{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T12:29:42Z","timestamp":1782822582388,"version":"3.54.5"},"reference-count":34,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T00:00:00Z","timestamp":1751673600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000005","name":"U.S. Army Medical Research and Development Command","doi-asserted-by":"publisher","award":["IS220007"],"award-info":[{"award-number":["IS220007"]}],"id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science Education Programs at National Institutes of Health (NIH)","award":["IS220007"],"award-info":[{"award-number":["IS220007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Thoracic injuries account for a high percentage of combat casualty mortalities, with 80% of preventable deaths resulting from abdominal or thoracic hemorrhage. An effective method for detecting and triaging thoracic injuries is point-of-care ultrasound (POCUS), as it is a cheap and portable noninvasive imaging method. POCUS image interpretation of pneumothorax (PTX) or hemothorax (HTX) injuries requires a skilled radiologist, which will likely not be available in austere situations where injury detection and triage are most critical. With the recent growth in artificial intelligence (AI) for healthcare, the hypothesis for this study is that deep learning (DL) models for classifying images as showing HTX or PTX injury, or being negative for injury can be developed for lowering the skill threshold for POCUS diagnostics on the future battlefield. Three-class deep learning classification AI models were developed using a motion-mode ultrasound dataset captured in animal study experiments from more than 25 swine subjects. Cluster analysis was used to define the \u201cpopulation\u201d based on brightness, contrast, and kurtosis properties. A MobileNetV3 DL model architecture was tuned across a variety of hyperparameters, with the results ultimately being evaluated using images captured in real-time. Different hyperparameter configurations were blind-tested, resulting in models trained on filtered data having a real-time accuracy from 89 to 96%, as opposed to 78\u201395% when trained without filtering and optimization. The best model achieved a blind accuracy of 85% when inferencing on data collected in real-time, surpassing previous YOLOv8 models by 17%. AI models can be developed that are suitable for high performance in real-time for thoracic injury determination and are suitable for potentially addressing challenges with responding to emergency casualty situations and reducing the skill threshold for using and interpreting POCUS.<\/jats:p>","DOI":"10.3390\/jimaging11070222","type":"journal-article","created":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T02:53:07Z","timestamp":1751856787000},"page":"222","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Development of Deep Learning Models for Real-Time Thoracic Ultrasound Image Interpretation"],"prefix":"10.3390","volume":"11","author":[{"given":"Austin J.","family":"Ruiz","sequence":"first","affiliation":[{"name":"Organ Support and Automation Technologies Group, U.S. Army Institute of Surgical Research, JBSA Fort Sam Houston, San Antonio, TX 78234, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sofia I.","family":"Hern\u00e1ndez Torres","sequence":"additional","affiliation":[{"name":"Organ Support and Automation Technologies Group, U.S. Army Institute of Surgical Research, JBSA Fort Sam Houston, San Antonio, TX 78234, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0293-4937","authenticated-orcid":false,"given":"Eric J.","family":"Snider","sequence":"additional","affiliation":[{"name":"Organ Support and Automation Technologies Group, U.S. Army Institute of Surgical Research, JBSA Fort Sam Houston, San Antonio, TX 78234, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1007\/s11886-020-01394-y","article-title":"Point-of-Care Ultrasound","volume":"22","author":"Lee","year":"2020","journal-title":"Curr. Cardiol. Rep."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"S514","DOI":"10.1097\/TA.0b013e3182754654","article-title":"Thoracic Injuries in US Combat Casualties: A 10-Year Review of Operation Enduring Freedom and Iraqi Freedom","volume":"73","author":"Ivey","year":"2012","journal-title":"J. Trauma. Acute Care Surg."},{"key":"ref_3","unstructured":"Townsend, S., and Lasher, W. (2018). The U.S. Army in Multi-Domain Operations 2028, U.S. Army."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"S124","DOI":"10.1097\/TA.0000000000003308","article-title":"Point-of-Care Ultrasound for Treatment and Triage in Austere Military Environments","volume":"91","author":"Dubecq","year":"2021","journal-title":"J. Trauma. Acute Care Surg."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1016\/j.eng.2018.11.020","article-title":"Deep Learning in Medical Ultrasound Analysis: A Review","volume":"5","author":"Liu","year":"2019","journal-title":"Engineering"},{"key":"ref_6","unstructured":"Wang, Z. (2020). Deep Learning in Medical Ultrasound Image Segmentation: A Review. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Hernandez Torres, S.I., Ruiz, A., Holland, L., Ortiz, R., and Snider, E.J. (2024). Evaluation of Deep Learning Model Architectures for Point-of-Care Ultrasound Diagnostics. Bioengineering, 11.","DOI":"10.3390\/bioengineering11040392"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Hernandez Torres, S.I., Holland, L., Winter, T., Ortiz, R., Amezcua, K.-L., Ruiz, A., Thorpe, C.R., and Snider, E.J. (2025). Real-Time Deployment of Ultrasound Image Interpretation AI Models for Emergency Medicine Triage Using a Swine Model. Technologies, 13.","DOI":"10.3390\/technologies13010029"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.neucom.2020.04.157","article-title":"Convolutional Neural Networks for Medical Image Analysis: State-of-the-Art, Comparisons, Improvement and Perspectives","volume":"444","author":"Yu","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.patcog.2018.07.031","article-title":"Automated Pulmonary Nodule Detection in CT Images Using Deep Convolutional Neural Networks","volume":"85","author":"Xie","year":"2019","journal-title":"Pattern Recognit."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1016\/j.patcog.2016.05.029","article-title":"Multi-Crop Convolutional Neural Networks for Lung Nodule Malignancy Suspiciousness Classification","volume":"61","author":"Shen","year":"2017","journal-title":"Pattern Recognit."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Boccatonda, A. (2022). Emergency Ultrasound: Is It Time for Artificial Intelligence?. J. Clin. Med., 11.","DOI":"10.3390\/jcm11133823"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Kim, S., Fischetti, C., Guy, M., Hsu, E., Fox, J., and Young, S.D. (2024). Artificial Intelligence (AI) Applications for Point of Care Ultrasound (POCUS) in Low-Resource Settings: A Scoping Review. Diagnostics, 14.","DOI":"10.3390\/diagnostics14151669"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"78","DOI":"10.24908\/pocus.v7iKidney.15345","article-title":"Machine Learning in Point of Care Ultrasound","volume":"7","author":"Sonko","year":"2022","journal-title":"POCUS J."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Cheng, C.-T., Ooyang, C.-H., Liao, C.-H., and Kang, S.-C. (2025). Applications of Deep Learning in Trauma Radiology: A Narrative Review. Biomed. J., 48.","DOI":"10.1016\/j.bj.2024.100743"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Diaz-Escobar, J., Ord\u00f3\u00f1ez-Guill\u00e9n, N.E., Villarreal-Reyes, S., Galaviz-Mosqueda, A., Kober, V., Rivera-Rodriguez, R., and Rizk, J.E.L. (2021). Deep-Learning Based Detection of COVID-19 Using Lung Ultrasound Imagery. PLoS ONE, 16.","DOI":"10.1371\/journal.pone.0255886"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Huang, S., Yang, J., Fong, S., and Zhao, Q. (2021). Artificial Intelligence in the Diagnosis of COVID-19: Challenges and Perspectives. Int. J. Biol. Sci., 17.","DOI":"10.7150\/ijbs.58855"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Kim, K., Macruz, F., Wu, D., Bridge, C., McKinney, S., Al Saud, A.A., Sharaf, E., Sesic, I., Pely, A., and Danset, P. (2023). Point-of-Care AI-Assisted Stepwise Ultrasound Pneumothorax Diagnosis. Phys. Med. Biol., 68.","DOI":"10.1088\/1361-6560\/acfb70"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1097\/TA.0000000000003845","article-title":"Detection of Pneumothorax on Ultrasound Using Artificial Intelligence","volume":"94","author":"Montgomery","year":"2023","journal-title":"J. Trauma. Acute Care Surg."},{"key":"ref_20","first-page":"15675","article-title":"MobilePTX: Sparse Coding for Pneumothorax Detection Given Limited Training Examples","volume":"37","author":"Hannan","year":"2023","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Hernandez Torres, S.I., Holland, L., Edwards, T.H., Venn, E.C., and Snider, E.J. (2024). Deep Learning Models for Interpretation of Point of Care Ultrasound in Military Working Dogs. Front. Vet. Sci., 11.","DOI":"10.3389\/fvets.2024.1374890"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Snider, E.J., Hernandez-Torres, S.I., and Boice, E.N. (2022). An Image Classification Deep-Learning Algorithm for Shrapnel Detection from Ultrasound Images. Sci. Rep., 12.","DOI":"10.1038\/s41598-022-12367-2"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. arXiv.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_24","unstructured":"Redmon, J., and Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1007\/BF02834632","article-title":"Mahalanobis Distance","volume":"4","author":"McLachlan","year":"1999","journal-title":"Resonance"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L.-C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (November, January 27). Searching for MobileNetV3. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref_27","unstructured":"Keskar, N., Mudigere, D., Nocedal, J., Smelyanskiy, M., and Tang, P. (2016). On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. arXiv.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_29","unstructured":"Yaseen, M. (2024). What Is YOLOv8: An In-Depth Exploration of the Internal Features of the Next-Generation Object Detector. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-Cam: Visual Explanations from Deep Networks via Gradient-Based Localization. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"e26","DOI":"10.23915\/distill.00026","article-title":"Exploring Bayesian Optimization","volume":"5","author":"Agnihotri","year":"2020","journal-title":"Distill"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Frazier, P.I. (2018). A Tutorial on Bayesian Optimization. arXiv.","DOI":"10.1287\/educ.2018.0188"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"362","DOI":"10.1016\/j.chest.2024.02.011","article-title":"Automated Real-Time Detection of Lung Sliding Using Artificial Intelligence: A Prospective Diagnostic Accuracy Study","volume":"166","author":"Fiedler","year":"2024","journal-title":"Chest"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Ja\u0161\u010dur, M., Bundzel, M., Mal\u00edk, M., Dzian, A., Feren\u010d\u00edk, N., and Babi\u010d, F. (2021). Detecting the Absence of Lung Sliding in Lung Ultrasounds Using Deep Learning. Appl. Sci., 11.","DOI":"10.3390\/app11156976"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/7\/222\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:05:06Z","timestamp":1760033106000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/7\/222"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,5]]},"references-count":34,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["jimaging11070222"],"URL":"https:\/\/doi.org\/10.3390\/jimaging11070222","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,5]]}}}