Automatic Segmentation of Bone Selective MR Images for Visualization and Craniometry of the Cranial Vault.
Automatic Segmentation of Bone Selective MR Images for Visualization and Craniometry of the Cranial Vault.
复制标题
DOI：
10.1016/j.acra.2021.03.010
复制
发表时间：
2022-03
影响因子：
4.8
通讯作者：
Wehrli FW
中科院分区：
文献类型：
--
作者：
Zimmerman CE;Khandelwal P;Xie L;Lee H;Song HK;Yushkevich PA;Vossough A;Bartlett SP;Wehrli FW
固态MRI已被证明是CT的一种无辐射替代成像策略。然而，手工图像分割生成基于骨选择性磁共振的3D渲染图是费时费力的，因此成为临床实践的瓶颈。本研究的目的是评估用于颅顶图像的自动多图谱分割管道，完全绕过先前的人工干预，并评估管道产生的MRI和基于ct的三维颅骨渲染之间颅测量测量的一致性。本前瞻性研究在2018年12月至2020年1月期间获得30名健康受试者的3T双射频、双回波、3D UTE脉冲序列MR数据以及低剂量CT图像。将四点MRI数据集（两个射频脉冲宽度和两个回波时间）结合起来产生骨特异性图像。CT图像的阈值和人工校正分割颅穹窿。然后使用互信息将CT图像严格地配准到MRI。然后将相应的颅拱顶分割转换为MRI。“ground truth”分割作为MR图像的参考。随后，使用自动多图谱管道对骨选择性图像进行分割。为了比较手动和自动分割的MR图像，我们计算了Dice相似系数（DSC）和Hausdorff距离（HD），并通过Lin’s concordance系数（LCC）检验了CT和基于自动管道的mri分割之间的颅骨测量值。自动分割减少了对专家进行分割的需要。平均DSC为90.86±1.94%，平均95百分位HD为1.65±0.44 mm。在关键的颅骨测量上，基于核磁共振的测量与基于ct的测量差异为0.73-1.2 mm。CT与mr标记点之间距离的lcc分别为顶点基底：0.906，左右额颧缝线：0.780，眉间-胸颅：0.956。CT和基于mr的自动三维颅骨拱顶绘制之间实现了良好的一致性，从而消除了费力的人工分割过程。目标应用包括颅面手术以及创伤性损伤和涉及骨骼和软组织的肿块的成像。
Solid-state MRI has been shown to provide a radiation-free alternative imaging strategy to CT. However, manual image segmentation to produce bone-selective MR-based 3D renderings is time and labor intensive, thereby acting as a bottleneck in clinical practice. The objective of this study was to evaluate an automatic multi-atlas segmentation pipeline for use on cranial vault images entirely circumventing prior manual intervention and to assess concordance of craniometric measurements between pipeline produced MRI and CT-based 3D skull renderings. Dual-RF, dual-echo, 3D UTE pulse sequence MR data were obtained at 3T on 30 healthy subjects along with low-dose CT images between December 2018 to January 2020 for this prospective study. The four-point MRI datasets (two RF pulse widths and two echo times) were combined to produce bone-specific images. CT images were thresholded and manually corrected to segment the cranial vault. CT images were then rigidly registered to MRI using mutual information. The corresponding cranial vault segmentations were then transformed to MRI. The “ground truth” segmentations served as reference for the MR images. Subsequently, an automated multi-atlas pipeline was used to segment the bone-selective images. To compare manually and automatically segmented MR images, the Dice similarity coefficient (DSC) and Hausdorff distance (HD) were computed, and craniometric measurements between CT and automated-pipeline MRI-based segmentations was examined via Lin’s concordance coefficient (LCC). Automated segmentation reduced the need for an expert to obtain segmentation. Average DSC was 90.86±1.94%, and average 95th percentile HD was 1.65±0.44 mm between ground truth and automated segmentations. MR-based measurements differed from CT-based measurements by 0.73–1.2 mm on key craniometric measurements. LCCfor distances between CT and MR-based landmarks were vertex-basion: 0.906, left-right frontozygomatic suture: 0.780, and glabella-opisthocranium: 0.956 for the three measurements. Good agreement between CT and automated MR-based 3D cranial vault renderings has been achieved, thereby eliminating the laborious manual segmentation process. Target applications comprise craniofacial surgery as well as imaging of traumatic injuries and masses involving both bone and soft tissue.
登录
查看更多内容
影响因子：
--
作者：
Berrington de González A;Mahesh M;Kim KP;Bhargavan M;Lewis R;Mettler F;Land C
通讯作者：
Land C
影响因子：
3.3
作者：
Hwang, SN;Wehrli, FW
通讯作者：
Wehrli, FW
影响因子：
0.9
作者：
Lin, Lawrence O.;Kalmar, Christopher L.;Taylor, Jesse A.
通讯作者：
Taylor, Jesse A.
DOI：
10.1016/j.bjps.2019.11.006
发表时间：
2020-04-01
影响因子：
2.7
作者：
Saarikko, Anne;Mellanen, Eero;Brandstack, Nina
通讯作者：
Brandstack, Nina
影响因子：
3.3
作者：
Johnson, Ethan M.;Vyas, Urvi;Ghanouni, Pejman;Pauly, Kim Butts;Pauly, John M.
通讯作者：
Pauly, John M.