Liu Yunxia, Liu Weifang, Chen Haipeng, Xie Sheng, Wang Ce, Liang Tian, Yu Yizhou, Liu Xiaoqing
Department of Radiology, The Third Medical Center of Chinese PLA General Hospital, Beijing, China.
Department of Radiology, Civil Aviation General Hospital, Beijing, China.
Quant Imaging Med Surg. 2023 Oct 1;13(10):6424-6433. doi: 10.21037/qims-23-428. Epub 2023 Sep 4.
Extremities fractures are a leading cause of death and disability, especially in the elderly. Avulsion fracture are also the most commonly missed diagnosis, and delayed diagnosis leads to higher litigation rates. Therefore, this study evaluates the diagnostic efficiency of the artificial intelligence (AI) model before and after optimization based on computed tomography (CT) images and then compares it with that of radiologists, especially for avulsion fractures.
The digital X-ray photography [digital radiography (DR)] and CT images of adult limb trauma in our hospital from 2017 to 2020 were retrospectively collected, with or without 1 or more fractures of the shoulder, elbow, wrist, hand, hip, knee, ankle, and foot. Labeling of the fracture referred to the visualization of the fracture on the corresponding CT images. After training the pre-optimized AI model, the diagnostic performance of the pre-optimized AI, optimized AI model, and the initial radiological reports were evaluated. For the lesion level, the detection rate of avulsion and non-avulsion fractures was analyzed, whereas for the case level, the accuracy, sensitivity, and specificity were compared among them.
The total datasets (1,035 cases) were divided into a training set (n=675), a validation set (n=169), and a test set (n=191) in a balanced joint distribution. At the lesion level, the detection rates of avulsion fracture (57.89% 35.09%, P=0.004) and non-avulsion fracture (85.64% 71.29%, P<0.001) by the optimized AI were significantly higher than that by pre-optimized AI. The average precision (AP) of the optimized AI model for all lesions was higher than that of pre-optimized AI model (0.582 0.425). The detection rate of avulsion fracture by the optimized AI model was significantly higher than that by radiologists (57.89% 29.82%, P=0.002). For the non-avulsion fracture, there was no significant difference of detection rate between the optimized AI model and radiologists (P=0.853). At the case level, the accuracy (86.40% 71.93%, P<0.001) and sensitivity (87.29% 73.48%, P<0.001) of the optimized AI were significantly higher than those of the pre-optimized AI model. There was no statistical difference in accuracy, sensitivity, and specificity between the optimized AI model and the radiologists (P>0.05).
The optimized AI model improves the diagnostic efficacy in detecting extremity fractures on radiographs, and the optimized AI model is significantly better than radiologists in detecting avulsion fractures, which may be helpful in the clinical practice of orthopedic emergency.
四肢骨折是导致死亡和残疾的主要原因，尤其是在老年人中。撕脱性骨折也是最常被漏诊的疾病，而延迟诊断会导致更高的诉讼率。因此，本研究基于计算机断层扫描（CT）图像评估优化前后人工智能（AI）模型的诊断效率，然后将其与放射科医生的诊断效率进行比较，尤其是针对撕脱性骨折。
回顾性收集我院2017年至2020年成人肢体创伤的数字X线摄影[数字X线摄影（DR）]和CT图像，包括有或无肩部、肘部、腕部、手部、髋部、膝部、踝部和足部一处或多处骨折的病例。骨折的标注参考相应CT图像上骨折的可视化情况。在训练预优化的AI模型后，评估预优化AI、优化后的AI模型以及初始放射学报告的诊断性能。在病变层面，分析撕脱性骨折和非撕脱性骨折的检出率，而在病例层面，比较它们之间的准确性、敏感性和特异性。
将总共1035例数据集以均衡的联合分布方式分为训练集（n = 675）、验证集（n = 169）和测试集（n = 191）。在病变层面，优化后的AI对撕脱性骨折（57.89%对35.09%，P = 0.004）和非撕脱性骨折（85.64%对71.29%，P < 0.001）的检出率显著高于预优化的AI。优化后的AI模型对所有病变的平均精度（AP）高于预优化的AI模型（0.582对(0.425)）。优化后的AI模型对撕脱性骨折的检出率显著高于放射科医生（57.89%对29.82%，P = 0.002）。对于非撕脱性骨折，优化后的AI模型与放射科医生的检出率无显著差异（P = 0.853）。在病例层面，优化后的AI的准确性（86.40%对71.93%，P < 0.001）和敏感性（87.29%对73.48%，P < 0.001）显著高于预优化的AI模型。优化后的AI模型与放射科医生在准确性、敏感性和特异性方面无统计学差异（P > 0.05）。
优化后的AI模型提高了在X线片上检测四肢骨折的诊断效能，且优化后的AI模型在检测撕脱性骨折方面明显优于放射科医生，这可能有助于骨科急诊的临床实践。
