of vibratory motion in typically developing pre-pubertal children and adults with use of high speed digital imaging. Study Design Prospective case-control study. Methods Vocal fold oscillations of 31 children and 35 adults were analysed. Endoscopic high-speed imaging was performed during sustained phonation at typical pitch and loudness. Quantitative technique of Phonovibrogram was used to compute spatiotemporal features. Spatial features are represented by opening and closing angles along the anterior and posterior parts of the vocal folds, as well as by left-right symmetry ratio. Temporal features are represented by the cycle-to-cycle variability of the spatial features. Group differences (adult females, adult males, and children) were statistically investigated. Results Statistical differences were more pronounced in the temporal behavior compared to the spatial behavior. Children demonstrated greater cycle-to-cycle variability in oscillations compared to adults. Most differences between children and adults were found for temporal characteristics along the anterior parts during closing phase. The spatiotemporal features differed more between children and males than between children and females. Both adults and children showed equally high left-right symmetry. Conclusions Results suggest a more unstable phonation in children than in adults yielding increased perturbation in periodicity. Children demonstrated longer phase delay in the anterior/posterior and medio-lateral parts during the opening phase compared to adults. The data presented may provide the bases for differentiating normal vibratory characteristics from the disordered in the pediatric population and eventually assist in aiding the clinical utility of high speed imaging.

show abstract

Automatic diagnosis of vocal fold paresis by employing phonovibrogram features and machine learning methods

Cited by 41 publications

References 35 publications

A Noninvasive Procedure for Early-Stage Discrimination of Malignant and Precancerous Vocal Fold Lesions Based on Laryngeal Dynamics Analysis

A Noninvasive Procedure for Early-Stage Discrimination of Malignant and Precancerous Vocal Fold Lesions Based on Laryngeal Dynamics Analysis

Evaluation of Unilateral Vocal Fold Immobility

Spatiotemporal analysis of vocal fold vibrations between children and adults

Contact Info

Product

Resources

About