{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T23:52:07Z","timestamp":1783122727513,"version":"3.54.6"},"reference-count":64,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T00:00:00Z","timestamp":1716940800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T00:00:00Z","timestamp":1716940800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100010712","name":"Viet Nam National University Ho Chi Minh City","doi-asserted-by":"publisher","award":["DS2020-42-01"],"award-info":[{"award-number":["DS2020-42-01"]}],"id":[{"id":"10.13039\/501100010712","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015501","name":"Qu\u1ef9 \u0110\u1ed5i m\u1edbi s\u00e1ng t\u1ea1o Vingroup","doi-asserted-by":"publisher","award":["VINIF.2022.ThS.JVN.08"],"award-info":[{"award-number":["VINIF.2022.ThS.JVN.08"]}],"id":[{"id":"10.13039\/501100015501","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015501","name":"Qu\u1ef9 \u0110\u1ed5i m\u1edbi s\u00e1ng t\u1ea1o Vingroup","doi-asserted-by":"publisher","award":["VINIF.2022.ThS.JVN.10"],"award-info":[{"award-number":["VINIF.2022.ThS.JVN.10"]}],"id":[{"id":"10.13039\/501100015501","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Digit Imaging. Inform. med."],"DOI":"10.1007\/s10278-024-01068-z","type":"journal-article","created":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T15:01:57Z","timestamp":1716994917000},"page":"2794-2809","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Improving Laryngoscopy Image Analysis Through Integration of Global Information and Local Features in VoFoCD Dataset"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0109-1114","authenticated-orcid":false,"given":"Thao Thi Phuong","family":"Dao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2481-0724","authenticated-orcid":false,"given":"Tuan-Luc","family":"Huynh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3211-9076","authenticated-orcid":false,"given":"Minh-Khoi","family":"Pham","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7363-2610","authenticated-orcid":false,"given":"Trung-Nghia","family":"Le","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8834-8092","authenticated-orcid":false,"given":"Tan-Cong","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2523-8851","authenticated-orcid":false,"given":"Quang-Thuc","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8007-0348","authenticated-orcid":false,"given":"Bich Anh","family":"Tran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7065-1261","authenticated-orcid":false,"given":"Boi Ngoc","family":"Van","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2876-0920","authenticated-orcid":false,"given":"Chanh Cong","family":"Ha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3046-3041","authenticated-orcid":false,"given":"Minh-Triet","family":"Tran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,5,29]]},"reference":[{"key":"1068_CR1","unstructured":"Samlan RA, Kunduk M: Visual Documentation of the Larynx, vol 1, 7th edn., Elsevier, Philadelphia, chap 54, pp 808\u2013813, 2020"},{"key":"1068_CR2","unstructured":"L \u0301opez \u0301Alvarez F, Rodrigo JP: Laryngeal cancer: Diagnosis and treatment. In:Boffetta P, Hainaut P (eds) Encyclopedia of Cancer (Third Edition), third edition edn. Academic Press, Oxford, p 332\u2013345, 2019"},{"key":"1068_CR3","doi-asserted-by":"crossref","unstructured":"Myronenko A: 3d mri brain tumor segmentation using autoencoder regularization. In: Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 4th International Workshop, BrainLes 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Revised Selected Papers, Part II 4, Springer, pp 311\u2013320, 2019","DOI":"10.1007\/978-3-030-11726-9_28"},{"key":"1068_CR4","doi-asserted-by":"crossref","unstructured":"Zlocha M, Dou Q, Glocker B: Improving retinanet for ct lesion detection with dense masks from weak recist labels. In: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13\u201317, 2019, Proceedings, Part VI 22, Springer, pp 402\u2013410, 2019","DOI":"10.1007\/978-3-030-32226-7_45"},{"key":"1068_CR5","doi-asserted-by":"crossref","unstructured":"Ouardini K, Yang H, Unnikrishnan B, Romain M, Garcin C, Zenati H, Campbell J, Chiang MF, Kalpathy-Cramer J, Chandrasekhar VR, Krishnaswamy P, Foo C: Towards practical unsupervised anomaly detection on retinal images. In: Domain Adaptation and Representation Transfer and Medical Image Learning with Less Labels and Imperfect Data: First MICCAI Workshop, DART 2019, and First International Workshop, MIL3ID 2019, Shenzhen, Held in Conjunction with MICCAI 2019, Shenzhen, China, October 13 and 17, 2019, Proceedings 1, Springer, pp 225\u2013234, 2019","DOI":"10.1007\/978-3-030-33391-1_26"},{"key":"1068_CR6","doi-asserted-by":"crossref","unstructured":"Yan K, Tang Y, Peng Y, Sandfort V, Bagheri M, Lu Z, Summers RM: Mulan: multitask universal lesion analysis network for joint lesion detection, tagging, and segmentation. In: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13\u201317, 2019, Proceedings, Part VI 22, Springer, pp 194\u2013 202, 2019","DOI":"10.1007\/978-3-030-32226-7_22"},{"issue":"2","key":"1068_CR7","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee F, Jaeger PF, Kohl SA, Petersen J, Maier-Hein KH: nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods 18(2):203\u2013211, 2021","journal-title":"Nature methods"},{"issue":"Pt 2","key":"1068_CR8","first-page":"583","volume":"16","author":"HI Suk","year":"2013","unstructured":"Suk HI, Shen D: Deep learning-based feature representation for ad\/mci classification. Medical image computing and computer-assisted intervention : MICCAI International Conference on Medical Image Computing and Computer-Assisted Intervention 16 Pt 2:583\u201390, 2013","journal-title":"Medical image computing and computer-assisted intervention : MICCAI International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"1068_CR9","doi-asserted-by":"crossref","unstructured":"Akselrod-Ballin A, Karlinsky L, Alpert S, Hasoul SY, Ben-Ari R, Barkan E: A region based convolutional network for tumor detection and classification in breast mammography. In: LABELS\/DLMIA@MICCAI, 2016","DOI":"10.1007\/978-3-319-46976-8_21"},{"key":"1068_CR10","first-page":"201","volume":"11071","author":"J Ren","year":"2018","unstructured":"Ren J, Hacihaliloglu I, Singer EA, Foran DJ, Qi X: Adversarial domain adaptation for classification of prostate histopathology whole-slide images. Medical image computing and computer-assisted intervention : MICCAI International Conference on Medical Image Computing and Computer-Assisted Intervention 11071:201\u2013209, 2018","journal-title":"Medical image computing and computer-assisted intervention : MICCAI International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"1068_CR11","doi-asserted-by":"crossref","unstructured":"Tran BA, Dao TTP, Dung HDQ, Van NB, Ha CC, Pham NH, Nguyen THTNC, Nguyen T-C, Pham M-K, Tran M-K, Tran TM, Tran M-T: Support of deep learning to classify vocal fold images in flexible laryngoscopy. American Journal of Otolaryngology, 2023","DOI":"10.1016\/j.amjoto.2023.103800"},{"key":"1068_CR12","doi-asserted-by":"crossref","unstructured":"Esmaeili N, Sharaf E, Ataide EJG, Illanes A, Boese A, Davaris N, Arens C, Navab N, Friebe M: Deep convolution neural network for laryngeal cancer classification on contact endoscopy-narrow band imaging. Sensors (Basel, Switzerland) 21, 2021","DOI":"10.3390\/s21238157"},{"key":"1068_CR13","unstructured":"Huynh T-L, Nguyen H-H, Hoang X-N, Dao TTP, Nguyen T-P, Huynh V-T, Nguyen H-D, Le T-N, Tran M-T: Tail-aware sperm analysis for transparent tracking of spermatozoa, 2022"},{"key":"1068_CR14","doi-asserted-by":"crossref","unstructured":"Zhou H, Wang K, Tian J: Deep learning radiomics for non-invasive diagnosis of benign and malignant thyroid nodules using ultrasound images. In: Medical Imaging, 2020","DOI":"10.1117\/12.2549433"},{"key":"1068_CR15","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1002\/jmri.27599","volume":"54","author":"P Khosravi","year":"2021","unstructured":"Khosravi P, Lysandrou M, Eljalby M, Li Q, Kazemi E, Zisimopoulos P, Sigaras A, Brendel MB, Barnes J, Ricketts C, Meleshko D, Yat A, McClure TD, Robinson BD, Sboner A, Elemento O, Chughtai B, Hajirasouliha I: A deep learning approach to diagnostic classification of prostate cancer using pathology\u2013radiology fusion. Journal of Magnetic Resonance Imaging 54:462 \u2013 471, 2021","journal-title":"Journal of Magnetic Resonance Imaging"},{"key":"1068_CR16","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1164\/rccm.201903-0505OC","volume":"202","author":"PP Massion","year":"2020","unstructured":"Massion PP, Antic SL, Ather S, Arteta, C, Brabec J, Chen H, Declerck J, Dufek D, Hickes W, Kadir T, Kunst J, Landman BA, Munden R, Novotny P, Peschl H, Pickup LC, Santos C, Smith GT, Talwar A, Gleeson FV: Assessing the accuracy of a deep learning method to risk stratify indeterminate pulmonary nodules. American Journal of Respiratory and Critical Care Medicine 202:241 \u2013 249, 2020","journal-title":"American Journal of Respiratory and Critical Care Medicine"},{"key":"1068_CR17","doi-asserted-by":"publisher","first-page":"730","DOI":"10.1080\/00016480310000412","volume":"123","author":"J Ilgner","year":"2003","unstructured":"Ilgner J, Palm C, Schu\u00a8tz AG, Spitzer K, Westhofen M, Lehmann TM: Colour texture analysis for quantitative laryngoscopy. Acta Oto-Laryngologica 123:730 \u2013 734, 2003","journal-title":"Acta Oto-Laryngologica"},{"issue":"8","key":"1068_CR18","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1016\/j.compmedimag.2007.07.003","volume":"31","author":"A Verikas","year":"2007","unstructured":"Verikas A, Gelzinis A, Bacauskiene M, Valincius D, Uloza V: A kernel-based approach to categorizing laryngeal images. Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society 31 8:587\u201394, 2007","journal-title":"Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society"},{"key":"1068_CR19","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1016\/j.cmpb.2006.11.002","volume":"853","author":"A Verikas","year":"2007","unstructured":"Verikas A, Gelzinis A, Valincius D, Bacauskiene M, Uloza V: Multiple feature sets based categorization of laryngeal images. Computer methods and programs in biomedicine 853:257\u201366, 2007","journal-title":"Computer methods and programs in biomedicine"},{"key":"1068_CR20","doi-asserted-by":"crossref","unstructured":"T \u0308urkmen HI, Karsligil ME, Ko \u0327cak I: Classification of laryngeal disorders based on shape and vascular defects of vocal folds. Computers in biology and medicine 62:76\u201385, 2015","DOI":"10.1016\/j.compbiomed.2015.02.001"},{"key":"1068_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10916-019-1481-4","volume":"44","author":"CT Matava","year":"2020","unstructured":"Matava CT, Pankiv E, Raisbeck S, Caldeira M, Alam F: A convolutional neural network for real time classification, identification, and labelling of vocal cord and tracheal using laryngoscopy and bronchoscopy video. Journal of Medical Systems 44:1\u201310, 2020","journal-title":"Journal of Medical Systems"},{"key":"1068_CR22","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/s11548-018-01910-0","volume":"14","author":"M-H Laves","year":"2018","unstructured":"Laves M-H, Bicker J, Kahrs LA, Ortmaier T: A dataset of laryngeal endoscopic images with comparative study on convolution neural network-based semantic segmentation. International Journal of Computer Assisted Radiology and Surgery 14:483\u2013492, 2018","journal-title":"International Journal of Computer Assisted Radiology and Surgery"},{"key":"1068_CR23","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1177\/0003489420950364","volume":"130","author":"F Parker","year":"2020","unstructured":"Parker F, Brodsky MB, Akst LM, Ali H: Machine learning in laryngoscopy analysis: A proof of concept observational study for the identification of post-extubation ulcerations and granulomas. Annals of Otology, Rhinology & Laryngology 130:286 \u2013 291, 2020","journal-title":"Annals of Otology, Rhinology & Laryngology"},{"key":"1068_CR24","unstructured":"Yousef AM, Deliyski DD, Zacharias SR, Naghibolhosseini M: Detection of vocal fold image obstructions in high-speed videoendoscopy during connected speech in adductor spasmodic dysphonia: A convolutional neural networks approach. Journal of Voice, 2022"},{"key":"1068_CR25","unstructured":"Cho WK, Choi SH: Comparison of convolutional neural network models for determination of vocal fold normality in laryngoscopic images. Journal of voice :official journal of the Voice Foundation, 2020"},{"key":"1068_CR26","doi-asserted-by":"crossref","unstructured":"Cho WK, Lee YJ, Joo H.A, Jeong IS, Choi Y, Nam SY, Kim SY, Choi SH: Diagnostic accuracies of laryngeal diseases using a convolutional neural network-based image classification system. The Laryngoscope 131, 2021","DOI":"10.1002\/lary.29595"},{"key":"1068_CR27","doi-asserted-by":"crossref","unstructured":"Ren JJ, Jing X, Wang J, Ren X, Xu Y, Yang Q, Ma L, Sun Y, Xu W, Yang N, Zou J, Zheng Y, Chen M, Gan W, Xiang T, An J, Liu R, Lv C, Lin K, Zheng X, Lou F, Rao Y-f, Yang H, Liu K, Liu G, Lu T, Zheng X, Zhao Y: Automatic recognition of laryngoscopic images using a deep-learning technique. The Laryngoscope 130, 2020","DOI":"10.1002\/lary.28539"},{"key":"1068_CR28","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.ebiom.2019.08.075","volume":"48","author":"H Xiong","year":"2019","unstructured":"Xiong H, Lin P, Yu, JG, Ye J, Xiao L, Tao Y, Jiang Z, Lin W, Liu M, Xu J, Hu W, Lu Y, Liu H, Li Y, Zheng Y, Yang H: Computer-aided diagnosis of laryngeal cancer via deep learning based on laryngoscopic images. EBioMedicine 48:92 \u2013 99, 2019","journal-title":"EBioMedicine"},{"key":"1068_CR29","first-page":"45","volume":"184","author":"T-N Le","year":"2019","unstructured":"Le T-N, Nguyen TV, Nie Z, Tran M-T: Anabranch network for camouflaged object segmentation. CVIU 184:45\u201356, 2019","journal-title":"CVIU"},{"key":"1068_CR30","doi-asserted-by":"crossref","unstructured":"Cheng B, Misra I, Schwing AG, Kirillov A, Girdhar R: Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 1290\u20131299, 2022","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"1068_CR31","doi-asserted-by":"crossref","unstructured":"Yao P, Witte D, German A, Periyakoil P, Kim YE, Gimonet H, Sulica L, Born H, Elemento O, Barnes J, Rameau A: A deep learning pipeline for automated classification of vocal fold polyps in flexible laryngoscopy. European Archives of Oto-Rhino-Laryngology pp 1\u20138, 2023","DOI":"10.1007\/s00405-023-08190-8"},{"key":"1068_CR32","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1002\/lio2.754","volume":"7","author":"P Yao","year":"2022","unstructured":"Yao P, Witte D, Gimonet H, German A, Andreadis K, Cheng M, Sulica L, Elemento O, Barnes J, Rameau A: Automatic classification of informative laryngoscopic images using deep learning. Laryngoscope Investigative Otolaryngology 7:460 \u2013 466, 2022","journal-title":"Laryngoscope Investigative Otolaryngology"},{"key":"1068_CR33","doi-asserted-by":"crossref","unstructured":"Adamian N, Naunheim MR, Jowett N: An open-source computer vision tool for automated vocal fold tracking from videoendoscopy. The Laryngoscope 131, 2020","DOI":"10.1002\/lary.28669"},{"issue":"6","key":"1068_CR34","doi-asserted-by":"publisher","first-page":"1564","DOI":"10.1002\/ohn.411","volume":"169","author":"AM Bur","year":"2023","unstructured":"Bur AM, Zhang T, Chen X, Kavookjian H, Kraft S, Karadaghy O, Farrokhian N, Mussatto C, Penn J, Wang G: Interpretable Computer Vision to Detect and Classify Structural Laryngeal Lesions in Digital Flexible Laryngoscopic Images. Otolaryngology\u2013Head and Neck Surgery 169(6):1564-1572, 2023","journal-title":"Otolaryngology-Head and Neck Surgery"},{"key":"1068_CR35","unstructured":"Ren S, He K, Girshick R, Sun J: Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28, 2015"},{"key":"1068_CR36","doi-asserted-by":"crossref","unstructured":"Sa R, Owens W, Wiegand R, Studin M, Capoferri D, Barooha K, Greaux A, Rattray R, Hutton A, Cintineo J, Chaudhary: Intervertebral disc detection in X-ray images using faster R-CNN. In2017 39th annual international conference of the IEEE engineering in medicine and biology society (EMBC) pp. 564\u2013567. IEEE, 2017","DOI":"10.1109\/EMBC.2017.8036887"},{"key":"1068_CR37","doi-asserted-by":"crossref","unstructured":"Mo X, Tao K, Wang Q, Wang G: An efficient approach for polyps detection in endoscopic videos based on faster R-CNN. In2018 24th international conference on pattern recognition (ICPR) pp. 3929\u20133934. IEEE, 2018","DOI":"10.1109\/ICPR.2018.8545174"},{"key":"1068_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106470","volume":"153","author":"J Xu","year":"2023","unstructured":"Xu J, Ren H, Cai S, Zhang X: An improved faster R-CNN algorithm for assisted detection of lung nodules. Computers In Biology And Medicine 153:106470, 2023","journal-title":"Computers In Biology And Medicine"},{"key":"1068_CR39","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le QV: Efficientdet: Scalable and efficient object detection. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 10778\u201310787, 2019","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"1068_CR40","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:201011929, 2020"},{"key":"1068_CR41","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S: End-to-end object detection with transformers. ArXiv abs\/2005.12872, 2020","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1068_CR42","doi-asserted-by":"crossref","unstructured":"Wu Y, Kong Q, Zhang L, Castiglione A, Nappi M, Wan S. Cdt-cad: Context-aware deformable transformers for end-to-end chest abnormality detection on x-ray images. IEEE\/ACM Transactions on Computational Biology and Bioinformatics, 2023","DOI":"10.1109\/TCBB.2023.3258455"},{"key":"1068_CR43","doi-asserted-by":"crossref","unstructured":"Leng B, Wang C, Leng M, Ge M, Dong W: Deep learning detection network for peripheral blood leukocytes based on improved detection transformer. Biomedical Signal Processing and Control 1;82:104518, 2023","DOI":"10.1016\/j.bspc.2022.104518"},{"issue":"7","key":"1068_CR44","doi-asserted-by":"publisher","first-page":"3676","DOI":"10.3390\/app12073676","volume":"12","author":"A Amer","year":"2022","unstructured":"Amer A, Lambrou T, Ye X: Mda-unet: a multi-scale dilated attention u-net for medical image segmentation. Applied Sciences 12(7):3676, 2022","journal-title":"Applied Sciences"},{"key":"1068_CR45","unstructured":"Jocher G, Stoken A, Chaurasia A, Borovec J, NanoCode012, TaoXie, Kwon Y, Michael K, Changyu L, Fang J, V A, Laughing, tkianai, yxNONG, Skalski P, Hogan A, Nadar J, imyhxy, Mammana L, AlexWang1900, Fati C, Montes D, Hajek J, Diaconu L, Minh MT, Marc, albinxavi, fatih, oleg, wanghaoyang0106: ultralytics\/yolov5: v6.0 - YOLOv5n \u2019Nano\u2019 models, Roboflow integration, TensorFlow export, OpenCV DNN support, 2021"},{"issue":"12","key":"1068_CR46","doi-asserted-by":"publisher","first-page":"2264","DOI":"10.3390\/diagnostics11122264","volume":"11","author":"J Wan","year":"2021","unstructured":"Wan J, Chen B, Yu Y: Polyp detection from colorectum images by using attentive yolov5. Diagnostics 11(12):2264, 2021","journal-title":"Diagnostics"},{"key":"1068_CR47","first-page":"2022","volume":"1\u201316","author":"A Mohiyuddin","year":"2022","unstructured":"Mohiyuddin A, Basharat A, Ghani U, Peter V, Abbas S, Naeem OB, Rizwan M: Breast tumor detection and classification in mammogram images using modified yolov5 network. Computational and Mathematical Methods in Medicine 2022:1\u201316, 2022","journal-title":"Computational and Mathematical Methods in Medicine"},{"key":"1068_CR48","unstructured":"Tan M, Le Q: Efficientnet: Rethinking model scaling for convolutional neural networks. In: International conference on machine learning, PMLR, pp 6105\u20136114, 2019"},{"key":"1068_CR49","doi-asserted-by":"crossref","unstructured":"Girshick R: Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440\u20131448, 2015","DOI":"10.1109\/ICCV.2015.169"},{"key":"1068_CR50","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg, AC: Ssd: Single shot multibox detector.In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14, Springer, pp 21\u201337, 2016","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1068_CR51","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala SK, Girshick RB, Farhadi A: You only look once: Unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, June 27\u201330, 2016. IEEE Computer Society, pp 779\u2013788, 2016","DOI":"10.1109\/CVPR.2016.91"},{"key":"1068_CR52","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A: YOLO9000: better, faster, stronger. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21\u201326, 2017. IEEE Computer Society, pp 6517\u20136525, 2017","DOI":"10.1109\/CVPR.2017.690"},{"key":"1068_CR53","unstructured":"Redmon J, Farhadi A: Yolov3: An incremental improvement. arXiv preprint arXiv:180402767, 2018"},{"key":"1068_CR54","unstructured":"Bochkovskiy A, Wang CY, Liao HYM: Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:200410934, 2020"},{"key":"1068_CR55","doi-asserted-by":"publisher","first-page":"3113","DOI":"10.1109\/TIP.2021.3058783","volume":"30","author":"YH Wu","year":"2021","unstructured":"Wu YH, Gao SH, Mei J, Xu J, Fan DP, Zhang RG, Cheng MM: JCS: An explainable COVID-19 diagnosis system by joint classification and segmentation. IEEE Transactions on Image Processing 30:3113\u20133126, 2021","journal-title":"IEEE Transactions on Image Processing"},{"key":"1068_CR56","doi-asserted-by":"crossref","unstructured":"Cao B, Araujo A, Sim J: Unifying deep local and global features for image search. European Conference on Computer Vision - ECCV 2020. Springer International Publishing, Cham, pp 726\u2013743, 2020","DOI":"10.1007\/978-3-030-58565-5_43"},{"key":"1068_CR57","doi-asserted-by":"crossref","unstructured":"Zou W, Ye T, Zheng W, Zhang Y, Chen L, Wu Y: Self-calibrated efficient transformer for lightweight super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 930\u2013939, 2022","DOI":"10.1109\/CVPRW56347.2022.00107"},{"key":"1068_CR58","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I: Attention is all you need. Advances in neural information processing systems 30, 2017"},{"key":"1068_CR59","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861, 2017"},{"key":"1068_CR60","doi-asserted-by":"crossref","unstructured":"Liu Z, Mao H, Wu C-Y, Feichtenhofer C, Darrell T, Xie S: A convnet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 11976\u201311986, 2022","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"1068_CR61","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J: Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 770\u2013778, 2016","DOI":"10.1109\/CVPR.2016.90"},{"key":"1068_CR62","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC: Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4510\u20134520, 2018","DOI":"10.1109\/CVPR.2018.00474"},{"key":"1068_CR63","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed SE, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A: Going deeper with convolutions. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1\u20139, 2015","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1068_CR64","unstructured":"Loshchilov I, Hutter F. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101. 2017 Nov 14."}],"container-title":["Journal of Imaging Informatics in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-024-01068-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10278-024-01068-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-024-01068-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T19:04:50Z","timestamp":1733166290000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10278-024-01068-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,29]]},"references-count":64,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["1068"],"URL":"https:\/\/doi.org\/10.1007\/s10278-024-01068-z","relation":{},"ISSN":["2948-2933"],"issn-type":[{"value":"2948-2933","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,29]]},"assertion":[{"value":"7 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 February 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 May 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was performed in line with the principles of the Declaration of Helsinki. Approval was granted by the Independent Ethics Committee of Cho Ray Hospital (Date: March 9th, 2022\/No.1280\/GCN-H\u0110\u0110\u0110).","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval"}},{"value":"Informed consent was waived in this study. Because the study only uses the historical data of laryngoscopy images, there will be no interaction with or impact on patients.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Participate"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}]}}