A deep learning system for automated, multi-modality 2D segmentation of vertebral bodies and intervertebral discs.
A deep learning system for automated, multi-modality 2D segmentation of vertebral bodies and intervertebral discs.
复制标题
DOI：
10.1016/j.bone.2021.115972
复制
发表时间：
2021-08
期刊：
影响因子：
4.1
通讯作者：
Rajapakse CS
中科院分区：
文献类型：
--
作者：
Suri A;Jones BC;Ng G;Anabaraonye N;Beyrer P;Domi A;Choi G;Tang S;Terry A;Leichner T;Fathali I;Bastin N;Chesnais H;Rajapakse CS
椎体骨折是骨质疏松症和其他骨骼疾病最常见的并发症之一。然而，旨在预测未来骨折和评估一般脊柱健康的研究必须在成像研究中手动描绘椎体和椎间盘，以进行进一步的放射组学分析。该研究旨在开发一种深度学习系统，可以在MR，CT和X射线成像研究中自动快速分割（描绘）椎骨和椎间盘。我们构建了一个神经网络来输出MR、CT和X射线成像研究的2D分割。我们在2005年至2020年的4490项MR、550项CT和1935项X射线成像研究（后数据增强）上训练了网络，这些研究涵盖了各种患者人群、骨骼疾病状态和年龄。使用5重交叉验证进行评估，该网络能够在椎体和椎间盘的所有模态中产生> 0.95的中值Dice分数（在MR/CT的最中心切片上和在X射线的图像上）。此外，从预测的分割掩模计算的放射组学特征（偏度、峰度、正值像素的平均值和熵）是高度准确的（当与地面实况相比时，所有放射组学特征的r ≥ 0.96）。在所有模态中，产生输出的平均时间< 1.7秒。我们的网络能够快速生成用于MR、CT和X射线成像研究的椎体和椎间盘分割。此外，从这些分割得到的放射组学量是高度准确的。由于该网络为这些常用的模式快速产生输出，因此可以立即用于评估脊柱健康的放射组学和临床成像研究。
Fractures in vertebral bodies are among the most common complications of osteoporosis and other bone diseases. However, studies that aim to predict future fractures and assess general spine health must manually delineate vertebral bodies and intervertebral discs in imaging studies for further radiomic analysis. This study aims to develop a deep learning system that can automatically and rapidly segment (delineate) vertebrae and discs in MR, CT, and X-ray imaging studies. We constructed a neural network to output 2D segmentations for MR, CT, and X-ray imaging studies. We trained the network on 4490 MR, 550 CT, and 1935 X-ray imaging studies (post-data augmentation) spanning a wide variety of patient populations, bone disease statuses, and ages from 2005–2020. Evaluated using 5-fold cross validation, the network was able to produce median Dice scores > 0.95 across all modalities for vertebral bodies and intervertebral discs (on the most central slice for MR/CT and on image for X-ray). Furthermore, radiomic features (skewness, kurtosis, mean of positive value pixels, and entropy) calculated from predicted segmentation masks were highly accurate (r ≥ 0.96 across all radiomic features when compared to ground truth). Mean time to produce outputs was < 1.7 seconds across all modalities. Our network was able to rapidly produce segmentations for vertebral bodies and intervertebral discs for MR, CT, and X-ray imaging studies. Furthermore, radiomic quantities derived from these segmentations were highly accurate. Since this network produced outputs rapidly for these modalities which are commonly used, it can be put to immediate use for radiomic and clinical imaging studies assessing spine health.
登录
查看更多内容
影响因子：
2.1
作者：
van der Walt, Stefan;Colbert, S. Chris;Varoquaux, Gael
通讯作者：
Varoquaux, Gael
影响因子：
8.9
作者：
Filograna, Laura;Lenkowicz, Jacopo;Valentini, Vincenzo
通讯作者：
Valentini, Vincenzo
影响因子：
2.1
作者：
Weaver, Jessica;Sajjan, Shiva;Harris, Steven T.
通讯作者：
Harris, Steven T.
影响因子：
3.9
作者：
Hwang, Eo-Jin;Kim, Sanghee;Jung, Joon-Yong
通讯作者：
Jung, Joon-Yong
影响因子：
2.4
作者：
Cho, Brian H.;Kaji, Deepak;Cho, Samuel K.
通讯作者：
Cho, Samuel K.