Alimiri Dehbaghi Hanieh, Khoshgard Karim, Sharini Hamid, Khairabadi Samira Jafari
Department of Medical Physics, Student Research Committee, University of Medical Sciences, Kermanshah, Iran.
Department of Medical Physics, University of Medical Sciences, Kermanshah, Iran.
J Res Med Sci. 2024 Dec 31;29:77. doi: 10.4103/jrms.jrms_847_23. eCollection 2024.
The initial assessment of trauma is a time-consuming and challenging task. The purpose of this research is to examine the diagnostic effectiveness and usefulness of machine learning models paired with radiomics features to identify blunt traumatic liver injury in abdominal computed tomography (CT) images.
In this study, 600 CT scan images of people with mild and severe liver damage due to trauma and healthy people were collected from the Kaggle dataset. The axial images were segmented by an experienced radiologist, and radiomics features were extracted from each region of interest. Initially, 30 machine learning models were implemented, and finally, three machine learning models were selected including Light Gradient-Boosting Machine (LGBM), Ridge Classifier, and Extreme Gradient Boosting (XGBoost), and their performance was examined in more detail.
The two criteria of precision and specificity of LGBM and XGBoost models in diagnosing mild liver injury were calculated to be 100%. Only 6.00% of cases were misdiagnosed by the LGBM model. The LGBM model achieved 100% sensitivity and 99.00% accuracy in diagnosing severe liver injury. The area under the receiver operating characteristic curve value and precision of this model were also calculated to be 99.00% and 98.00%, respectively.
The artificial intelligence models used in this study have great potential to improve patient care by assisting radiologists and other physicians in diagnosing and staging trauma-related liver injuries. These models can help prioritize positive studies, allow more rapid evaluation, and identify more severe injuries that may require immediate intervention.
创伤的初步评估是一项耗时且具有挑战性的任务。本研究的目的是检验机器学习模型与放射组学特征相结合在腹部计算机断层扫描（CT）图像中识别钝性创伤性肝损伤的诊断有效性和实用性。
在本研究中，从Kaggle数据集中收集了600例因创伤导致轻度和重度肝损伤患者以及健康人的CT扫描图像。轴向图像由经验丰富的放射科医生进行分割，并从每个感兴趣区域提取放射组学特征。最初，实施了30种机器学习模型，最后选择了三种机器学习模型，包括轻梯度提升机（LGBM）、岭分类器和极端梯度提升（XGBoost），并对其性能进行了更详细的检验。
LGBM和XGBoost模型在诊断轻度肝损伤时的精度和特异性这两个标准计算得出均为100%。LGBM模型仅误诊了6.00%的病例。LGBM模型在诊断重度肝损伤时的灵敏度达到100%，准确率达到99.00%。该模型的受试者工作特征曲线下面积值和精度也分别计算得出为99.00%和98.00%。
本研究中使用的人工智能模型在协助放射科医生和其他医生诊断和分期创伤相关肝损伤方面具有巨大潜力，可改善患者护理。这些模型有助于对阳性研究进行优先级排序，实现更快速的评估，并识别可能需要立即干预的更严重损伤。
