{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T20:25:24Z","timestamp":1791923124144,"version":"4.3.4"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T00:00:00Z","timestamp":1748304000000},"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. Physiol."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Emergency rescue scenes and pre-hospital emergency stages commonly encounter trauma victims. Life-saving measures must be taken at the scene if a trauma patient has pneumothorax; if the patient is not evaluated and diagnosed right away, their life may be in jeopardy. Ultrasound, which has the advantages of being non-invasive, non-radioactive, portable, rapid, and repeatable, can be used to diagnose pneumothorax. However, those who interpret ultrasound images must undergo extensive, specialized, and rigorous training. Deep learning technology allows for the intelligent diagnosis of ultrasound images, allowing general healthcare professionals to quickly and with minimal training diagnose pneumothorax in lung ultrasound patients.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Previous studies focused primarily on the lung-sliding characteristics of M-mode images, neglecting other key features in lung ultrasonography pneumothorax, and used similar technological techniques. Our study team used video understanding technology for medical ultrasound imaging diagnostics, training the TSM video understanding model on the ResNet50 network with 657 clips and testing the model with untrained 164 lung ultrasound clips.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The model\u2019s sensitivity was 99.21%, specificity was 89.19%, and average accuracy was 96.95%. The F1 score was 0.929, and the AUC was 0.97.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>This study is the first to apply video understanding models to the multi-feature fusion diagnosis of pneumothorax, demonstrating the feasibility of using video understanding technology in medical image diagnosis.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fphys.2025.1530808","type":"journal-article","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T04:10:38Z","timestamp":1748319038000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Use video comprehension technology to diagnose ultrasound pneumothorax like a doctor would"],"prefix":"10.3389","volume":"16","author":[{"given":"Xiaoyong","family":"Qiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanjun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Limei","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weibin","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,5,27]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1378\/chest.11-0131","article-title":"Test characteristics of ultrasonography for the detection of pneumothorax: a systematic review and meta-analysis","volume":"141","author":"Alrajhi","year":"2012","journal-title":"Chest"},{"key":"B2","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1197\/j.aem.2005.05.005","article-title":"A prospective comparison of supine chest radiography and bedside ultrasound for the diagnosis of traumatic pneumothorax","volume":"12","author":"Blaivas","year":"2005","journal-title":"Acad. Emerg. Med."},{"key":"B3","doi-asserted-by":"publisher","first-page":"249","DOI":"10.3390\/jimaging8090249","article-title":"Training ultrasound image classification deep-learning algorithms for pneumothorax detection using a synthetic tissue phantom apparatus","volume":"8","author":"Boice","year":"2022","journal-title":"J. Imaging"},{"key":"B4","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1016\/j.chest.2021.01.068","article-title":"Pulmonary critical care fellows\u2019 use of and self-reported barriers to learning bedside ultrasound during training: results of a national survey","volume":"160","author":"Brady","year":"2021","journal-title":"Chest"},{"key":"B5","first-page":"4724","article-title":"Quo vadis, action recognition? A new model and the kinetics dataset","author":"Carreira","year":"2017"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1212","DOI":"10.1007\/s00134-019-05710-1","article-title":"Speckle tracking quantification of lung sliding for the diagnosis of pneumothorax: a multicentric observational study","volume":"45","author":"Duclos","year":"2019","journal-title":"Intensive Care Med."},{"key":"B7","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1186\/s13017-019-0263-0","article-title":"Anatomical locations of air for rapid diagnosis of pneumothorax in blunt trauma patients","volume":"14","author":"Hefny","year":"2019","journal-title":"World J. Emerg. Surg."},{"key":"B8","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1016\/j.resuscitation.2007.06.033","article-title":"C.A.U.S.E.: cardiac arrest ultra-sound exam--a better approach to managing patients in primary non-arrhythmogenic cardiac arrest","volume":"76","author":"Hernandez","year":"2008","journal-title":"Resuscitation"},{"key":"B9","doi-asserted-by":"publisher","first-page":"6976","DOI":"10.3390\/app11156976","article-title":"Detecting the absence of lung sliding in lung ultrasounds using deep learning","volume":"11","author":"Ja\u0161\u010dur","year":"2021","journal-title":"Appl. Sci."},{"key":"B10","doi-asserted-by":"publisher","first-page":"205013","DOI":"10.1088\/1361-6560\/acfb70","article-title":"Point-of-care AI-assisted stepwise ultrasound pneumothorax diagnosis","volume":"68","author":"Kim","year":"2023","journal-title":"Phys. Med. and Biol."},{"key":"B11","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1007\/978-3-030-01045-4_8","article-title":"Ultrasound-based detection of lung abnormalities using single shot detection convolutional neural networks","volume-title":"Simulation, image processing, and ultrasound systems for assisted diagnosis and navigation","author":"Kulhare","year":"2018"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1659","DOI":"10.1378\/chest.14-1313","article-title":"BLUE-protocol and FALLS-protocol: two applications of lung ultrasound in the critically ill","volume":"147","author":"Lichtenstein","year":"2015","journal-title":"Chest"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1378\/chest.108.5.1345","article-title":"A bedside ultrasound sign ruling out pneumothorax in the critically III: lung sliding","volume":"108","author":"Lichtenstein","year":"1995","journal-title":"Chest"},{"key":"B14","first-page":"7082","article-title":"Temporal shift module for efficient video understanding","author":"Lin","year":"2019"},{"key":"B15","doi-asserted-by":"crossref","first-page":"723","DOI":"10.1007\/978-3-030-13469-3_84","article-title":"Automated pneumothorax diagnosis using deep neural networks","volume-title":"Progress in pattern recognition, image analysis, computer vision, and applications","author":"Lindsey","year":"2019"},{"key":"B16","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1007\/978-3-030-32875-7_9","article-title":"Deep learning-based pneumothorax detection in ultrasound videos","volume-title":"Smart ultrasound imaging and perinatal, preterm and paediatric image analysis","author":"Mehanian","year":"2019"},{"key":"B17","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1177\/000313481107700427","article-title":"Ultrasound detection of pneumothorax compared with chest X-ray and computed tomography scan","volume":"77","author":"Nagarsheth","year":"2011","journal-title":"Am. Surgeon\u2122"},{"key":"B18","doi-asserted-by":"publisher","first-page":"550","DOI":"10.3760\/cma.j.issn.1671-0282.2019.05.002","article-title":"Actively participating in the construction of trauma centers to accelerate the development of emergency medicine","volume":"28","author":"Qian","year":"2019","journal-title":"Chin. J. Emerg. Med."},{"key":"B19","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1186\/s41747-020-00152-7","article-title":"Deep learning detection and quantification of pneumothorax in heterogeneous routine chest computed tomography","volume":"4","author":"R\u00f6hrich","year":"2020","journal-title":"Eur. Radiol. Exp."},{"key":"B20","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1016\/j.ajem.2017.03.073","article-title":"Diagnostic accuracy of a novel software technology for detecting pneumothorax in a porcine model","volume":"35","author":"Summers","year":"2017","journal-title":"Am. J. Emerg. Med."},{"key":"B21","doi-asserted-by":"publisher","first-page":"e1002697","DOI":"10.1371\/journal.pmed.1002697","article-title":"Automated detection of moderate and large pneumothorax on frontal chest X-rays using deep convolutional neural networks: a retrospective study","volume":"15","author":"Taylor","year":"2018","journal-title":"PLoS Med."},{"key":"B22","doi-asserted-by":"publisher","first-page":"e200190","DOI":"10.1148\/ryai.2021200190","article-title":"Deep learning systems for pneumothorax detection on chest radiographs: a multicenter external validation study","volume":"3","author":"Thian","year":"2021","journal-title":"Radiol. Artif. Intell."},{"key":"B23","first-page":"4489","article-title":"Learning spatiotemporal features with 3D convolutional networks","author":"Tran","year":"2015"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1414","DOI":"10.1016\/j.ajem.2019.11.040","article-title":"Prevalence, documentation, and communication of incidental findings in focused assessment with sonography for trauma (FAST) examinations","volume":"38","author":"Valenzuela","year":"2020","journal-title":"Am. J. Emerg. Med."},{"key":"B25","doi-asserted-by":"publisher","first-page":"105953","DOI":"10.1016\/j.compbiomed.2022.105953","article-title":"Accurate assessment of the lung sliding artefact on lung ultrasonography using a deep learning approach","volume":"148","author":"VanBerlo","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"B26","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.rmed.2018.06.018","article-title":"Diagnostic chest ultrasound for acute respiratory failure","volume":"141","author":"Wallbridge","year":"2018","journal-title":"Respir. Med."},{"key":"B27","first-page":"178","volume-title":"Clinical diagnostics","author":"Wan","year":"2015"},{"key":"B28","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","article-title":"Temporal segment networks: towards good practices for deep action recognition","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Wang","year":"2016"},{"key":"B29","unstructured":"Non-local neural networks\n          \n          \n            \n              Wang\n              X.\n            \n            \n              Girshick\n              R.\n            \n            \n              Gupta\n              A.\n            \n            \n              He\n              K.\n            \n          \n          \n          2018"},{"key":"B30","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1016\/j.radcr.2020.12.034","article-title":"Dramatic complication of pneumothorax treatment requiring lifesaving open-heart surgery","volume":"16","author":"Weissman","year":"2021","journal-title":"Radiol. Case Rep."},{"key":"B31","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1007\/978-3-030-01267-0_19","article-title":"Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Xie","year":"2018"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1239","DOI":"10.3969\/j.issn.1002-0101.2023.11.013","article-title":"Application value of lung ultrasound pleural effusion diagnosis process and three-point localization method guided pleural effusion puncture","volume":"39","author":"Zhao","year":"","journal-title":"Chin. J. Ultrasound Med."},{"key":"B33","doi-asserted-by":"publisher","first-page":"892","DOI":"10.3969\/j.issn.1002-1949.2019.09.018","article-title":"Research progress on the value of bedside lung ultrasound in the diagnosis of pneumothorax","volume":"39","author":"Zhao","year":"","journal-title":"Chin. J. Emerg. Med."},{"key":"B34","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1007\/978-3-030-01246-5_49","article-title":"Temporal relational reasoning in videos","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Zhou","year":"2018"},{"key":"B35","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1007\/978-3-030-01216-8_43","article-title":"Efficient convolutional network for online video understanding","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Zolfaghari","year":"2018"}],"container-title":["Frontiers in Physiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2025.1530808\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T04:10:45Z","timestamp":1748319045000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2025.1530808\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,27]]},"references-count":35,"alternative-id":["10.3389\/fphys.2025.1530808"],"URL":"https:\/\/doi.org\/10.3389\/fphys.2025.1530808","relation":{},"ISSN":["1664-042X"],"issn-type":[{"value":"1664-042X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,27]]},"article-number":"1530808"}}