文献速递骨肌技术与安全DRCTMR

AI辅助骨盆/髋部X线股骨颈骨折检测的多中心研究

Improving Recognition Performance and Reader Efficiency for Femoral-Neck Fracture Detection on Pelvic or Hip Radiographs Using Artificial Intelligence.
PubMed 文献 · Radiology · 2026-01-01

本研究开发并外部验证深度学习模型OccuNet,用于在骨盆或髋部X线片上检测股骨颈骨折。共纳入2576例疑髋部外伤成人患者,以同期CT或MRI为参考标准。结果显示OccuNet敏感度97.5%、特异度98.8%,并提高放射科与急诊科医师的敏感度和阅片效率。

要点

  • OccuNet对X线阴性或不明确股骨颈骨折敏感度达94.7%,高于放射科86.2%及急诊科68.8%。
  • AI辅助使放射科与急诊科医师敏感度分别由93.7%、84.3%升至97.2%、95.6%,阅片时间缩短14.9%、18.9%。
  • 模型在Garden I-II型等X线隐匿性骨折中仍有较高检出能力,可作为日常阅片辅助工具。

核心结论

  • OccuNet在骨盆或髋部X线片上对股骨颈骨折检测表现出优异性能,敏感度97.5%、特异度98.8%、AUC 0.99。
  • 在X线阴性或不明确(Garden I-II)股骨颈骨折中,模型敏感度为94.7%,高于放射科(86.2%)和急诊科医师(68.8%)。
  • AI辅助可提高放射科和急诊科医师的敏感度并缩短阅片时间,兼具临床效能与效率价值。

研究设计与样本

  • 多中心回顾性研究,纳入2009年1月至2025年8月四家医院2576例疑髋部外伤并接受骨盆或髋部X线及同期CT或MRI的成人患者。
  • 患者分为训练集、内部测试集和三个外部测试集。
  • 采用两阶段模型OccuNet:第一阶段使用同一X线片原始与伪影增强版本的对比预训练学习抗伪影特征,第二阶段微调骨折检测器。
  • 与10名阅片者(5名肌骨放射科医师、5名急诊科医师)比较诊断性能;参考标准为同期CT或MRI。

关键影像表现/征象

  • 研究重点为X线阴性或不明确股骨颈骨折,即X线片未能明确显示的骨折,需依靠CT或MRI确认。
  • 模型在X线伪影增强预训练后可学习抗伪影特征,适用于临床常见伪影干扰下的骨折检测。
  • AI辅助下阅片时间显著缩短,提示模型输出有助于快速定位可疑区域。

诊断标准与关键数值

  • 合并组(1766例)中,模型敏感度97.5%(913/936),特异度98.8%(820/830),AUC 0.99(95% CI: 0.99, 0.99)。
  • X线阴性或不明确骨折(189例)中,模型敏感度94.7%(179/189),高于放射科86.2%(163/189)和急诊科68.8%(130/189),均P < .001。
  • AI辅助下放射科医师敏感度由93.7%(877/936)升至97.2%(910/936,P < .001)。
  • AI辅助下急诊科医师敏感度由84.3%(789/936)升至95.6%(895/936,P < .001)。
  • AI辅助下放射科与急诊科医师平均阅片时间分别缩短14.9%与18.9%,均P < .001。

临床应用与阅片要点

  • 对X线报告未见明确骨折但临床高度怀疑股骨颈骨折的病例,可借助此类AI工具定位可疑区域并建议进一步CT或MRI检查。
  • AI模型对Garden I-II型隐匿性骨折的高敏感度可减少漏诊导致的延迟治疗与并发症。
  • AI辅助不仅提升低年资或非肌骨专科医师的敏感度,还缩短阅片时间,适合急诊和基层场景。
  • 临床应用时需将模型输出视为辅助定位工具,最终诊断应结合临床与参考标准。

局限性

  • 本研究为回顾性设计,可能存在选择偏倚,模型前瞻性临床应用价值尚需验证。
  • 患者来源于四家医院且集中于特定时间段,外部推广性受设备、体位、人口特征等影响。
  • 原文未报告不同骨折类型或非股骨颈骨折场景下的特异度与假阳性表现。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

Background Radiographs sometimes do not depict femoral-neck fractures, particularly radiograph-negative or indeterminate femoral-neck fractures, leading to delayed treatment and complications. Purpose To develop and externally evaluate a deep learning model, OccuNet, for detecting femoral-neck fractures on pelvic or hip radiographs, compare its performance and accuracy with those of radiologists and emergency medicine physicians, and evaluate its effect on reader performance and accuracy. Materials and Methods This multicenter retrospective study included adults suspected of having hip trauma who underwent pelvic or hip radiography and same-episode CT or MRI at four hospitals (January 2009-August 2025). Patients were split into a training set, an internal test set, and three external test sets. A two-stage model, OccuNet, was trained: Stage 1 used contrastive pretraining on paired original and artifact-augmented versions of the same radiograph to learn artifact-robust features, and stage 2 fine-tuned a fracture detector. Performance and accuracy were compared with those of 10 readers (five musculoskeletal radiologists, five emergency medicine physicians), and artificial intelligence (AI) assistance was tested for sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and reading time. Results This study included 2576 patients (mean age [±SD], 69 years ± 11.2; 1380 women). In the pooled group (n = 1766), the model achieved a sensitivity of 97.5% (913 of 936), specificity of 98.8% (820 of 830), and excellent performance (AUC, 0.99 [95% CI: 0.99, 0.99]). For radiograph-negative or indeterminate fractures (n = 189), sensitivity of the model (94.7% [179 of 189]) was higher than that of radiologists (86.2% [163 of 189]; P < .001) and emergency medicine physicians (68.8% [130 of 189]; P < .001). With AI assistance, radiologist and emergency medicine physician sensitivities increased from 93.7% (877 of 936) to 97.2% (910 of 936; P < .001) and from 84.3% (789 of 936) to 95.6% (895 of 936; P < .001), respectively, and mean reading times shortened by 14.9% and 18.9% (both P < .001), respectively. Conclusion OccuNet demonstrated excellent performance for femoral-neck fracture detection on pelvic or hip radiographs, maintained high sensitivity in radiograph-negative or indeterminate (Garden I-II) fractures, and improved reader sensitivity and efficiency.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Lin, Qian, Zhou, et al. Improving Recognition Performance and Reader Efficiency for Femoral-Neck Fracture Detection on Pelvic or Hip Radiographs Using Artificial Intelligence. Radiology. 2026. PMID: 42708850. doi:10.1148/radiol.253931

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。