基于人工智能的CT创伤性椎体骨折自动检测与稳定性分析
本研究纳入257例CT检查患者(463个骨折椎体、1883个非骨折椎体,其中190个不稳定骨折),开发并测试了用于椎体骨折自动检测与稳定性分析的神经网络。排除C1/2时,网络检测骨折的敏感度75.8%、特异度80.3%,判断稳定性的敏感度88.4%、特异度80.3%,骨折检测与稳定性分析的AUC分别为87%和91%。
要点
- 排除C1/2时,网络检测骨折敏感度75.8%、特异度80.3%,AUC 87%。
- 排除C1/2时,网络判断稳定性敏感度88.4%、特异度80.3%,AUC 91%。
- 排除C1/2时,全脊柱至少一处骨折的敏感度78.7%,至少一处不稳定骨折的敏感度97.2%。
核心结论
- 所开发的神经网络能自动检测椎体骨折并同时评估其稳定性,诊断性能较高。
研究设计与样本
- 经机构审查委员会(IRB)批准的研究,纳入257例接受CT检查的患者,含463个骨折椎体和1883个非骨折椎体,其中190个为不稳定骨折;由两名读者识别椎体骨折并评估稳定性;采用分层卷积神经网络(hNet)与骨折分类网络(fNet)组合构建神经网络,最终测试设置包括纳入C1/2水平和排除C1/2水平两种。
诊断标准与关键数值
- 排除C1/2时,网络区分骨折与非骨折椎体的敏感度75.8%、特异度80.3%。
- 排除C1/2时,网络判断椎体稳定性的敏感度88.4%、特异度80.3%。
- 排除C1/2时,骨折检测与稳定性分析的AUC分别为87%和91%。
- 排除C1/2时,网络提示全脊柱至少存在一处骨折的敏感度78.7%,提示至少存在一处不稳定骨折的敏感度97.2%。
局限性
- 原文未报告局限性。
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
PURPOSE: We developed and tested a neural network for automated detection and stability analysis of vertebral body fractures on computed tomography (CT).
MATERIALS AND METHODS: 257 patients who underwent CT were included in this Institutional Review Board (IRB) approved study. 463 fractured and 1883 non-fractured vertebral bodies were included, with 190 fractures unstable. Two readers identified vertebral body fractures and assessed their stability. A combination of a Hierarchical Convolutional Neural Network (hNet) and a fracture Classification Network (fNet) was used to build a neural network for the automated detection and stability analysis of vertebral body fractures on CT. Two final test settings were chosen: one with vertebral body levels C1/2 included and one where they were excluded.
RESULTS: The mean age of the patients was 68 ± 14 years. 140 patients were female. The network showed a slightly higher diagnostic performance when excluding C1/2. Accordingly, the network was able to distinguish fractured and non-fractured vertebral bodies with a sensitivity of 75.8 % and a specificity of 80.3 %. Additionally, the network determined the stability of the vertebral bodies with a sensitivity of 88.4 % and a specificity of 80.3 %. The AUC was 87 % and 91 % for fracture detection and stability analysis, respectively. The sensitivity of our network in indicating the presence of at least one fracture / one unstable fracture within the whole spine achieved values of 78.7 % and 97.2 %, respectively, when excluding C1/2.
CONCLUSION: The developed neural network can automatically detect vertebral body fractures and evaluate their stability concurrently with a high diagnostic performance.
引用
- Polzer C, Yilmaz E, Meyer C, et al. AI-based automated detection and stability analysis of traumatic vertebral body fractures on computed tomography. Eur J Radiol. 2024. PMID: 38364589. doi:10.1016/j.ejrad.2024.111364
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。