Segmentation of Glottal Images from High-Speed Videoendoscopy Optimized by Synchronous Acoustic Recordings
Laryngeal high-speed videoendoscopy (LHSV) is an imaging technique offering novel visualization quality of the vibratory activity of the vocal folds. However, in most image analysis methods, the interaction of the medical personnel and access to ground truth annotations are required to achieve accur...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/5/1751 |
| _version_ | 1797473778043715584 |
|---|---|
| author | Bartosz Kopczynski Ewa Niebudek-Bogusz Wioletta Pietruszewska Pawel Strumillo |
| author_facet | Bartosz Kopczynski Ewa Niebudek-Bogusz Wioletta Pietruszewska Pawel Strumillo |
| author_sort | Bartosz Kopczynski |
| collection | DOAJ |
| description | Laryngeal high-speed videoendoscopy (LHSV) is an imaging technique offering novel visualization quality of the vibratory activity of the vocal folds. However, in most image analysis methods, the interaction of the medical personnel and access to ground truth annotations are required to achieve accurate detection of vocal folds edges. In our fully automatic method, we combine video and acoustic data that are synchronously recorded during the laryngeal endoscopy. We show that the image segmentation algorithm of the glottal area can be optimized by matching the Fourier spectra of the pre-processed video and the spectra of the acoustic recording during the phonation of sustained vowel /i:/. We verify our method on a set of LHSV recordings taken from subjects with normophonic voice and patients with voice disorders due to glottal insufficiency. We show that the computed geometric indices of the glottal area make it possible to discriminate between normal and pathologic voices. The median of the Open Quotient and Minimal Relative Glottal Area values for healthy subjects were 0.69 and 0.06, respectively, while for dysphonic subjects were 1 and 0.35, respectively. We also validate these results using independent phoniatrician experts. |
| first_indexed | 2024-03-09T20:22:15Z |
| format | Article |
| id | doaj.art-4e99d2eab4d74bcf86785d340823f1c2 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T20:22:15Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-4e99d2eab4d74bcf86785d340823f1c22023-11-23T23:45:34ZengMDPI AGSensors1424-82202022-02-01225175110.3390/s22051751Segmentation of Glottal Images from High-Speed Videoendoscopy Optimized by Synchronous Acoustic RecordingsBartosz Kopczynski0Ewa Niebudek-Bogusz1Wioletta Pietruszewska2Pawel Strumillo3Institute of Electronics, Lodz University of Technology, 90-924 Lodz, PolandDepartment of Otolaryngology, Head and Neck Oncology, Medical University of Lodz, 90-001 Lodz, PolandDepartment of Otolaryngology, Head and Neck Oncology, Medical University of Lodz, 90-001 Lodz, PolandInstitute of Electronics, Lodz University of Technology, 90-924 Lodz, PolandLaryngeal high-speed videoendoscopy (LHSV) is an imaging technique offering novel visualization quality of the vibratory activity of the vocal folds. However, in most image analysis methods, the interaction of the medical personnel and access to ground truth annotations are required to achieve accurate detection of vocal folds edges. In our fully automatic method, we combine video and acoustic data that are synchronously recorded during the laryngeal endoscopy. We show that the image segmentation algorithm of the glottal area can be optimized by matching the Fourier spectra of the pre-processed video and the spectra of the acoustic recording during the phonation of sustained vowel /i:/. We verify our method on a set of LHSV recordings taken from subjects with normophonic voice and patients with voice disorders due to glottal insufficiency. We show that the computed geometric indices of the glottal area make it possible to discriminate between normal and pathologic voices. The median of the Open Quotient and Minimal Relative Glottal Area values for healthy subjects were 0.69 and 0.06, respectively, while for dysphonic subjects were 1 and 0.35, respectively. We also validate these results using independent phoniatrician experts.https://www.mdpi.com/1424-8220/22/5/1751vocal disorderslaryngeal high-speed videoimage segmentationacoustic recordings of voicesignal processingmultimodal sensing |
| spellingShingle | Bartosz Kopczynski Ewa Niebudek-Bogusz Wioletta Pietruszewska Pawel Strumillo Segmentation of Glottal Images from High-Speed Videoendoscopy Optimized by Synchronous Acoustic Recordings Sensors vocal disorders laryngeal high-speed video image segmentation acoustic recordings of voice signal processing multimodal sensing |
| title | Segmentation of Glottal Images from High-Speed Videoendoscopy Optimized by Synchronous Acoustic Recordings |
| title_full | Segmentation of Glottal Images from High-Speed Videoendoscopy Optimized by Synchronous Acoustic Recordings |
| title_fullStr | Segmentation of Glottal Images from High-Speed Videoendoscopy Optimized by Synchronous Acoustic Recordings |
| title_full_unstemmed | Segmentation of Glottal Images from High-Speed Videoendoscopy Optimized by Synchronous Acoustic Recordings |
| title_short | Segmentation of Glottal Images from High-Speed Videoendoscopy Optimized by Synchronous Acoustic Recordings |
| title_sort | segmentation of glottal images from high speed videoendoscopy optimized by synchronous acoustic recordings |
| topic | vocal disorders laryngeal high-speed video image segmentation acoustic recordings of voice signal processing multimodal sensing |
| url | https://www.mdpi.com/1424-8220/22/5/1751 |
| work_keys_str_mv | AT bartoszkopczynski segmentationofglottalimagesfromhighspeedvideoendoscopyoptimizedbysynchronousacousticrecordings AT ewaniebudekbogusz segmentationofglottalimagesfromhighspeedvideoendoscopyoptimizedbysynchronousacousticrecordings AT wiolettapietruszewska segmentationofglottalimagesfromhighspeedvideoendoscopyoptimizedbysynchronousacousticrecordings AT pawelstrumillo segmentationofglottalimagesfromhighspeedvideoendoscopyoptimizedbysynchronousacousticrecordings |