文献速递脊柱脊髓外科

深度学习模型在颈椎X线片上检测颈髓压迫的性能对比研究

Performance comparison between a deep learning model and spine surgeons in detecting cervical spinal cord compression on radiographs.
PubMed 文献 · J Neurosurg Spine · 2026-05-22

该回顾性研究开发了一种基于颈椎X线片的深度学习模型,用于检测颈髓压迫,并与两名脊柱外科医生的诊断性能进行比较,以MRI为金标准。内部测试集显示模型准确率达94.67%,AUC为0.9911,显著优于两名外科医生(准确率69.09%和71.18%,p<0.05)。外部测试集模型准确率为93.33%,AUC为0.9868。

要点

  • 深度学习模型在颈椎X线片上检测颈髓压迫的准确率显著高于脊柱外科医生。
  • 模型在外部测试集中保持较高准确率,显示较好泛化能力。
  • Grad-CAM可视化显示模型关注椎间盘、椎间孔和小关节区域。

核心结论

  • 深度学习模型在颈椎X线片上检测颈髓压迫的性能优于脊柱外科医生,有望用于临床诊断尤其是资源有限或偏远地区。

研究设计与样本

  • 回顾性研究,纳入连续住院患者,训练集480例、验证集60例、内部测试集60例,外部测试集60例来自另一中心。
  • 以MRI为金标准判定颈髓压迫,模型基于X线片训练,包括分割定位算法和二元分类,并用Grad-CAM可视化。

主要发现

  • 内部测试集模型准确率94.67%,AUC 0.9911;两名外科医生准确率分别为69.09%和71.18%,差异有统计学意义(p<0.05)。
  • 外部测试集模型准确率93.33%,AUC 0.9868。
  • 模型、读者1和读者2与参考标准的kappa系数分别为0.893、0.378和0.422。
  • Grad-CAM显示模型高特征密度区域位于椎间盘、椎间孔和小关节。

临床怎么用

  • 该模型可辅助在颈椎X线片上检测颈髓压迫并定位受累节段,提高检出率,适用于资源有限或偏远地区筛查。

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)。

原文

OBJECTIVE: This study aimed to develop a deep learning (DL) model for the detection of cervical spinal cord compression on cervical radiographs and compare its performance with spine surgeons. METHODS: The authors conducted a retrospective study on consecutive hospitalized patients who underwent cervical spine radiography and MRI at their center. Data from 600 patients were randomly divided into the training (n = 480), validation (n = 60), and internal test (n = 60) sets. Additionally, patients from another center were included as an external test set (n = 60). MR images were used as the gold standard for determining the presence of cervical segmental compression. The model was trained on cervical radiographs, where a segmentation-based localization algorithm was first developed to identify cervical segments, followed by a binary classification to diagnose spinal cord compression. Furthermore, the gradient-weighted class activation mapping (Grad-CAM) was used to visualize the area with high feature densities extracted by the model. Model performance was evaluated based on accuracy, sensitivity, specificity, F1 score, and area under the receiver operating characteristic curve (AUC), and compared to the diagnoses of two spine surgeons. RESULTS: In the internal test set, the model achieved 94.67% accuracy and an AUC of 0.9911, significantly outperforming the two spine surgeons (69.09% and 71.18% accuracy, p < 0.05). In the external test set, the model achieved 93.33% accuracy with an AUC of 0.9868. Compared to the reference standard, the kappa coefficients for the model, reader 1, and reader 2 were 0.893, 0.378, and 0.422, respectively. Grad-CAM showed high feature density in the intervertebral discs, intervertebral foramina, and facet joints. CONCLUSIONS: The DL model developed in this study achieved binary classification of cervical spinal cord compression and localized the affected segments on cervical radiographs, demonstrating superior diagnostic performance to that of spine surgeons. This DL model ensures high detection rates for cervical spinal cord compression and holds promise for clinical diagnosis, particularly in resource-limited or remote settings.

来源:J Neurosurg Spine,查看原文。版权归原作者所有。

引用

  1. Chen R, Liang M, Zhang Y, et al. Performance comparison between a deep learning model and spine surgeons in detecting cervical spinal cord compression on radiographs. J Neurosurg Spine. 2026. PMID: 42172670. doi:10.3171/2026.1.SPINE251409

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。