Medical Science
| Open Access |
DOI: Multimodal Analysis of Liver Injuries in Children with Road Traffic Injuries Using Artificial Intelligence and Digital Morphometry
Abstract
Road traffic injuries remain a major cause of morbidity and mortality among children and young people worldwide. Abdominal trauma associated with road traffic accidents may result in clinically significant liver injuries, ranging from minor parenchymal lesions to extensive lacerations and vascular damage. Early and accurate assessment of hepatic trauma is essential for selecting an appropriate treatment strategy and preventing complications. Conventional diagnostic approaches, including ultrasonography and computed tomography (CT), remain central to the evaluation of pediatric abdominal trauma; however, interpretation of complex imaging findings may be challenging, particularly in emergency settings. Recent advances in artificial intelligence (AI), medical image segmentation, radiomics, and digital morphometry provide opportunities for more objective and quantitative assessment of traumatic liver damage. This article reviews the potential role of AI-assisted multimodal analysis in children with liver injuries caused by road traffic accidents. Particular attention is given to automated liver segmentation, measurement of liver volume and injury dimensions, assessment of lesion morphology, radiomics-based characterization, and integration of imaging parameters with clinical data. Digital morphometry may complement conventional qualitative radiological interpretation by providing reproducible quantitative indicators of tissue damage. AI-based machine learning models have already demonstrated promising results in the identification of traumatic liver injuries on CT images, although most available evidence is derived from adult or mixed-age populations. Pediatric-specific validation remains necessary because anatomical proportions, imaging protocols, and clinical management differ from those of adults. A multimodal framework integrating clinical, laboratory, ultrasonographic, CT, and quantitative morphometric information could improve diagnostic consistency, support injury grading, facilitate monitoring, and potentially assist clinical decision-making. Nevertheless, issues related to data quality, radiation exposure, algorithmic bias, explainability, and external validation must be addressed before routine clinical implementation.
Keywords
Artificial intelligence, pediatric trauma, liver injury
References
World Health Organization. Road Traffic Injuries. WHO; 2023.
World Health Organization. Road Traffic Injuries: Children. WHO; 2023.
World Health Organization. Global Status Report on Road Safety 2023. Geneva: World Health Organization; 2023.
Notrica DM, Linnaus ME, et al. Updated APSA Guidelines for the Management of Blunt Liver and Spleen Injuries. Journal of Pediatric Surgery. 2023. doi:10.1016/j.jpedsurg.2023.03.012.
Coccolini F, Coimbra R, Ordonez C, et al. Liver trauma: WSES 2020 guidelines. World Journal of Emergency Surgery. 2020;15:24. doi:10.1186/s13017-020-00302-7.
Pegoraro F, Giusti G, Giacalone M, Parri N. Contrast-enhanced ultrasound in pediatric blunt abdominal trauma: a systematic review. Ultrasound Journal. 2022;25(3):419–427. doi:10.1007/s40477-021-00623-6.
American Association for the Surgery of Trauma. Organ Injury Scale Revisions: Liver, Spleen and Kidney—2018 Version. AAST Trauma Resources.
Dehbaghi HA, Khoshgard K, Sharini H, Jafari Khairabadi S. Diagnosis of traumatic liver injury on computed tomography using machine learning algorithms and radiomics features: The role of artificial intelligence for rapid diagnosis in emergency rooms. Journal of Research in Medical Sciences. 2024;29:77. doi:10.4103/jrms.jrms_847_23.
Teng Z, Li L, Xin Z, et al. A literature review of artificial intelligence (AI) for medical image segmentation: from AI and explainable AI to trustworthy AI. Quantitative Imaging in Medicine and Surgery. 2024;14(12):9620–9652. doi:10.21037/qims-24-723.
Christ PF, Ettlinger F, Grün F, et al. Automatic liver and tumor segmentation of CT and MRI volumes using cascaded fully convolutional neural networks. arXiv. 2017.
Download and View Statistics
Copyright License
Copyright (c) 2026 Dilso‘z Egamberdieva
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain the copyright of their manuscripts, and all Open Access articles are disseminated under the terms of the Creative Commons Attribution License 4.0 (CC-BY), which licenses unrestricted use, distribution, and reproduction in any medium, provided that the original work is appropriately cited. The use of general descriptive names, trade names, trademarks, and so forth in this publication, even if not specifically identified, does not imply that these names are not protected by the relevant laws and regulations.