Interpretable Computer Vision to Detect and Classify Structural Laryngeal Lesions in Digital Flexible Laryngoscopic Images
Open accessAbstract
Objective: To localize structural laryngeal lesions within digital flexible laryngoscopic images and to classify them as benign or suspicious for malignancy using state‐of‐the‐art computer vision detection models. Study Design: Cross‐sectional diagnostic study Setting: Tertiary care voice clinic Methods: Digital stroboscopic videos, demographic and clinical data were collected from patients evaluated for a structural laryngeal lesion. Laryngoscopic images were extracted from videos and manually labeled with bounding boxes encompassing the lesion. Four detection models were employed to simultaneously localize and classify structural laryngeal lesions in laryngoscopic images. Classification accuracy, intersection over union (IoU) and mean average precision (mAP) were evaluated as measures of classification, localization, and overall performance, respectively. Results: In total, 8,172 images from 147 patients were included in the laryngeal image dataset. Classification accuracy was 88.5 for individual laryngeal images and increased to 92.0 when all images belonging to the same sequence (video) were considered. Mean average precision across all four detection models was 50.1 using an IoU threshold of 0.5 to determine successful localization. Conclusion: Results of this study showed that deep neural network‐based detection models trained using a labeled dataset of digital laryngeal images have the potential to classify structural laryngeal lesions as benign or suspicious for malignancy and to localize them within an image. This approach provides valuable insight into which part of the image was used by the model to determine a diagnosis, allowing clinicians to independently evaluate models' predictions.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
ResNet-based encoders offered only incremental gains in multiclass scenarios.
“In their comparative analysis, ResNet-based encoders offered only incremental gains in multiclass scenarios [48,62].”
From Diagnostic Accuracy of Artificial Intelligence in Laryngeal Disorders: An Integrative Review (2026) · cites this paper as [62]
The Experimental Settings state that every detection model used the same ResNet-50 backbone, so the study did not compare ResNet-based encoders to assess incremental gains. The Conclusions describe classification as benign or suspicious for malignancy, not a multiclass scenario. No page numbers are available in our copy. (LLM, conf=0.83)
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredBur et al. reported ~92% sequence-level accuracy for benign versus malignant lesion classification using a ResNet-50 backbone on flexible laryngoscopic images.
“Bur et al. reported ~92% sequence-level accuracy for benign versus malignant lesion classification using a ResNet-50 backbone on flexible laryngoscopic images [62].”
From Diagnostic Accuracy of Artificial Intelligence in Laryngeal Disorders: An Integrative Review (2026) · cites this paper as [62]
The Results report 92.0% mean sequence-level accuracy, and Experimental Settings state that all detection models used a ResNet-50 backbone. However, the paper classifies lesions as benign or “suspicious for malignancy,” not definitively benign or malignant; the claim omits that diagnostic qualifier. (LLM, conf=0.87)
Experimental — accuracy not yet measuredFeature-based shallow models suit binary screening and broad category recognition, whereas deep convolutional and self-supervised pipelines are justified for image-based diagnosis and fine-grained multi-pathology classification at the cost of reduced transparency.
“feature-based shallow models suit binary screening and broad category recognition [39,40,48], whereas deep convolutional and self-supervised pipelines are justified for image-based diagnosis and fine-grained multi-pathology classification at the cost of reduced transparency [27,62,63].”
From Diagnostic Accuracy of Artificial Intelligence in Laryngeal Disorders: An Integrative Review (2026) · cites this paper as [62]
Split into 2 atoms — 0 confirmed, 1 partially supported, 0 disputed, 0 misattributed, 1 unverifiable. Expand the claim to see per-atom verdicts.
Experimental — accuracy not yet measuredLee and Lee demonstrated on the SVD that SVMs trained on high-dimensional ComParE or OpenSMILE features-optionally enriched with glottal source measures-provided the best unweighted recall (86.4%) for organic versus control classification.
“Lee and Lee demonstrated on the SVD that SVMs trained on high-dimensional ComParE or OpenSMILE features—optionally enriched with glottal source measures—provided the best unweighted recall (86.4%) for organic versus control classification.”
From Diagnostic Accuracy of Artificial Intelligence in Laryngeal Disorders: An Integrative Review (2026) · cites this paper as [62]
The Model training and Experimental Settings sections describe object-detection models trained on laryngoscopic images, not SVMs trained on voice features. Searches for Lee and Lee, the SVD, ComParE/OpenSMILE, and 86.4% unweighted recall found no passage addressing the claimed result. (LLM, conf=0.78)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · see citing works
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460 · see citing works
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · see citing works
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939 · see citing works
The REDCap consortium: building an international community of software platform partners
Harris, P. A., Taylor, R., Minor, B. L., Elliott, V., Fernandez, M., O'Neal, L., McLeod, L., Delacqua, G., Delacqua, F., Kirby, J., et al. (2019) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2019.103208 · Cited by 24,013 · see citing works
The pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599 · see citing works
Universal Adversarial Perturbations
Moosavi-Dezfooli, S.-M., Fawzi, A., Fawzi, O., & Frossard, P. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.17 · Cited by 2,680 · see citing works
Zhang, S., Chi, C., Yao, Y., Lei, Z., & Li, S. Z. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00978 · Cited by 2,531 · see citing works
VarifocalNet: An IoU-aware Dense Object Detector
Zhang, H., Wang, Y., Dayoub, F., & Sünderhauf, N. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00841 · Cited by 1,252 · see citing works
Probabilistic Anchor Assignment with IoU Prediction for Object Detection
Kim, K., & Lee, H. S. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58595-2_22 · Cited by 529 · see citing works
Xiang, L., Wang, W., Hu, X., Li, J., Tang, J., & Yang, J. J. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01146 · Cited by 476 · see citing works
Carter, S., Armstrong, Z., Schubert, L., Johnson, I., & Olah, C. (2019) · Distill · doi:10.23915/distill.00015 · Cited by 147 · see citing works
Automatic Recognition of Laryngoscopic Images Using a Deep‐Learning Technique
Ren, J., Jing, X., Wang, J., Ren, X., Yang, X., Yang, Q., Ma, L., Sun, Y., Xu, W. H., Yang, N., et al. (2020) · The Laryngoscope · doi:10.1002/lary.28539 · Cited by 135 · see citing works
Applications of Artificial Intelligence to Office Laryngoscopy: A Scoping Review
Yao, P., Usman, M., Chen, Y. H., German, A., Andreadis, K., Mages, K. C., & Rameau, A. (2021) · The Laryngoscope · doi:10.1002/lary.29886 · Cited by 46 · see citing works
Learning curve for competency in flexible laryngoscopy
Laeeq, K., Pandian, V., Skinner, M. L., et al. (2010) · The Laryngoscope · doi:10.1002/lary.21063 · Cited by 45 · see citing works
Artificial Intelligence in Laryngeal Endoscopy: Systematic Review and Meta-Analysis
Żurek, M., Rzepakowska, A., Jasak, K., & Niemczyk, K. (2022) · Journal of Clinical Medicine · doi:10.3390/jcm11102752 · Cited by 41 · see citing works
Harnessing the Power of Artificial Intelligence in Otolaryngology and the Communication Sciences
Wilson, B. S., Tucci, D. L., Moses, D. A., Chang, E. F., Young, N. M., Zeng, F., Lesica, N. A., Bur, A. M., Kavookjian, H. L., Mussatto, C. C., et al. (2022) · Journal of the Association for Research in Otolaryngology · doi:10.1007/s10162-022-00846-2 · Cited by 36 · see citing works
Self-citationA “Medical Mission” at Home: The Needs of Rural America in Terms of Otolaryngology Care
Winters, R. D., Pou, A. M., & Friedlander, P. L. (2010) · The Journal of Rural Health · doi:10.1111/j.1748-0361.2010.00343.x · Cited by 32 · see citing works
Time to Competency, Reliability of Flexible Transnasal Laryngoscopy by Training Level
Brook, C. D., Platt, M. P., Russell, K., et al. (2015) · Otolaryngology · doi:10.1177/0194599815572792 · Cited by 14 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Diagnostic Accuracy of Artificial Intelligence in Laryngeal Disorders: An Integrative Review
Mairesse, S., Maniaci, A., Briganti, G., & Lechien, J. R. (2026) · Journal of Personalized Medicine · doi:10.3390/jpm16060301 · Cited by 1 · see citing works
“Bur et al. reported ~92% sequence-level accuracy for benign versus malignant lesion classification using a ResNet-50 backbone on flexible laryngoscopic images [62].”
- Authors
- Bur, A. M., Zhang, T., Chen, X., Kavookjian, H., Kraft, S., Karadaghy, O., Farrokhian, N., Mussatto, C., Penn, J., & Wang, G.
- Affiliations
- University of Kansas Medical Center (US)
- University of Kansas (US)
- Toronto Metropolitan University (CA)
- Corresponding author
- Bur, Andrés M.
- ORCID
- Venue
- Otolaryngology–Head and Neck Surgery
- Publisher
- Wiley
- Published
- 2023-06-23
- Volume
- 169
- Issue
- 6
- Pages
- 1564-1572
- ISSN
- 0161-6439 (ISSN-L)
- 0194-5998
- 1097-6817
- PMC
- PMC12374229
- OpenAlex
- W4381716346
- Cited by
- 25
- References
- 20
- Citations by year
- 2026: 5 · 2025: 8 · 2024: 9 · 2023: 3
- FWCI
- 2.36
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Otolaryngology (publishedVersion)
- PubMed (publishedVersion)
- Europe PMC (PubMed Central) (acceptedVersion)
- PubMed Central (acceptedVersion)
- Funders
- National Institutes of Health
- National Cancer Institute (R03CA253212)
- National Institute of General Medical Sciences (P20GM130423)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Physiology › Voice and Speech Disorders
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- flexible laryngoscopy, laryngeal cancer detection, benign versus malignant differentiation, lesion localization, deep learning object detection
- MeSH terms
- Computers, Cross-Sectional Studies, Humans, Laryngeal Neoplasms, Laryngoscopy, Larynx
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
