{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T16:30:37Z","timestamp":1771518637706,"version":"3.50.1"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,5,12]],"date-time":"2023-05-12T00:00:00Z","timestamp":1683849600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Precise detection and localization of the Endotracheal tube (ETT) is essential for patients receiving chest radiographs. A robust deep learning model based on U-Net++ architecture is presented for accurate segmentation and localization of the ETT. Different types of loss functions related to distribution and region-based loss functions are evaluated in this paper. Then, various integrations of distribution and region-based loss functions (compound loss function) have been applied to obtain the best intersection over union (IOU) for ETT segmentation. The main purpose of the presented study is to maximize IOU for ETT segmentation, and also minimize the error range that needs to be considered during calculation of distance between the real and predicted ETT by obtaining the best integration of the distribution and region loss functions (compound loss function) for training the U-Net++ model. We analyzed the performance of our model using chest radiograph from the Dalin Tzu Chi Hospital in Taiwan. The results of applying the integration of distribution-based and region-based loss functions on the Dalin Tzu Chi Hospital dataset show enhanced segmentation performance compared to other single loss functions. Moreover, according to the obtained results, the combination of Matthews Correlation Coefficient (MCC) and Tversky loss functions, which is a hybrid loss function, has shown the best performance on ETT segmentation based on its ground truth with an IOU value of 0.8683.<\/jats:p>","DOI":"10.3389\/frai.2023.1181812","type":"journal-article","created":{"date-parts":[[2023,5,12]],"date-time":"2023-05-12T06:40:12Z","timestamp":1683873612000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["A robust approach for endotracheal tube localization in chest radiographs"],"prefix":"10.3389","volume":"6","author":[{"given":"Chung-Chian","family":"Hsu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rasoul","family":"Ameri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chih-Wen","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia-Shiang","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meghdad","family":"Biyari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atefeh","family":"Yarahmadi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shahab S.","family":"Band","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tin-Kwang","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen-Lin","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2023,5,12]]},"reference":[{"key":"B1","first-page":"171","article-title":"\u201cX-ray computed tomography and nanomaterials as contrast agents for tumor diagnosis,\u201d","volume-title":"Bionanotechnology in Cancer","author":"Aswathy","year":"2023"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2003.09424","article-title":"Coronavirus (COVID-19) classification using CT images by machine learning methods","author":"Barstugan","year":"2020","journal-title":"arXiv preprint arXiv:2003.09424"},{"key":"B3","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1016\/S0149-7944(99)00159-2","article-title":"The utilization of directed clinical evaluation to eliminate routine daily chest X-rays in intensive care unit patients","volume":"56","author":"Brengman","year":"1999","journal-title":"Curr. Surg"},{"key":"B4","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1016\/j.acra.2022.04.022","article-title":"Automated endotracheal tube placement check using semantically embedded deep neural networks","volume":"30","author":"Brown","year":"2022","journal-title":"Acad. Radiol"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.1007\/s00521-015-1916-x","article-title":"Efficient and robust deep learning with correntropy-induced loss function","volume":"27","author":"Chen","year":"2016","journal-title":"Neural Comput. Appl"},{"key":"B6","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1177\/175045890801800301","article-title":"Tracheal intubation, tracheal tubes and laryngeal mask airways","volume":"18","author":"Chethan","year":"2008","journal-title":"J. Perioperat. Practice"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2352\/J.ImagingSci.Technol.2020.64.2.020508","article-title":"Medical image segmentation based on u-net: A review","volume":"64","author":"Du","year":"2020","journal-title":"J. Imag. Sci. Technol"},{"key":"B8","doi-asserted-by":"crossref","DOI":"10.5220\/0010304005610568","article-title":"\u201cOn power Jaccard losses for semantic segmentation,\u201d","volume-title":"VISAPP 2021: 16th International Conference on Computer Vision Theory and Applications","author":"Duque-Arias","year":"2021"},{"key":"B9","first-page":"784","article-title":"\u201cEndotracheal tube detection and segmentation in chest radiographs using synthetic data,\u201d","volume-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"Frid-Adar","year":"2019"},{"key":"B10","doi-asserted-by":"publisher","first-page":"563","DOI":"10.2214\/AJR.10.7226","article-title":"Chest radiography in the ICU: Part 1, Evaluation of airway, enteric, and pleural tubes","volume":"198","author":"Godoy","year":"2012","journal-title":"Am. J. Roentgenol"},{"key":"B11","doi-asserted-by":"publisher","first-page":"433","DOI":"10.2214\/ajr.127.3.433","article-title":"Radiographic evaluation of endotracheal tube position","volume":"127","author":"Goodman","year":"1976","journal-title":"Am. J. Roentgenol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"846","DOI":"10.1007\/s10278-021-00495-6","article-title":"Measurement of endotracheal tube positioning on chest X-Ray using object detection","volume":"34","author":"Harris","year":"2021","journal-title":"J. Digit. Imag"},{"key":"B13","first-page":"770","article-title":"\u201cDeep residual learning for image recognition,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"He","year":"2016"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1107","DOI":"10.1378\/chest.06-3014","article-title":"A web-based Delphi study on the indications of chest radiographs for patients in ICUs","volume":"133","author":"Hejblum","year":"2008","journal-title":"Chest"},{"key":"B15","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/0899-7071(95)00097-6","article-title":"Chest radiography in the ICU","volume":"21","author":"Henschke","year":"1997","journal-title":"Clin. Imag"},{"key":"B16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/CIBCB48159.2020.9277638","article-title":"\u201cA survey of loss functions for semantic segmentation,\u201d","volume-title":"2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","author":"Jadon","year":"2020"},{"key":"B17","unstructured":"Jarrel SeahJ.\n            MaggieM. L.\n            SarahD.\n          RANZCR CLiP\u2014Catheter and Line Position Challenge2023"},{"key":"B18","doi-asserted-by":"publisher","first-page":"898","DOI":"10.1007\/s10278-021-00463-0","article-title":"Identification and localization of endotracheal tube on chest radiographs using a cascaded convolutional neural network approach","volume":"34","author":"Kara","year":"2021","journal-title":"J. Digit. Imag"},{"key":"B19","first-page":"355","article-title":"\u201cProbabilistic anchor assignment with iou prediction for object detection,\u201d","volume-title":"European Conference on Computer Vision","author":"Kim","year":"2020"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2104.09752","article-title":"Flow-based video segmentation for human head and shoulders","author":"Kuang","year":"2021","journal-title":"arXiv preprint arXiv:"},{"key":"B21","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1007\/s10278-017-9980-7","article-title":"Deep convolutional neural networks for endotracheal tube position and X-ray image classification: Challenges and opportunities","volume":"30","author":"Lakhani","year":"2017","journal-title":"J. Digit. Imag"},{"key":"B22","doi-asserted-by":"publisher","first-page":"21002","DOI":"10.48550\/arXiv.2006.04388","article-title":"Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection","volume":"33","author":"Li","year":"2020","journal-title":"Adv. Neural Inform. Process. Syst"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1913","DOI":"10.3390\/diagnostics12081913","article-title":"Detecting endotracheal tube and carina on portable supine chest radiographs using one-stage detector with a coarse-to-fine attention","volume":"12","author":"Mao","year":"2022","journal-title":"Diagnostics"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2011.05746","article-title":"Classification of COVID-19 in chest CT images using convolutional support vector machines","author":"\u00d6zkaya","year":"2020","journal-title":"arXiv preprint arXiv:2011.05746"},{"key":"B25","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1002\/ima.22469","article-title":"Classification of Coronavirus (COVID-19) from X-ray and CT images using shrunken features","volume":"31","author":"\u00d6zt\u00fcrk","year":"2021","journal-title":"Int. J. Imag. Syst. Technol"},{"key":"B26","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1111\/j.1365-2044.2012.07075.x","article-title":"Difficult Airway Society Guidelines for the management of tracheal extubation","volume":"67","author":"Popat","year":"2012","journal-title":"Anaesthesia"},{"key":"B27","first-page":"10428","article-title":"\u201cDesigning network design spaces,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Radosavovic","year":"2020"},{"key":"B28","doi-asserted-by":"publisher","first-page":"e0261307","DOI":"10.1371\/journal.pone.0261307","article-title":"Novel loss functions for ensemble-based medical image classification","volume":"16","author":"Rajaraman","year":"2021","journal-title":"PLoS ONE"},{"key":"B29","first-page":"234","article-title":"\u201cU-net: Convolutional networks for biomedical image segmentation,\u201d","volume-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"Ronneberger","year":"2015"},{"key":"B30","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1007\/978-3-319-67389-9_44","article-title":"\u201cTversky loss function for image segmentation using 3D fully convolutional deep networks,\u201d","volume-title":"International Workshop on Machine Learning in Medical Imaging","author":"Salehi","year":"2017"},{"key":"B31","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1097\/RTI.0000000000000608","article-title":"Using deep learning segmentation for endotracheal tube position assessment","volume":"37","author":"Schultheis","year":"2022","journal-title":"J. Thoracic Imag"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1801.05912","article-title":"On the influence of Dice loss function in multi-class organ segmentation of abdominal CT using 3D fully convolutional networks","author":"Shen","year":"2018","journal-title":"arXiv preprint arXiv:1801.05912"},{"key":"B33","doi-asserted-by":"publisher","first-page":"W63","DOI":"10.1097\/RTI.0000000000000174","article-title":"ACR Appropriateness Criteria\u00ae intensive care unit patients","volume":"30","author":"Suh","year":"2015","journal-title":"J. Thoracic Imag"},{"key":"B34","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-030-00889-5_1","article-title":"\u201cUnet++: A nested u-net architecture for medical image segmentation,\u201d","volume-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support","author":"Zhou","year":"2018"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1109\/TMI.2019.2959609","article-title":"Unet++: Redesigning skip connections to exploit multiscale features in image segmentation","volume":"39","author":"Zhou","year":"2019","journal-title":"IEEE Trans. Med. Imag"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1181812\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,12]],"date-time":"2023-05-12T06:40:27Z","timestamp":1683873627000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1181812\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,12]]},"references-count":35,"alternative-id":["10.3389\/frai.2023.1181812"],"URL":"https:\/\/doi.org\/10.3389\/frai.2023.1181812","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,12]]},"article-number":"1181812"}}