Objective: A deep learning-based method for evaluating the quality of pediatric pelvic X-ray images is proposed to construct a diagnostic model and verify its clinical feasibility.
Methods: Three thousand two hundred and forty-seven children with anteroposteric pelvic radiographs are retrospectively collected and randomly divided into training datasets, validation datasets and test datasets. Artificial intelligence model is conducted to evaluate the reliability of quality control model.
Results: The diagnostic accuracy, area under ROC curve, sensitivity and specificity of the model are 99.4%, 0.993, 98.6% and 100.0%, respectively. The 95% consistency limit of the pelvic tilt index of the model is -0.052-0.072. The 95% consistency threshold of pelvic rotation index is -0.088-0.055.
Conclusion: This is the first attempt to apply AI algorithm to the quality assessment of children's pelvic radiographs, and has significantly improved the diagnosis and treatment status of DDH in children.
目的: 提出一种基于深度学习的儿童骨盆正位X线片质量评估方法，构建诊断模型并验证其临床可行性。.
方法: 回顾性收集3 247例儿童骨盆正位X线片，随机分为训练数据集、验证数据集及测试数据集。构建人工智能模型，评估质量控制模型可靠性。.
结果: 模型的诊断准确率、ROC曲线下面积、灵敏度及特异度分别为99.4%、0.993、98.6%和100.0%。模型的骨盆倾斜指数95%一致性界限为−0.052~0.072；骨盆旋转指数95%一致性界限为−0.088~0.055。.
结论: 该研究首次尝试将AI算法应用于儿童骨盆X线片的质量评估，并显著改善了儿童发育性髋关节发育不良的诊疗现状。.
Keywords: artificial intelligence; developmental dysplasia of the hip (DDH); pelvic X-ray images; software.