A Deep‐Learning Model for Multi‐class Audio Classification of Vocal Fold Pathologies in Office Stroboscopy
Fuente:
Wiley Open Access
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Artículo Open Access |
| Published: |
Wiley
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1867006451641221120 |
|---|---|
| author | Yeo E. Kim Maria Dobko Haomiao Li Tianlan Shao Preethi Periyakoil Courtney Tipton Christine Colasacco Aisha Serpedin Olivier Elemento Mert Sabuncu Michael Pitman Lucian Sulica Anaïs Rameau |
| author_facet | Yeo E. Kim Maria Dobko Haomiao Li Tianlan Shao Preethi Periyakoil Courtney Tipton Christine Colasacco Aisha Serpedin Olivier Elemento Mert Sabuncu Michael Pitman Lucian Sulica Anaïs Rameau Yeo E. Kim Maria Dobko Haomiao Li Tianlan Shao Preethi Periyakoil Courtney Tipton Christine Colasacco Aisha Serpedin Olivier Elemento Mert Sabuncu Michael Pitman Lucian Sulica Anaïs Rameau |
| collection | Wiley Open Access |
| contents | A Deep‐Learning Model for Multi‐class Audio Classification of Vocal Fold Pathologies in Office Stroboscopy Yeo E. Kim Maria Dobko Haomiao Li Tianlan Shao Preethi Periyakoil Courtney Tipton Christine Colasacco Aisha Serpedin Olivier Elemento Mert Sabuncu Michael Pitman Lucian Sulica Anaïs Rameau The Laryngoscope Objective To develop and validate a deep‐learning classifier trained on voice data extracted from videolaryngostroboscopy recordings, differentiating between three different vocal fold (VF) states: healthy (HVF), unilateral paralysis (UVFP), and VF lesions, including benign and malignant pathologies. Methods Patients with UVFP ( n = 105), VF lesions ( n = 63), and HVF ( n = 41) were retrospectively identified. Voice samples were extracted from stroboscopic videos (Pentax Laryngeal Strobe Model 9400), including sustained /i/ phonation, pitch glide, and /i/ sniff task. Extracted audio files were converted into Mel‐spectrograms. Voice samples were independently divided into training (80%), validation (10%), and test (10%) by patient. Pretrained ResNet18 models were trained to classify (1) HVF and pathological VF (lesions and UVFP), and (2) HVF, UVFP, and VF lesions. Both classifiers were further validated on an external dataset consisting of 12 UVFP, 13 VF lesions, and 15 HVF patients. Model performances were evaluated by accuracy and F1‐score. Results When evaluated on a hold‐out test set, the binary classifier demonstrated stronger performance compared to the multi‐class classifier (accuracy 83% vs. 40%; F1‐score 0.90 vs. 0.36). When evaluated on an external dataset, the binary classifier achieved an accuracy of 63% and F1‐score of 0.48, compared to 35% and 0.25 for the multi‐class classifier. Conclusions Deep‐learning classifiers differentiating HVF, UVFP, and VF lesions were developed using voice data from stroboscopic videos. Although healthy and pathological voice were differentiated with moderate accuracy, multi‐class classification lowered model performance. The model performed poorly on an external dataset. Voice captured in stroboscopic videos may have limited diagnostic value, though further studies are needed. Level of Evidence 4 Laryngoscope , 135:2428–2436, 2025 10.1002/lary.32036 http://onlinelibrary.wiley.com/termsAndConditions#vor |
| doi_str_mv | 10.1002/lary.32036 |
| format | Artículo Open Access |
| id | wiley_oa_10_1002_lary_32036 |
| institution | Wiley Open Access |
| license_str_mv | http://onlinelibrary.wiley.com/termsAndConditions#vor |
| publishDate | 2025 |
| publisher | Wiley |
| record_format | wiley_oa |
| spellingShingle | A Deep‐Learning Model for Multi‐class Audio Classification of Vocal Fold Pathologies in Office Stroboscopy Yeo E. Kim Maria Dobko Haomiao Li Tianlan Shao Preethi Periyakoil Courtney Tipton Christine Colasacco Aisha Serpedin Olivier Elemento Mert Sabuncu Michael Pitman Lucian Sulica Anaïs Rameau The Laryngoscope A Deep‐Learning Model for Multi‐class Audio Classification of Vocal Fold Pathologies in Office Stroboscopy Yeo E. Kim Maria Dobko Haomiao Li Tianlan Shao Preethi Periyakoil Courtney Tipton Christine Colasacco Aisha Serpedin Olivier Elemento Mert Sabuncu Michael Pitman Lucian Sulica Anaïs Rameau The Laryngoscope Objective To develop and validate a deep‐learning classifier trained on voice data extracted from videolaryngostroboscopy recordings, differentiating between three different vocal fold (VF) states: healthy (HVF), unilateral paralysis (UVFP), and VF lesions, including benign and malignant pathologies. Methods Patients with UVFP ( n = 105), VF lesions ( n = 63), and HVF ( n = 41) were retrospectively identified. Voice samples were extracted from stroboscopic videos (Pentax Laryngeal Strobe Model 9400), including sustained /i/ phonation, pitch glide, and /i/ sniff task. Extracted audio files were converted into Mel‐spectrograms. Voice samples were independently divided into training (80%), validation (10%), and test (10%) by patient. Pretrained ResNet18 models were trained to classify (1) HVF and pathological VF (lesions and UVFP), and (2) HVF, UVFP, and VF lesions. Both classifiers were further validated on an external dataset consisting of 12 UVFP, 13 VF lesions, and 15 HVF patients. Model performances were evaluated by accuracy and F1‐score. Results When evaluated on a hold‐out test set, the binary classifier demonstrated stronger performance compared to the multi‐class classifier (accuracy 83% vs. 40%; F1‐score 0.90 vs. 0.36). When evaluated on an external dataset, the binary classifier achieved an accuracy of 63% and F1‐score of 0.48, compared to 35% and 0.25 for the multi‐class classifier. Conclusions Deep‐learning classifiers differentiating HVF, UVFP, and VF lesions were developed using voice data from stroboscopic videos. Although healthy and pathological voice were differentiated with moderate accuracy, multi‐class classification lowered model performance. The model performed poorly on an external dataset. Voice captured in stroboscopic videos may have limited diagnostic value, though further studies are needed. Level of Evidence 4 Laryngoscope , 135:2428–2436, 2025 10.1002/lary.32036 http://onlinelibrary.wiley.com/termsAndConditions#vor |
| title | A Deep‐Learning Model for Multi‐class Audio Classification of Vocal Fold Pathologies in Office Stroboscopy |
| topic | The Laryngoscope |
| url | https://onlinelibrary.wiley.com/doi/10.1002/lary.32036 |