Laryngeal Image Processing of Vocal Folds Motion

Abstract

This review provides a comprehensive compilation, from a digital image processing point of view of the most important techniques currently developed to characterize and quantify the vibration behaviour of the vocal folds, along with a detailed description of the laryngeal image modalities currently used in the clinic. The review presents an overview of the most significant glottal-gap segmentation and facilitative playbacks techniques used in the literature for the mentioned purpose, and shows the drawbacks and challenges that still remain unsolved to develop robust vocal folds vibration function analysis tools based on digital image processing.

Ses Telleri Görüntülerinde Otomatik Piksel Tabanlı Sınıflandırma için Performans Ölçütlerinin İncelenmesi

“…[8,9] Genellikle HSV görüntüleri incelenirken ilk aşamada ilgi bölgesi (İB) belirlenir, ardından İB içerisinde bölütleme işlemi gerçekleştirilir. [7] İB belirlenmesinde literatürde ilk başvurulan yöntem manuel yapılması, el ile seçilmesidir. [10][11][12] Diğer bir yöntem ise başlangıç bölgesinin manuel olarak seçilip, sonraki analizler için bölgenin otomatik adapte edilmesidir.…”

“…[4][5][6] Bu görüntüler bir hastanın ses tellerinin titreşiminin bir periyodunun yakalanmasını ve ses telleri titreşimlerinin ölçümünü sağlar. [7] Ses telleri normal konuşma esnasında 70-400 Hz frekans aralığında titreşirler. Klinik ses analizinde kullanılan HSV sistemleri bir periyot içerisinde ses tellerinin frekansına göre her bir periyotta en az 10 kare görüntüleme yapabilir ve özellikle düşük frekansta olan erkek ses tellerinin bir periyodunu detaylı yakalayabilmek için yeterli hıza sahiptir.…”

A Deep Learning Enhanced Novel Software Tool for Laryngeal Dynamics Analysis

“…with recording frame rates from 4 up to 20 kHz (Echternach et al, 2013;Inwald et al, 2011), enables the detailed visualization and analysis of all oscillation cycles and transient processes, such as phonation onset , aperiodic oscillation (Deliyski et al, 2015), singing (Echternach et al, 2013), and speech production (Yousef et al, 2020). The potential and usefulness of HSV has been shown in numerous studies over the last two decades and has been discussed in several overviews (Andrade-Miranda et al, 2020;Deliyski & Hillman, 2010;Deliyski et al, 2008;Döellinger, 2009;Woo, 2014Woo, , 2020Ziethe et al, 2011).…”

“…A common way to quantify the vocal fold oscillation in HSV is analyzing the changing glottal area over time (Deliyski et al, 2008). Several approaches have been described in the literature to segment the glottal area (see Andrade-Miranda et al, 2020, for a review). Out of many, the threshold-based region growing algorithm has been established as a reliable way to semiautomatically segment the glottal area from endoscopic images (see Figure 1, Segmentation; Lohscheller et al, 2007;Wittenberg et al, 1995).…”

“…However, the segmentation of the glottal area has been shown to be a difficult task requiring varying degrees of user interaction (Andrade- Miranda et al, 2020;Andrade-Miranda & Godino-Llorente, 2017;Gloger et al, 2015;Huang et al, 2014;Lohscheller et al, 2007;Mendez-Zorrilla & Garcia-Zapirain, 2015;Naghibolhosseini et al, 2018;Osma-Ruiz et al, 2008;Shi et al, 2015). These algorithms were also only validated on very limited data sets.…”