{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T17:40:08Z","timestamp":1786815608999,"version":"build-2736575974"},"reference-count":27,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.mdpi.com"],"crossmark-restriction":true},"short-container-title":["JCM"],"abstract":"<jats:p>Background\/Objectives: Video laryngoscopy is one of the primary methods used by otolaryngologists for detecting and classifying laryngeal lesions. However, the diagnostic process of these images largely relies on clinicians\u2019 visual inspection, which can lead to overlooked small structural changes, delayed diagnosis, and interpretation errors. Methods: AI-based approaches are becoming increasingly critical for accelerating early-stage diagnosis and improving reliability. This study proposes a hybrid Convolutional Neural Network (CNN) architecture that eliminates repetitive and clinically insignificant frames from videos, utilizing only meaningful key frames. Video data from healthy individuals, patients with vocal fold nodules, and those with vocal fold polyps were summarized using three different threshold values with the Structural Similarity Index Measure (SSIM). Results: The resulting key frames were then classified using a hybrid CNN. Experimental findings demonstrate that selecting an appropriate threshold can significantly reduce the model\u2019s memory usage and processing load while maintaining accuracy. In particular, a threshold value of 0.90 provided richer information content thanks to the selection of a wider variety of frames, resulting in the highest success rate. Fine-tuning the last 20 layers of the MobileNetV2 and Xception backbones, combined with the fusion of extracted features, yielded an overall classification accuracy of 98%. Conclusions: The proposed approach provides a mechanism that eliminates unnecessary data and prioritizes only critical information in video-based diagnostic processes, thus helping physicians accelerate diagnostic decisions and reduce memory requirements.<\/jats:p>","DOI":"10.3390\/jcm14196899","type":"journal-article","created":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T09:12:23Z","timestamp":1759223543000},"page":"6899","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Vocal Fold Disorders Classification and Optimization of a Custom Video Laryngoscopy Dataset Through Structural Similarity Index and a Deep Learning-Based Approach"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5659-3499","authenticated-orcid":false,"given":"Elif","family":"Emre","sequence":"first","affiliation":[{"name":"Department of Anatomy, Faculty of Medicine, F\u0131rat University, Elaz\u0131\u011f 23119, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0710-2280","authenticated-orcid":false,"given":"Dilber","family":"Cetintas","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Malatya Turgut Ozal University, Malatya 44210, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1866-4721","authenticated-orcid":false,"given":"Muhammed","family":"Yildirim","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Malatya Turgut Ozal University, Malatya 44210, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7906-9902","authenticated-orcid":false,"given":"Sadettin","family":"Emre","sequence":"additional","affiliation":[{"name":"Department of Otorhinolaryngology, Private Elaz\u0131\u011f Medikal Hospital, Elaz\u0131\u011f 23100, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1971","DOI":"10.1109\/TPAMI.2008.29","article-title":"Nonchronological video synopsis and indexing","volume":"30","author":"Pritch","year":"2008","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_2","first-page":"808","article-title":"Visual documentation of the Larynx","volume":"1\u20133","author":"Samlan","year":"2020","journal-title":"Cummings Otolaryngol. Head Neck Surg."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"460","DOI":"10.1002\/lio2.754","article-title":"Automatic classification of informative laryngoscopic images using deep learning","volume":"7","author":"Yao","year":"2022","journal-title":"Laryngoscope Investig. Otolaryngol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2794","DOI":"10.1007\/s10278-024-01068-z","article-title":"Improving Laryngoscopy Image Analysis Through Integration of Global Information and Local Features in VoFoCD Dataset","volume":"37","author":"Dao","year":"2024","journal-title":"J. Imaging Inform. Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"761.e1","DOI":"10.1016\/j.jvoice.2015.09.017","article-title":"Voice disorders: Etiology and diagnosis","volume":"30","author":"Martins","year":"2016","journal-title":"J. Voice"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"609","DOI":"10.1016\/j.jvoice.2017.08.023","article-title":"Nonmedical treatments of vocal fold nodules: A systematic review","volume":"32","author":"Mansuri","year":"2018","journal-title":"J. Voice"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Barsties v Latoszek, B., Watts, C.R., Hetjens, S., and Neumann, K. (2023). The efficacy of different voice treatments for vocal fold polyps: A systematic review and meta-analysis. J. Clin. Med., 12.","DOI":"10.3390\/jcm12103451"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"3-es","DOI":"10.1145\/1198302.1198305","article-title":"Video abstraction: A systematic review and classification","volume":"3","author":"Truong","year":"2007","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl. (TOMM)"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Xu, Z.H., Fan, D.G., Huang, J.Q., Wang, J.W., Wang, Y., and Li, Y.Z. (2023). Computer-aided diagnosis of laryngeal cancer based on deep learning with laryngoscopic images. Diagnostics, 13.","DOI":"10.3390\/diagnostics13243669"},{"key":"ref_10","first-page":"6","article-title":"Automatic anatomical site recognition of laryngoscopic images using convolutional neural network","volume":"37","author":"Wang","year":"2023","journal-title":"Lin Chuang Er Bi Yan Hou Tou Jing Wai Ke Za Zhi = J. Clin. Otorhinolaryngol. Head Neck Surg."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"103800","DOI":"10.1016\/j.amjoto.2023.103800","article-title":"Support of deep learning to classify vocal fold images in flexible laryngoscopy","volume":"44","author":"Tran","year":"2023","journal-title":"Am. J. Otolaryngol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.compbiomed.2015.02.001","article-title":"Classification of laryngeal disorders based on shape and vascular defects of vocal folds","volume":"62","author":"Turkmen","year":"2015","journal-title":"Comput. Biol. Med."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2558","DOI":"10.1002\/lary.29595","article-title":"Diagnostic accuracies of laryngeal diseases using a convolutional neural network-based image classification system","volume":"131","author":"Cho","year":"2021","journal-title":"Laryngoscope"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1099","DOI":"10.1002\/ohn.591","article-title":"Vocal cord leukoplakia classification using Siamese network under small samples of white light endoscopy images","volume":"170","author":"You","year":"2024","journal-title":"Otolaryngol.\u2013Head Neck Surg."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"115306","DOI":"10.1109\/ACCESS.2023.3324880","article-title":"Laryngeal cancer detection and classification using aquila optimization algorithm with deep learning on throat region images","volume":"11","author":"Alrowais","year":"2023","journal-title":"IEEE Access"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1007\/s10916-019-1481-4","article-title":"A convolutional neural network for real time classification, identification, and labelling of vocal cord and tracheal using laryngoscopy and bronchoscopy video","volume":"44","author":"Matava","year":"2020","journal-title":"J. Med. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Kim, G.H., Hwang, Y.J., Lee, H., Sung, E.S., and Nam, K.W. (2023). Convolutional neural network-based vocal cord tumor classification technique for home-based self-prescreening purpose. BioMed. Eng. OnLine, 22.","DOI":"10.1186\/s12938-023-01139-2"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Sandhu, S.K., and Agarwal, A. (2015, January 25\u201327). Summarizing Videos by Key frame extraction using SSIM and other Visual Features. Proceedings of the Sixth International Conference on Computer and Communication Technology 2015, Allahabad, India.","DOI":"10.1145\/2818567.2818607"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Liu, T., Meng, Q., Vlontzos, A., Tan, J., Rueckert, D., and Kainz, B. (2020, January 4\u20138). Ultrasound video summarization using deep reinforcement learning. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Lima, Peru.","DOI":"10.1007\/978-3-030-59716-0_46"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1495","DOI":"10.1186\/s40064-016-3171-8","article-title":"Visual saliency models for summarization of diagnostic hysteroscopy videos in healthcare systems","volume":"5","author":"Muhammad","year":"2016","journal-title":"SpringerPlus"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"24513","DOI":"10.1007\/s00521-021-06322-x","article-title":"A novel keyframe extraction method for video classification using deep neural networks","volume":"35","author":"Gan","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2018, January 18\u201323). Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Zoph, B., Vasudevan, V., Shlens, J., and Le, Q.V. (2018, January 18\u201323). Learning transferable architectures for scalable image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 22\u201325). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017, January 22\u201325). Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s11760-025-03915-0","article-title":"Efficient monkeypox detection using hybrid lightweight CNN architectures and optimized SVM with grid search on imbalanced data","volume":"19","year":"2025","journal-title":"Signal Image Video Process."}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/14\/19\/6899\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T09:49:28Z","timestamp":1759225768000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/14\/19\/6899"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,29]]},"references-count":27,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["jcm14196899"],"URL":"https:\/\/doi.org\/10.3390\/jcm14196899","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,29]]}}}