{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T16:35:46Z","timestamp":1791909346116,"version":"4.3.4"},"reference-count":41,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T00:00:00Z","timestamp":1776124800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Endoscopic airway imaging, used in endoscopy-guided airway management, enables geometry-based assessment of the airways. However, COCO-format datasets often include fragmented regions and geometrically inconsistent polygon annotations. Such inconsistencies may reduce reproducibility and spatial stability in deep learning-based image segmentation. This study proposes a systematic annotation quality-control (QC) workflow to improve dataset integrity before model training. Methods: The phantom subset of the Upper Airway Anatomical Landmark (UAAL) dataset containing 4526 polygon instances across 2746 frames (2267 training; 479 validation) was analyzed. The QC pipeline validated polygon structure, generated masks at native image resolution, and removed small noise-like instances using an area threshold. A YOLOv8-seg model was trained using (i) original annotations and (ii) QC-refined annotations. Performance was evaluated using precision, recall, mAP@0.5, mAP@0.5:0.95, and Dice similarity coefficient (DSC). Frame-level DSC values were compared using the Wilcoxon signed-rank test. Results: Annotation QC improved boundary consistency and reduced mask fragmentation. Training with QC-refined annotations increased box mAP@0.5:0.95 from 0.602 to 0.628 and mean DSC from 0.823 to 0.830 (p &lt; 0.05). A pilot evaluation on the UAAL clinical subset also showed improved performance, with Box mAP@0.5 increasing from 0.635 to 0.706 and Mask mAP@0.5 from 0.631 to 0.704. Conclusions: Annotation-level QC enhances segmentation robustness without modifying the network architecture. The proposed workflow improves the reproducibility of results in endoscopic image segmentation and may support more stable geometry-based airway analysis in deep learning applications.<\/jats:p>","DOI":"10.3390\/diagnostics16081160","type":"journal-article","created":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T14:24:58Z","timestamp":1776176698000},"page":"1160","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Reproducible COCO-Polygon Quality-Control Pipeline Improves Segmentation Stability in Endoscopic Airway Imaging"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0902-8717","authenticated-orcid":false,"given":"Medine","family":"Atmaca","sequence":"first","affiliation":[{"name":"Department of Mathematics, Graduate School of Natural and Applied Sciences, Gaziantep University, 27410 Gaziantep, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5547-1860","authenticated-orcid":false,"given":"Ilkay Sibel","family":"Kervanc\u0131","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Faculty of Engineering, Gaziantep University, 27410 Gaziantep, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6683-126X","authenticated-orcid":false,"given":"Necati","family":"Olgun","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Graduate School of Natural and Applied Sciences, Gaziantep University, 27410 Gaziantep, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"8","DOI":"10.4103\/bjoa.bjoa_228_22","article-title":"Prediction of difficult endotracheal intubation by different bedside tests: An observational study","volume":"7","author":"Kamal","year":"2023","journal-title":"Bali J. Anaesthesiol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1186\/s13063-023-07641-1","article-title":"Comparison of Video Laryngoscope, Video Stylet, and Flexible Videoscope for Transoral Endotracheal Intubation in Patients with Difficult Airways: A Randomized, Parallel-Group Study","volume":"24","author":"Zhang","year":"2023","journal-title":"Trials"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Wesemeyer, T., Jauer, M.L., and Deserno, T.M. (2021). Annotation quality vs. quantity for deep-learned medical image segmentation. Medical Imaging 2021: Imaging Informatics for Healthcare, Research, and Applications, SPIE. Proc. SPIE 11601.","DOI":"10.1117\/12.2582226"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1186\/s41747-023-00408-y","article-title":"Image annotation and curation in radiology: An overview for machine learning practitioners","volume":"8","author":"Galbusera","year":"2024","journal-title":"Eur. Radiol. Exp."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1109\/TMI.2016.2535302","article-title":"Convolutional neural networks for medical image analysis: Full training or fine tuning?","volume":"35","author":"Tajbakhsh","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_6","first-page":"101512","article-title":"Exploring the potential of artificial intelligence in airway management","volume":"59","author":"Maniaci","year":"2024","journal-title":"Trends Anaesth. Crit. Care"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"939","DOI":"10.1007\/s42044-025-00258-4","article-title":"The impact of backbone selection in YOLOv8 models on brain tumor localization","volume":"8","author":"Ranjbarzadeh","year":"2025","journal-title":"Iran J. Comput. Sci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"3293","DOI":"10.62347\/BIHI3707","article-title":"Improved YOLOv8-seg for laryngeal structure recognition in medical images","volume":"17","author":"Cui","year":"2025","journal-title":"Am. J. Transl. Res."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1021","DOI":"10.1007\/s00586-025-09619-w","article-title":"Semi-automated end-to-end quality control system for annotation data based on automated Cobb angle measurement","volume":"35","author":"Su","year":"2026","journal-title":"Eur. Spine J."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"107398","DOI":"10.1016\/j.cmpb.2023.107398","article-title":"PyMIC: A deep learning toolkit for annotation-efficient medical image segmentation","volume":"231","author":"Wang","year":"2023","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"15943","DOI":"10.1609\/aaai.v38i14.29525","article-title":"FedA3I: Annotation quality-aware aggregation for federated medical image segmentation against heterogeneous annotation noise","volume":"Volume 38","author":"Wu","year":"2024","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"109400","DOI":"10.1016\/j.patcog.2023.109400","article-title":"Learning from multiple annotators for medical image segmentation","volume":"138","author":"Zhang","year":"2023","journal-title":"Pattern Recognit."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2519","DOI":"10.1109\/TBME.2023.3252889","article-title":"Self-supervised learning for annotation-efficient biomedical image segmentation","volume":"70","author":"Rettenberger","year":"2023","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"102185","DOI":"10.1016\/j.media.2021.102185","article-title":"A positive\/unlabeled approach for the segmentation of medical sequences using point-wise supervision","volume":"73","author":"Lejeune","year":"2021","journal-title":"Med. Image Anal."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"5915","DOI":"10.1038\/s41467-021-26216-9","article-title":"Annotation-efficient deep learning for automatic medical image segmentation","volume":"12","author":"Wang","year":"2021","journal-title":"Nat. Commun."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Tang, C., Yang, Y., Qi, R., Zhou, K., Gong, Y., Heng, P.A., Hsiao, J.H., and Dou, Q. (2024). Weakly-supervised medical image segmentation with gaze annotations. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2024), Springer.","DOI":"10.1007\/978-3-031-72384-1_50"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Zhang, T., Yu, L., Hu, N., Lv, S., and Gu, S. (2020). Robust medical image segmentation from non-expert annotations with tri-network. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2020), Springer.","DOI":"10.1007\/978-3-030-59719-1_25"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1533","DOI":"10.1109\/TMI.2022.3141425","article-title":"Improving medical image classification with label noise using dual-uncertainty estimation","volume":"41","author":"Ju","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Multusch, M.M., Hansen, L., Heinrich, M.P., Berkel, L., Saalbach, A., Schulz, H., and Sieren, M.M. (2025). Impact of radiologist experience on AI annotation quality in chest radiographs: A comparative analysis. Diagnostics, 15.","DOI":"10.3390\/diagnostics15060777"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Pethmunee, T., Kansomkeat, S., Bhurayanontachai, P., and Intajag, S. (2025). Confident learning-based label correction for retinal image segmentation. Diagnostics, 15.","DOI":"10.3390\/diagnostics15141735"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2753","DOI":"10.1109\/ACCESS.2022.3140378","article-title":"Automated Annotator Variability Inspection for Biomedical Image Segmentation","volume":"10","author":"Schilling","year":"2022","journal-title":"IEEE Access"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1907","DOI":"10.1038\/s41597-025-06169-0","article-title":"Upper airway anatomical landmark dataset for automated bronchoscopy and intubation","volume":"12","author":"Hao","year":"2025","journal-title":"Sci. Data"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.diii.2019.05.008","article-title":"Annotated normal CT data of the abdomen for deep learning: Challenges and strategies for implementation","volume":"101","author":"Park","year":"2020","journal-title":"Diagn. Interv. Imaging"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1055\/s-0044-1800860","article-title":"A radiologist\u2019s perspective of medical annotations for AI programs: The entire journey from its planning to execution, challenges faced","volume":"35","author":"Rao","year":"2025","journal-title":"Indian J. Radiol. Imaging"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Ragab, M.G., Danyaro, K.U., Abdulkadir, S.J., Al-Selwi, S.M., Sumiea, E.H., and Alqushaibi, A. (2024). Brain tumor detection instance segmentation using YOLOv8 in medical imaging. Proceedings of the 2024 IEEE Asia-Pacific Conference on Applied Electromagnetics (APACE), Langkawi, Kedah, Malaysia, 21\u201323 December 2024, IEEE.","DOI":"10.1109\/APACE62360.2024.10877358"},{"key":"ref_26","unstructured":"Pangakis, N., Wolken, S., and Fasching, N. (2023). Automated Annotation with Generative AI Requires Validation. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., and Zitnick, C.L. (2014). Microsoft COCO: Common Objects in Context. Proceedings of the European Conference on Computer Vision (ECCV), Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Athanasiou, G., Arcos, J.L., and Cerquides, J. (2023). Enhancing Medical Image Segmentation: Ground Truth Optimization through Evaluating Uncertainty in Expert Annotations. Mathematics, 11.","DOI":"10.3390\/math11173771"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Gao, X., Ram, S., Philip, R.C., Rodr\u00edguez, J.J., Szep, J., Shao, S., Satam, P., Pacheco, J., and Hariri, S. (2022). Selecting post-processing schemes for accurate detection of small objects in low-resolution wide-area aerial imagery. Remote Sens., 14.","DOI":"10.3390\/rs14020255"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Celaya, A., Netherton, T., Schellingerhout, D., Chung, C., Riviere, B., and Fuentes, D. (2025). Pre- and Post-Treatment Glioma Segmentation with the Medical Imaging Segmentation Toolkit. arXiv.","DOI":"10.1007\/978-3-032-16365-3_3"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Ryu, J., Kwak, D., and Choi, S. (2025). YOLOv8 with Post-Processing for Small Object Detection Enhancement. Appl. Sci., 15.","DOI":"10.3390\/app15137275"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Ge, Y., Zhang, Q., Sun, Y., Shen, Y., and Wang, X. (2022). Grayscale medical image segmentation method based on 2D and 3D object detection with deep learning. BMC Med. Imaging, 22.","DOI":"10.1186\/s12880-022-00760-2"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Yushkevich, P.A., Gao, Y., and Gerig, G. (2016). ITK-SNAP: An interactive tool for semi-automatic segmentation of multi-modality biomedical images. Proceedings of the 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, FL, USA, 16\u201320 August 2016, IEEE.","DOI":"10.1109\/EMBC.2016.7591443"},{"key":"ref_34","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"47109","DOI":"10.1007\/s11042-023-14621-9","article-title":"Effective deep learning based segmentation and classification in wireless capsule endoscopy images","volume":"82","author":"Padmavathi","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"101759","DOI":"10.1016\/j.media.2020.101759","article-title":"Deep learning with noisy labels: Exploring techniques and remedies in medical image analysis","volume":"65","author":"Karimi","year":"2020","journal-title":"Med. Image Anal."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2240","DOI":"10.21037\/qims-23-1273","article-title":"A deep learning-based automatic image quality assessment method for respiratory phase on computed tomography chest images","volume":"14","author":"Su","year":"2024","journal-title":"Quant. Imaging Med. Surg."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1016\/j.media.2019.03.003","article-title":"CT Male Pelvic Organ Segmentation Using Fully Convolutional Networks with Boundary-Sensitive Representation","volume":"54","author":"Wang","year":"2019","journal-title":"Med. Image Anal."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Cergan, R., Taciuc, I.A., Dumitru, M., Vrinceanu, D., Manole, F., Sanda, N., and Marinescu, A.N. (2025). The Current Status of Virtual Autopsy Using Combined Imaging Modalities: A Scoping Review. J. Clin. Med., 14.","DOI":"10.3390\/jcm14030782"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Yang, L., Zhang, Y., Chen, J., Zhang, S., and Chen, D.Z. (2017). Suggestive annotation: A deep active learning framework for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Qu\u00e9bec City, QC, Canada, 11\u201313 September 2017, Springer.","DOI":"10.1007\/978-3-319-66179-7_46"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"5197","DOI":"10.1109\/TMI.2025.3589058","article-title":"Region uncertainty estimation for medical image segmentation with noisy labels","volume":"44","author":"Han","year":"2025","journal-title":"IEEE Trans. Med. Imaging"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/8\/1160\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T14:34:27Z","timestamp":1776177267000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/8\/1160"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,14]]},"references-count":41,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["diagnostics16081160"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16081160","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,14]]}}}