{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T11:17:39Z","timestamp":1793272659946,"version":"4.5.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,12,9]],"date-time":"2021-12-09T00:00:00Z","timestamp":1639008000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,12,9]],"date-time":"2021-12-09T00:00:00Z","timestamp":1639008000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2018R1C1B5086518"],"award-info":[{"award-number":["2018R1C1B5086518"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Anesthesiologists commonly use video bronchoscopy to facilitate intubation or confirm the location of the endotracheal tube; however, depth and orientation in the bronchial tree can often be confused because anesthesiologists cannot trace the airway from the oropharynx when it is performed using an endotracheal tube. Moreover, the decubitus position is often used in certain surgeries. Although it occurs rarely, the misinterpretation of tube location can cause accidental extubation or endobronchial intubation, which can lead to hyperinflation. Thus, video bronchoscopy with a decision supporting system using artificial intelligence would be useful in the anesthesiologic process. In this study, we aimed to develop an artificial intelligence model robust to rotation and covering using video bronchoscopy images. We collected video bronchoscopic images from an institutional database. Collected images were automatically labeled by an optical character recognition engine as the carina and left\/right main bronchus. Except 180 images for the evaluation dataset, 80% were randomly allocated to the training dataset. The remaining images were assigned to the validation and test datasets in a 7:3 ratio. Random image rotation and circular cropping were applied. Ten kinds of pretrained models with\u2009&lt;\u200925 million parameters were trained on the training and validation datasets. The model showing the best prediction accuracy for the test dataset was selected as the final model. Six human experts reviewed the evaluation dataset for the inference of anatomical locations to compare its performance with that of the final model. In the experiments, 8688 images were prepared and assigned to the evaluation (180), training (6806), validation (1191), and test (511) datasets. The EfficientNetB1 model showed the highest accuracy (0.86) and was selected as the final model. For the evaluation dataset, the final model showed better performance (accuracy, 0.84) than almost all human experts (0.38, 0.44, 0.51, 0.68, and 0.63), and only the most-experienced pulmonologist showed performance comparable (0.82) with that of the final model. The performance of human experts was generally proportional to their experiences. The performance difference between anesthesiologists and pulmonologists was marked in discrimination of the right main bronchus. Using bronchoscopic images, our model could distinguish anatomical locations among the carina and both main bronchi under random rotation and covering. The performance was comparable with that of the most-experienced human expert. This model can be a basis for designing a clinical decision support system with video bronchoscopy.\n<\/jats:p>","DOI":"10.1038\/s41598-021-03219-6","type":"journal-article","created":{"date-parts":[[2021,12,9]],"date-time":"2021-12-09T11:12:09Z","timestamp":1639048329000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":57,"title":["Deep learning for anatomical interpretation of video bronchoscopy images"],"prefix":"10.1038","volume":"11","author":[{"given":"Ji Young","family":"Yoo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Se Yoon","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jong Sun","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Young-Jae","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sung Yong","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ho Il","family":"Yoon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sang Jun","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han-Gil","family":"Jeong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tackeun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,12,9]]},"reference":[{"key":"3219_CR1","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.ebiom.2019.07.019","volume":"46","author":"C Garcia-Vidal","year":"2019","unstructured":"Garcia-Vidal, C., Sanjuan, G., Puerta-Alcalde, P., Moreno-Garcia, E. & Soriano, A. Artificial intelligence to support clinical decision-making processes. EBioMedicine 46, 27\u201329 (2019).","journal-title":"EBioMedicine"},{"key":"3219_CR2","doi-asserted-by":"publisher","first-page":"2199","DOI":"10.1001\/jama.2018.17163","volume":"320","author":"EH Shortliffe","year":"2018","unstructured":"Shortliffe, E. H. & Sepulveda, M. J. Clinical decision support in the era of artificial intelligence. JAMA 320, 2199\u20132200 (2018).","journal-title":"JAMA"},{"key":"3219_CR3","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1055\/s-0039-1677911","volume":"28","author":"S Montani","year":"2019","unstructured":"Montani, S. & Striani, M. Artificial intelligence in clinical decision support: A focused literature survey. Yearb. Med. Inform. 28, 120\u2013127 (2019).","journal-title":"Yearb. Med. Inform."},{"key":"3219_CR4","doi-asserted-by":"publisher","DOI":"10.23736\/S0375-9393.20.14999-X","author":"EG Bignami","year":"2020","unstructured":"Bignami, E. G., Cozzani, F., Del Rio, P. & Bellini, V. Artificial intelligence and perioperative medicine. Minerva Anestesiol. https:\/\/doi.org\/10.23736\/S0375-9393.20.14999-X (2020).","journal-title":"Minerva Anestesiol."},{"key":"3219_CR5","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/S0749-0704(05)70098-1","volume":"16","author":"JM Liebler","year":"2000","unstructured":"Liebler, J. M. & Markin, C. J. Fiberoptic bronchoscopy for diagnosis and treatment. Crit. Care Clin. 16, 83\u2013100 (2000).","journal-title":"Crit. Care Clin."},{"key":"3219_CR6","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1159\/000498951","volume":"98","author":"DIK Fielding","year":"2019","unstructured":"Fielding, D. I. K. et al. First human use of a new robotic-assisted fiber optic sensing navigation system for small peripheral pulmonary nodules. Respiration 98, 142\u2013150 (2019).","journal-title":"Respiration"},{"key":"3219_CR7","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1097\/LBR.0000000000000499","volume":"25","author":"JR Rojas-Solano","year":"2018","unstructured":"Rojas-Solano, J. R., Ugalde-Gamboa, L. & Machuzak, M. Robotic bronchoscopy for diagnosis of suspected lung cancer: A feasibility study. J. Bronchol. Interv. Pulmonol. 25, 168\u2013175 (2018).","journal-title":"J. Bronchol. Interv. Pulmonol."},{"key":"3219_CR8","doi-asserted-by":"publisher","first-page":"025001","DOI":"10.1088\/1361-6560\/abca07","volume":"66","author":"S Navaei Lavasani","year":"2021","unstructured":"Navaei Lavasani, S. et al. Bronchoscope motion tracking using centerline-guided Gaussian mixture model in navigated bronchoscopy. Phys. Med. Biol. 66, 025001 (2021).","journal-title":"Phys. Med. Biol."},{"key":"3219_CR9","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.athoracsur.2018.01.051","volume":"106","author":"AC Chen","year":"2018","unstructured":"Chen, A. C. & Gillespie, C. T. Robotic endoscopic airway challenge: REACH assessment. Ann. Thorac Surg. 106, 293\u2013297 (2018).","journal-title":"Ann. Thorac Surg."},{"key":"3219_CR10","doi-asserted-by":"publisher","first-page":"1089","DOI":"10.1007\/s11548-017-1609-2","volume":"12","author":"M Visentini-Scarzanella","year":"2017","unstructured":"Visentini-Scarzanella, M., Sugiura, T., Kaneko, T. & Koto, S. Deep monocular 3D reconstruction for assisted navigation in bronchoscopy. Int. J. Comput. Assist. Radiol. Surg. 12, 1089\u20131099 (2017).","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"3219_CR11","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1097\/00008506-199901000-00003","volume":"11","author":"G Fuchs","year":"1999","unstructured":"Fuchs, G. et al. Fiberoptic intubation in 327 neurosurgical patients with lesions of the cervical spine. J. Neurosurg. Anesthesiol. 11, 11\u201316 (1999).","journal-title":"J. Neurosurg. Anesthesiol."},{"key":"3219_CR12","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1097\/00000542-199802000-00012","volume":"88","author":"U Klein","year":"1998","unstructured":"Klein, U. et al. Role of fiberoptic bronchoscopy in conjunction with the use of double-lumen tubes for thoracic anesthesia: A prospective study. Anesthesiology 88, 346\u2013350 (1998).","journal-title":"Anesthesiology"},{"key":"3219_CR13","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1111\/anae.13850","volume":"72","author":"A Moore","year":"2017","unstructured":"Moore, A. et al. Videolaryngoscopy or fibreoptic bronchoscopy for awake intubation of bariatric patients with predicted difficult airways\u2014A randomised, controlled trial. Anaesthesia 72, 538\u2013539 (2017).","journal-title":"Anaesthesia"},{"key":"3219_CR14","doi-asserted-by":"publisher","first-page":"797","DOI":"10.1097\/00000542-199503000-00033","volume":"82","author":"D Soroker","year":"1995","unstructured":"Soroker, D., Ezri, T. & Szmuk, P. Fiberoptic bronchoscopy in a patient requiring continuous positive airway pressure. Anesthesiology 82, 797\u2013798 (1995).","journal-title":"Anesthesiology"},{"key":"3219_CR15","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1186\/s13063-018-3163-9","volume":"20","author":"T Ryu","year":"2019","unstructured":"Ryu, T. et al. Comparing the placement of a left-sided double-lumen tube via fiberoptic bronchoscopy guidance versus conventional intubation using a Macintosh laryngoscope, to reduce the incidence of malpositioning: Study protocol for a randomized controlled pilot trial. Trials 20, 51 (2019).","journal-title":"Trials"},{"key":"3219_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1097\/00001503-200402000-00002","volume":"17","author":"E Cohen","year":"2004","unstructured":"Cohen, E. Double-lumen tube position should be confirmed by fiberoptic bronchoscopy. Curr. Opin. Anaesthesiol. 17, 1\u20136 (2004).","journal-title":"Curr. Opin. Anaesthesiol."},{"key":"3219_CR17","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1097\/ACO.0b013e32831a43ab","volume":"22","author":"JH Campos","year":"2009","unstructured":"Campos, J. H. Update on tracheobronchial anatomy and flexible fiberoptic bronchoscopy in thoracic anesthesia. Curr. Opin. Anaesthesiol. 22, 4\u201310 (2009).","journal-title":"Curr. Opin. Anaesthesiol."},{"key":"3219_CR18","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1097\/00000542-199005000-00010","volume":"72","author":"RA Caplan","year":"1990","unstructured":"Caplan, R. A., Posner, K. L., Ward, R. J. & Cheney, F. W. Adverse respiratory events in anesthesia: A closed claims analysis. Anesthesiology 72, 828\u2013833 (1990).","journal-title":"Anesthesiology"},{"key":"3219_CR19","doi-asserted-by":"publisher","first-page":"c5943","DOI":"10.1136\/bmj.c5943","volume":"341","author":"C Sitzwohl","year":"2010","unstructured":"Sitzwohl, C. et al. Endobronchial intubation detected by insertion depth of endotracheal tube, bilateral auscultation, or observation of chest movements: Randomised trial. BMJ 341, c5943 (2010).","journal-title":"BMJ"},{"key":"3219_CR20","doi-asserted-by":"crossref","unstructured":"Deng, J. et al. Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, 248\u2013255 (IEEE, 2009).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3219_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Identity mappings in deep residual networks. In European Conference on Computer Vision, 630\u2013645 (Springer, 2016).","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"3219_CR22","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L. & Weinberger, K. Q. Densely connected convolutional networks. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 4700\u20134708 (2017).","DOI":"10.1109\/CVPR.2017.243"},{"key":"3219_CR23","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A. & Chen, L.-C. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 4510\u20134520 (2018).","DOI":"10.1109\/CVPR.2018.00474"},{"key":"3219_CR24","unstructured":"Tan, M. & Le, Q. Efficientnet: Rethinking model scaling for convolutional neural networks. In International Conference on Machine Learning, 6105\u20136114 (PMLR, 2019)."},{"key":"3219_CR25","doi-asserted-by":"crossref","unstructured":"Zoph, B., Vasudevan, V., Shlens, J. & Le, Q. V. Learning transferable architectures for scalable image recognition. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 8697\u20138710 (2018).","DOI":"10.1109\/CVPR.2018.00907"},{"key":"3219_CR26","unstructured":"Kingma, D. P. & Ba, J. Adam: A method for stochastic optimization. Preprint at http:\/\/arXiv.org\/1412.6980 (2014)."},{"key":"3219_CR27","unstructured":"Selvaraju, R. R, et al. Grad-CAM: Why did you say that? Preprint at http:\/\/arXiv.org\/1611.07450 (2016)."},{"key":"3219_CR28","doi-asserted-by":"publisher","first-page":"6997","DOI":"10.3390\/s20236997","volume":"20","author":"JC Chien","year":"2020","unstructured":"Chien, J. C., Lee, J. D., Su, E. & Li, S. H. A bronchoscope localization method using an augmented reality co-display of real bronchoscopy images with a virtual 3D bronchial tree model. Sensors (Basel) 20, 6997 (2020).","journal-title":"Sensors (Basel)"},{"key":"3219_CR29","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1378\/chest.107.2.430","volume":"107","author":"CA Pue","year":"1995","unstructured":"Pue, C. A. & Pacht, E. R. Complications of fiberoptic bronchoscopy at a university hospital. Chest 107, 430\u2013432 (1995).","journal-title":"Chest"},{"key":"3219_CR30","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1378\/chest.14-0678","volume":"148","author":"A Ernst","year":"2015","unstructured":"Ernst, A. et al. Adult bronchoscopy training: Current state and suggestions for the future: CHEST expert panel report. Chest 148, 321\u2013332 (2015).","journal-title":"Chest"},{"issue":"Suppl 1","key":"3219_CR31","first-page":"i1","volume":"56","author":"British Thoracic Society Bronchoscopy Guidelines Committee, a Subcommittee of Standards of Care Committee of British Thoracic Society","year":"2001","unstructured":"British Thoracic Society Bronchoscopy Guidelines Committee, a Subcommittee of Standards of Care Committee of British Thoracic Society. British Thoracic Society guidelines on diagnostic flexible bronchoscopy. Thorax 56(Suppl 1), i1\u2013i21 (2001).","journal-title":"Thorax"},{"key":"3219_CR32","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1111\/j.1440-1843.2012.02270.x","volume":"18","author":"DR Stather","year":"2013","unstructured":"Stather, D. R., Maceachern, P., Chee, A., Dumoulin, E. & Tremblay, A. Trainee impact on advanced diagnostic bronchoscopy: An analysis of 607 consecutive procedures in an interventional pulmonary practice. Respirology 18, 179\u2013184 (2013).","journal-title":"Respirology"},{"key":"3219_CR33","doi-asserted-by":"publisher","first-page":"1022","DOI":"10.1007\/s12630-013-9999-2","volume":"60","author":"JP Wanderer","year":"2013","unstructured":"Wanderer, J. P., Ehrenfeld, J. M., Sandberg, W. S. & Epstein, R. H. The changing scope of difficult airway management. Can. J. Anaesth. 60, 1022\u20131024 (2013).","journal-title":"Can. J. Anaesth."},{"key":"3219_CR34","doi-asserted-by":"publisher","first-page":"189","DOI":"10.5603\/AIT.a2017.0035","volume":"49","author":"M Parotto","year":"2017","unstructured":"Parotto, M. et al. Evaluation of a low-cost, 3D-printed model for bronchoscopy training. Anaesthesiol. Intens. Ther. 49, 189\u2013197 (2017).","journal-title":"Anaesthesiol. Intens. Ther."},{"key":"3219_CR35","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.1111\/anae.13951","volume":"72","author":"TH Pedersen","year":"2017","unstructured":"Pedersen, T. H. et al. A randomised, controlled trial evaluating a low cost, 3D-printed bronchoscopy simulator. Anaesthesia 72, 1005\u20131009 (2017).","journal-title":"Anaesthesia"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-03219-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-03219-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-03219-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,3]],"date-time":"2022-12-03T18:02:20Z","timestamp":1670090540000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-03219-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,9]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["3219"],"URL":"https:\/\/doi.org\/10.1038\/s41598-021-03219-6","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,9]]},"assertion":[{"value":"29 June 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 November 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 December 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"23765"}}