Automated Measurement of Lumbar Lordosis on Radiographs Using Machine Learning and Computer Vision
Automated Measurement of Lumbar Lordosis on Radiographs Using Machine Learning and Computer Vision
复制标题
DOI：
10.1177/2192568219868190
复制
发表时间：
2019-08-13
影响因子：
2.4
通讯作者：
Cho, Samuel K.
中科院分区：
文献类型：
--
作者：
Cho, Brian H.;Kaji, Deepak;Cho, Samuel K.
研究设计：横断面数据库研究。目的：开发全自动人工智能和计算机视觉流程，用于辅助评估腰椎前凸。方法：使用侧位腰椎 X 光片来开发分割神经网络 (n = 629)。综合增强后，这些射线照片中的 70% 用于网络训练，其余 30% 用于超参数优化。在分段的射线照片上部署计算机视觉算法来计算腰椎前凸角度。使用一组射线照片测试来评估整个管道的有效性（n = 151）。结果：U-Net 分割的测试数据集 dice 得分为 0.821，接收者操作曲线下面积为 0.914，准确度为 0.862。计算机视觉算法在 84.1% 的测试集上识别出 L1 和 S1 椎骨，平均速度为 0.14 秒/射线照片。从 151 张测试集 X 光照片中，随机选择 50 张进行外科医生测量。与这些测量值相比，我们的算法实现了 8.055 度的平均绝对误差和 6.965 度的中值绝对误差（不具有统计显着性，P > .05）。结论：这项研究首次在组合管道中使用人工智能和计算机视觉来快速测量矢状骨盆参数，而无需外科医生事先手动输入。该管道测量的角度与外科医生手动测量的角度没有统计学上的显着差异。该管道以辅助能力提供临床实用性，未来的工作应侧重于提高分段网络性能。
Study Design: Cross sectional database study. Objective: To develop a fully automated artificial intelligence and computer vision pipeline for assisted evaluation of lumbar lordosis. Methods: Lateral lumbar radiographs were used to develop a segmentation neural network (n = 629). After synthetic augmentation, 70% of these radiographs were used for network training, while the remaining 30% were used for hyperparameter optimization. A computer vision algorithm was deployed on the segmented radiographs to calculate lumbar lordosis angles. A test set of radiographs was used to evaluate the validity of the entire pipeline (n = 151). Results: The U-Net segmentation achieved a test dataset dice score of 0.821, an area under the receiver operating curve of 0.914, and an accuracy of 0.862. The computer vision algorithm identified the L1 and S1 vertebrae on 84.1% of the test set with an average speed of 0.14 seconds/radiograph. From the 151 test set radiographs, 50 were randomly chosen for surgeon measurement. When compared with those measurements, our algorithm achieved a mean absolute error of 8.055 degrees and a median absolute error of 6.965 degrees (not statistically significant, P > .05). Conclusion: This study is the first to use artificial intelligence and computer vision in a combined pipeline to rapidly measure a sagittal spinopelvic parameter without prior manual surgeon input. The pipeline measures angles with no statistically significant differences from manual measurements by surgeons. This pipeline offers clinical utility in an assistive capacity, and future work should focus on improving segmentation network performance.