{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:00:32Z","timestamp":1775577632069,"version":"3.50.1"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,5,23]],"date-time":"2021-05-23T00:00:00Z","timestamp":1621728000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,5,23]],"date-time":"2021-05-23T00:00:00Z","timestamp":1621728000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Digit Imaging"],"published-print":{"date-parts":[[2021,8]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Rapid and accurate assessment of endotracheal tube (ETT) location is essential in the intensive care unit (ICU) setting, where timely identification of a mispositioned support device may prevent significant patient morbidity and mortality. This study proposes a series of deep learning-based algorithms which together iteratively identify and localize the position of an ETT relative to the carina on chest radiographs. Using the open-source MIMIC Chest X-Ray (MIMIC-CXR) dataset, a total of 16,000 patients were identified (8000 patients with an ETT and 8000 patients without an ETT). Three different convolutional neural network (CNN) algorithms were created. First, a regression loss function CNN was trained to estimate the coordinate location of the carina, which was then used to crop the original radiograph to the distal trachea and proximal bronchi. Second, a classifier CNN was trained using the cropped inputs to determine the presence or absence of an ETT. Finally, for radiographs containing an ETT, a third regression CNN was trained to both refine the coordinate location of the carina and identify the location of the distal ETT tip. Model accuracy was assessed by comparing the absolute distance of prediction and ground-truth coordinates as well as CNN predictions relative to measurements documented in original radiologic reports. Upon five-fold cross validation, binary classification for the presence or absence of ETT demonstrated an accuracy, sensitivity, specificity, PPV, NPV, and AUC of 97.14%, 97.37%, 96.89%, 97.12%, 97.15%, and 99.58% respectively. CNN predicted coordinate location of the carina, and distal ETT tip was estimated within a median error of 0.46\u00a0cm and 0.60\u00a0cm from ground-truth annotations respectively. Overall final CNN assessment of distance between the carina and distal ETT tip was predicted within a median error of 0.60\u00a0cm from manual ground-truth annotations, and a median error of 0.66\u00a0cm from measurements documented in the original radiology reports. A serial cascaded CNN approach demonstrates high accuracy for both identification and localization of ETT tip and carina on chest radiographs. High performance of the proposed multi-step strategy is in part related to iterative refinement of coordinate localization as well as explicit image cropping which focuses algorithm attention to key anatomic regions of interest.<\/jats:p>","DOI":"10.1007\/s10278-021-00463-0","type":"journal-article","created":{"date-parts":[[2021,5,23]],"date-time":"2021-05-23T20:02:40Z","timestamp":1621800160000},"page":"898-904","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Identification and Localization of Endotracheal Tube on Chest Radiographs Using a Cascaded Convolutional Neural Network Approach"],"prefix":"10.1007","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3595-4923","authenticated-orcid":false,"given":"Su","family":"Kara","sequence":"first","affiliation":[]},{"given":"Jake Y.","family":"Akers","sequence":"additional","affiliation":[]},{"given":"Peter D.","family":"Chang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,5,23]]},"reference":[{"key":"463_CR1","unstructured":"Eldridge L, Doru P: How an endotracheal tube is used: understanding the purpose, procedure, and possible risks. Verywell Health. Available at https:\/\/www.verywellhealth.com\/endotracheal-tube-information-2249093, 2020"},{"key":"463_CR2","unstructured":"Peitzman AB, Yealy DM, Fabian TC, Schwab CW: The trauma manual: trauma and acute care surgery, Philadelphia, Wolters Kluwer, 2019"},{"key":"463_CR3","doi-asserted-by":"publisher","unstructured":"Gupta PK, Gupta K, Jain M, Garg T: Postprocedural chest radiograph: Impact on the management in critical care unit. Anesth Essays Res 8(2):139\u2013144, https:\/\/doi.org\/10.4103\/0259-1162.134481, 2014","DOI":"10.4103\/0259-1162.134481"},{"key":"463_CR4","doi-asserted-by":"publisher","unstructured":"Divatia JV, Khan PU, Myatra SN: Tracheal intubation in the ICU: Life saving or life threatening? Indian J Anaesth 55(5): 470\u2013475, https:\/\/doi.org\/10.4103\/0019-5049.89872, 2011","DOI":"10.4103\/0019-5049.89872"},{"key":"463_CR5","doi-asserted-by":"publisher","unstructured":"Hitti EA, El-Eid GR, Tamim H, Saleh R, Saliba M, Naffaa L: Improving emergency department radiology transportation time: a successful implementation of lean methodology. BMC Health Serv Res. 17: 625, https:\/\/doi.org\/10.1186\/s12913-017-2488-5, 2017","DOI":"10.1186\/s12913-017-2488-5"},{"key":"463_CR6","unstructured":"Rajpurkar P, Irvin J, Zhu K, Yang B, Mehta H, Duan T, Ding D, Bagul A, Langlotz C, Shpanskaya K, Lungren MP, Ng AY: CheXNet: Radiologist-level pneumonia detection on chest x-rays with deep learning. https:\/\/arxiv.org\/abs\/1711.05225, 2017"},{"key":"463_CR7","doi-asserted-by":"publisher","unstructured":"Stirenko S, Kochura Y, Alienin O, Rokovyi O, Gang P, Zeng W, Gordienko Y: Chest X-ray analysis of tuberculosis by deep learning with segmentation and augmentation.\u00a0https:\/\/arxiv.org\/abs\/1803.01199, https:\/\/doi.org\/10.1109\/ELNANO.2018.8477564, 2018","DOI":"10.1109\/ELNANO.2018.8477564"},{"issue":"23","key":"463_CR8","doi-asserted-by":"publisher","first-page":"e215","DOI":"10.1161\/01.CIR.101.23.e215","volume":"101","author":"AL Goldberger","year":"2000","unstructured":"Goldberger AL, Amaral LAN, Glass L, Hausdorff JM, Ivanov PC, Mark RG, Mietus JE, Moody GB, Peng CK, Stanley HE: PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101(23):e215-e220, 2000","journal-title":"Circulation"},{"key":"463_CR9","doi-asserted-by":"publisher","unstructured":"Johnson AEW, Pollard TJ, Berkowitz SJ et al.: MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Sci Data 6(317).\u00a0\u00a0https:\/\/doi.org\/10.1038\/s41597-019-0322-0, 2019","DOI":"10.1038\/s41597-019-0322-0"},{"key":"463_CR10","doi-asserted-by":"publisher","unstructured":"Johnson AEW, Pollard TJ, Berkowitz SJ, Mark R, Horng S: MIMIC-CXR Database (version 2.0.0). PhysioNet. https:\/\/doi.org\/10.13026\/C2JT1Q, 2019","DOI":"10.13026\/C2JT1Q"},{"key":"463_CR11","unstructured":"Read the Docs. Available at https:\/\/ml-cheatsheet.readthedocs.io\/en\/latest\/activation_functions.html#leakyrelu. Accessed 5 July 2020."},{"key":"463_CR12","unstructured":"Xavier G, Bengio Y: Understanding the difficulty of training deep feedforward neural networks. AISTATS, 2010"},{"key":"463_CR13","unstructured":"Kingma DP, Ba JA: A Method for Stochastic Optimization. CoRR abs\/1412.6980, 2014"},{"key":"463_CR14","unstructured":"Abadi M. et al.: TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. CoRR abs\/1603.04467, 2015"},{"issue":"10","key":"463_CR15","doi-asserted-by":"publisher","first-page":"e0204155","DOI":"10.1371\/journal.pone.0204155","volume":"13","author":"R Singh","year":"2018","unstructured":"Singh R, Kalra MK, Nitiwarangkul C, Patti JA, Homayounieh F, Padole A, et al.: Deep learning in chest radiography: detection of findings and presence of change. PLoS ONE 13(10): e0204155, 2018","journal-title":"PLoS ONE"},{"key":"463_CR16","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1016\/j.measurement.2019.05.076","volume":"145","author":"AK Jaiswal","year":"2019","unstructured":"Jaiswal AK, Tiwari P, Kumar S, Gupta D, Khanna A, et al.: Identifying pneumonia in chest X-rays: A deep learning approach. Measurement 145:511-518, 2019","journal-title":"Measurement"},{"key":"463_CR17","doi-asserted-by":"publisher","unstructured":"Lakhani P, Sundaram B: Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology 284(2), https:\/\/doi.org\/10.1148\/radiol.2017162326, 2017","DOI":"10.1148\/radiol.2017162326"},{"key":"463_CR18","unstructured":"Wang H, Xia Y: ChestNet: A deep neural network for classification of thoracic diseases on chest radiography. https:\/\/arxiv.org\/abs\/1807.03058v1, 2018"},{"key":"463_CR19","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1016\/j.patrec.2019.11.013","volume":"129","author":"A Bhandary","year":"2020","unstructured":"Bhandary A, Prabhu GA, et al.: Deep-learning framework to detect lung abnormality\u2014a study with chest X-Ray and lung CT scan images. Pattern Recognition Letters 129:271-278, 2020","journal-title":"Pattern Recognition Letters"},{"key":"463_CR20","doi-asserted-by":"publisher","unstructured":"Lakhani P: Deep convolutional neural networks for endotracheal tube position and x-ray image classification: Challenges and opportunities. J Digit Imaging 30:460\u2013468, https:\/\/doi.org\/10.1007\/s10278-017-9980-7, 2017","DOI":"10.1007\/s10278-017-9980-7"},{"key":"463_CR21","doi-asserted-by":"publisher","unstructured":"Frid-Adar M, Amer R, Greenspan H: Endotracheal tube detection and segmentation in chest radiographs using synthetic data. MICCAI 2019. Lecture Notes in Computer Science 11769. https:\/\/doi.org\/10.1007\/978-3-030-32226-7_87, 2019","DOI":"10.1007\/978-3-030-32226-7_87"},{"key":"463_CR22","doi-asserted-by":"publisher","unstructured":"Huo Z, Mao H, Zhang J, Sykes AM, Munn S, Wandtke J: Computer-aided detection of malpositioned endotracheal tubes in portable chest radiographs. Proc. SPIE 9035, Medical Imaging 2014: Computer-Aided Diagnosis, https:\/\/doi.org\/10.1117\/12.2043826, 2014","DOI":"10.1117\/12.2043826"},{"key":"463_CR23","unstructured":"Noothout, Julia MH, et al.: CNN-based landmark detection in cardiac CTA scans. arXiv preprint.\u00a0https:\/\/arxiv.org\/abs\/1804.06963, 2018"},{"key":"463_CR24","doi-asserted-by":"crossref","unstructured":"Tan, Zimeng, et al.: A cascade regression model for anatomical landmark detection. international workshop on statistical atlases and computational models of the heart. Springer, Cham, 2019","DOI":"10.1007\/978-3-030-39074-7_5"},{"key":"463_CR25","doi-asserted-by":"crossref","unstructured":"Theriault-Lauzier, Pascal, et al.: Recursive multiresolution convolutional neural networks for 3D aortic valve annulus planimetry. International journal of computer assisted radiology and surgery 15.4:577\u2013588, 2020","DOI":"10.1007\/s11548-020-02131-0"},{"key":"463_CR26","doi-asserted-by":"crossref","unstructured":"Ma, Tianyu, Ajay Gupta, and Mert R. Sabuncu: Volumetric landmark detection with a multi-scale shift equivariant neural network. 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI). IEEE, 2020","DOI":"10.1109\/ISBI45749.2020.9098620"}],"container-title":["Journal of Digital Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-021-00463-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10278-021-00463-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-021-00463-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T16:57:15Z","timestamp":1632243435000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10278-021-00463-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,23]]},"references-count":26,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,8]]}},"alternative-id":["463"],"URL":"https:\/\/doi.org\/10.1007\/s10278-021-00463-0","relation":{},"ISSN":["0897-1889","1618-727X"],"issn-type":[{"value":"0897-1889","type":"print"},{"value":"1618-727X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,23]]},"assertion":[{"value":"11 August 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 March 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 May 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}