Deep Learning for Multi-Tissue Segmentation and Fully Automatic Personalized Biomechanical Models from BACPAC Clinical Lumbar Spine MRI.
Deep Learning for Multi-Tissue Segmentation and Fully Automatic Personalized Biomechanical Models from BACPAC Clinical Lumbar Spine MRI.
复制标题
用于多组织分割的深度学习和来自bacpac临床腰椎MRI的全自动生物力学模型。
DOI：
10.1093/pm/pnac142
复制
发表时间：
2023-08-04
期刊：
影响因子：
3.1
通讯作者：
Majumdar, Sharmila
中科院分区：
文献类型：
--
作者：
Hess, Madeline;Allaire, Brett;Gao, Kenneth T.;Tibrewala, Radhika;Inamdar, Gaurav;Bharadwaj, Upasana;Chin, Cynthia;Pedoia, Valentina;Bouxsein, Mary;Anderson, Dennis;Majumdar, Sharmila
关键词：
临床腰椎磁共振成像（MRI）全自动定量成像特征提取的体内回顾性研究。为了证明在临床腰椎MRI中用自动分割代替人工分割的主要解剖结构来生成定量的基于图像的特征和生物力学模型的可行性。以前的研究已经证明了自动分割应用于医学图像的可行性；然而，这些网络分割临床获取图像的可行性尚未得到证实，因为它们在很大程度上依赖于专门的序列或严格的成像数据质量来实现良好的性能。训练卷积神经网络从矢状和轴向t1加权mri中划分椎体、椎间盘和棘旁肌肉。椎间盘高度、肌肉横截面积和受试者特定的腰椎组织负荷肌肉骨骼模型，然后从这些分割中计算出来，并与人类划分的面具计算出来的结果进行比较。分割掩模，以及从这些掩模中计算出的形态度量和生物力学模型，在人类和计算机生成的方法之间高度相似。分割相似，跨网络的Dice相似系数为0.77或更高，形态指标和生物力学模型相似，显著时Pearson R相关系数为0.69或更高。本研究证明了在不中断常规临床护理的情况下，用计算机生成的腰椎MRI主要解剖结构分割代替人工生成的分割的可行性，从而快速、高效、大规模地计算定量的基于图像的形态学指标和组织负荷的受试者特定肌肉骨骼模型。
In vivo retrospective study of fully automatic quantitative imaging feature extraction from clinically acquired lumbar spine magnetic resonance imaging (MRI). To demonstrate the feasibility of substituting automatic for human-demarcated segmentation of major anatomic structures in clinical lumbar spine MRI to generate quantitative image-based features and biomechanical models. Previous studies have demonstrated the viability of automatic segmentation applied to medical images; however, the feasibility of these networks to segment clinically acquired images has not yet been demonstrated, as they largely rely on specialized sequences or strict quality of imaging data to achieve good performance. Convolutional neural networks were trained to demarcate vertebral bodies, intervertebral disc, and paraspinous muscles from sagittal and axial T1-weighted MRIs. Intervertebral disc height, muscle cross-sectional area, and subject-specific musculoskeletal models of tissue loading in the lumbar spine were then computed from these segmentations and compared against those computed from human-demarcated masks. Segmentation masks, as well as the morphological metrics and biomechanical models computed from those masks, were highly similar between human- and computer-generated methods. Segmentations were similar, with Dice similarity coefficients of 0.77 or greater across networks, and morphological metrics and biomechanical models were similar, with Pearson R correlation coefficients of 0.69 or greater when significant. This study demonstrates the feasibility of substituting computer-generated for human-generated segmentations of major anatomic structures in lumbar spine MRI to compute quantitative image-based morphological metrics and subject-specific musculoskeletal models of tissue loading quickly, efficiently, and at scale without interrupting routine clinical care.
登录
查看更多内容
DOI：
10.1002/jbmr.4222
发表时间：
2021-04
期刊：
Journal of bone and mineral research : the official journal of the American Society for Bone and Mineral Research
影响因子：
--
作者：
Mokhtarzadeh H;Anderson DE;Allaire BT;Bouxsein ML
通讯作者：
Bouxsein ML
影响因子：
3.5
作者：
GUO, HR;TANAKA, S;PUTZANDERSON, V
通讯作者：
PUTZANDERSON, V
影响因子：
3
作者：
Barker, KL;Shamley, DR;Jackson, D
通讯作者：
Jackson, D
影响因子：
3
作者：
Niemelaeinen, Riikka;Briand, Marie-Michele;Battie, Michele C.
通讯作者：
Battie, Michele C.
影响因子：
3.3
作者：
Iriondo, Claudia;Pedoia, Valentina;Majumdar, Sharmila
通讯作者：
Majumdar, Sharmila