PDF(Pubmed)
Abstract：
OBJECTIVE: To construct and evaluate the efficacy of a deep learning system to rapidly and automatically locate six vertebral landmarks, which are used to measure vertebral body heights, and to output spine angle measurements (lumbar lordosis angles [LLAs]) across multiple modalities.
METHODS: In this retrospective study, MR (n = 1123), CT (n = 137), and radiographic (n = 484) images were used from a wide variety of patient populations, ages, disease stages, bone densities, and interventions (n = 1744 total patients, 64 years ± 8, 76.8% women; images acquired 2005-2020). Trained annotators assessed images and generated data necessary for deformity analysis and for model development. A neural network model was then trained to output vertebral body landmarks for vertebral height measurement. The network was trained and validated on 898 MR, 110 CT, and 387 radiographic images and was then evaluated or tested on the remaining images for measuring deformities and LLAs. The Pearson correlation coefficient was used in reporting LLA measurements.
RESULTS: On the holdout testing dataset (225 MR, 27 CT, and 97 radiographic images), the network was able to measure vertebral heights (mean height percentage of error ± 1 standard deviation: MR images, 1.5% ± 0.3; CT scans, 1.9% ± 0.2; radiographs, 1.7% ± 0.4) and produce other measures such as the LLA (mean absolute error: MR images, 2.90°; CT scans, 2.26°; radiographs, 3.60°) in less than 1.7 seconds across MR, CT, and radiographic imaging studies.
CONCLUSIONS: The developed network was able to rapidly measure morphometric quantities in vertebral bodies and output LLAs across multiple modalities.Keywords: Computer Aided Diagnosis (CAD), MRI, CT, Spine, Demineralization-Bone, Feature Detection Supplemental material is available for this article. © RSNA, 2021.
METHODS: In this retrospective study, MR (n = 1123), CT (n = 137), and radiographic (n = 484) images were used from a wide variety of patient populations, ages, disease stages, bone densities, and interventions (n = 1744 total patients, 64 years ± 8, 76.8% women; images acquired 2005-2020). Trained annotators assessed images and generated data necessary for deformity analysis and for model development. A neural network model was then trained to output vertebral body landmarks for vertebral height measurement. The network was trained and validated on 898 MR, 110 CT, and 387 radiographic images and was then evaluated or tested on the remaining images for measuring deformities and LLAs. The Pearson correlation coefficient was used in reporting LLA measurements.
RESULTS: On the holdout testing dataset (225 MR, 27 CT, and 97 radiographic images), the network was able to measure vertebral heights (mean height percentage of error ± 1 standard deviation: MR images, 1.5% ± 0.3; CT scans, 1.9% ± 0.2; radiographs, 1.7% ± 0.4) and produce other measures such as the LLA (mean absolute error: MR images, 2.90°; CT scans, 2.26°; radiographs, 3.60°) in less than 1.7 seconds across MR, CT, and radiographic imaging studies.
CONCLUSIONS: The developed network was able to rapidly measure morphometric quantities in vertebral bodies and output LLAs across multiple modalities.Keywords: Computer Aided Diagnosis (CAD), MRI, CT, Spine, Demineralization-Bone, Feature Detection Supplemental material is available for this article. © RSNA, 2021.
摘要：
目的：构建和评估深度学习系统的功效，以快速自动定位六个椎骨标志，用来测量椎体高度，并输出多个模式的脊柱角度测量值（腰椎前凸角度[LLA]）。
方法：在这项回顾性研究中，MR（n=1123），CT(n=137),和放射学（n=484）图像来自各种各样的患者人群，年龄,疾病阶段，骨密度,和干预措施(n=1744名患者，64岁±8岁，76.8%的女性；2005-2020年获得的图像）。训练有素的注释者评估了畸形分析和模型开发所需的图像和生成的数据。然后训练神经网络模型以输出椎体标志以进行椎体高度测量。该网络在898MR上进行了训练和验证，110CT,和387张射线照相图像，然后在其余图像上进行评估或测试，以测量畸形和LLA。Pearson相关系数用于报告LLA测量。
结果：在保持测试数据集（225MR，27CT,和97张射线照相图像)，该网络能够测量椎骨高度(平均高度误差百分比±1标准偏差：MR图像，1.5%±0.3;CT扫描,1.9%±0.2；射线照片，1.7%±0.4)，并产生其他措施，如LLA(平均绝对误差：MR图像，2.90°;CT扫描,2.26°；射线照片，3.60°)在整个MR小于1.7秒内,CT,和射线成像研究。
结论：开发的网络能够快速测量椎体的形态计量学数量，并在多种模式下输出LLA。关键词:计算机辅助诊断(CAD),MRI,CT,脊椎,去矿质-骨,功能检测补充材料可用于本文。©RSNA,2021年。
方法：在这项回顾性研究中，MR（n=1123），CT(n=137),和放射学（n=484）图像来自各种各样的患者人群，年龄,疾病阶段，骨密度,和干预措施(n=1744名患者，64岁±8岁，76.8%的女性；2005-2020年获得的图像）。训练有素的注释者评估了畸形分析和模型开发所需的图像和生成的数据。然后训练神经网络模型以输出椎体标志以进行椎体高度测量。该网络在898MR上进行了训练和验证，110CT,和387张射线照相图像，然后在其余图像上进行评估或测试，以测量畸形和LLA。Pearson相关系数用于报告LLA测量。
结果：在保持测试数据集（225MR，27CT,和97张射线照相图像)，该网络能够测量椎骨高度(平均高度误差百分比±1标准偏差：MR图像，1.5%±0.3;CT扫描,1.9%±0.2；射线照片，1.7%±0.4)，并产生其他措施，如LLA(平均绝对误差：MR图像，2.90°;CT扫描,2.26°；射线照片，3.60°)在整个MR小于1.7秒内,CT,和射线成像研究。
结论：开发的网络能够快速测量椎体的形态计量学数量，并在多种模式下输出LLA。关键词:计算机辅助诊断(CAD),MRI,CT,脊椎,去矿质-骨,功能检测补充材料可用于本文。©RSNA,2021年。
