Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China; Shenzhen Colleges of Advanced Technology, University of Chinese Academy of Sciences, Beijing, China.
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
Comput Methods Programs Biomed. 2020 Apr;186:105110. doi: 10.1016/j.cmpb.2019.105110. Epub 2019 Nov 14.
For cerebrovascular segmentation from time-of-flight (TOF) magnetic resonance angiography (MRA), the focused issues are segmentation accuracy, vascular network coverage ratio, and cerebral artery and vein (CA/CV) separation. Therefore, cerebral artery segmentation is a challenging work, while a complete solution is lacking so far.
The preprocessing of skull-stripping and Hessian-based feature extraction is first implemented to acquire an indirect prior knowledge of vascular distribution and shape. Then, a novel intensity- and shape-based Markov statistical modeling is proposed for complete cerebrovascular segmentation, where our low-level process employs a Gaussian mixture model to fit the intensity histogram of the skull-stripped TOF-MRA data, while our high-level process employs the vascular shape prior to construct the energy function. To regularize the individual data processes, Markov regularization parameter is automatically estimated by using a machine-learning algorithm. Further, cerebral artery and vein (CA/CV) separation is explored with a series of morphological logic operations, which are based on a direct priori knowledge on the relationship of arteriovenous topology and brain tissues in between TOF-MRA and MR-T1.
We employed 109 sets of public datasets from MIDAS for qualitative and quantitative assessment. The Dice similarity coefficient, false negative rate (FNR), and false positive rate (FPR) of 0.933, 0.158, and 0.091% on average, as well as CA/CV separation results with the agreement, FNR, and FPR of 0.976, 0.041, and 0.022 on average. For clinical visual assessment, our methods can segment various sizes of the vessel in different contrast region, especially performs better on vessels of small size in low contrast region.
Our methods obtained satisfying results in visual and quantitative evaluation. The proposed method is capable of accurate cerebrovascular segmentation and efficient CA/CV separation. Further, it can stimulate valuable clinical applications on the computer-assisted cerebrovascular intervention according to the neurosurgeon's recommendation.
针对基于时间飞跃（TOF）磁共振血管成像（MRA）的脑血管分割，重点关注分割准确性、血管网络覆盖率以及脑动脉和静脉（CA/CV）分离。因此，脑动脉分割是一项具有挑战性的工作，目前还缺乏完整的解决方案。
首先进行颅骨剥离和基于 Hessian 的特征提取的预处理，以获取血管分布和形状的间接先验知识。然后，提出了一种新的基于强度和形状的马尔可夫统计建模方法，用于完整的脑血管分割，其中我们的低水平过程使用高斯混合模型来拟合颅骨剥离的 TOF-MRA 数据的强度直方图，而我们的高水平过程则使用血管形状先验来构建能量函数。为了对每个数据过程进行正则化，使用机器学习算法自动估计马尔可夫正则化参数。此外，通过基于 TOF-MRA 和 MR-T1 之间的动静脉拓扑和脑组织之间的直接先验知识的一系列形态逻辑运算来探索脑动脉和静脉（CA/CV）的分离。
我们使用 MIDAS 提供的 109 组公共数据集进行定性和定量评估。平均的 Dice 相似系数、假阴性率（FNR）和假阳性率（FPR）分别为 0.933%、0.158%和 0.091%，以及平均 CA/CV 分离的一致性、FNR 和 FPR 分别为 0.976%、0.041%和 0.022%。对于临床视觉评估，我们的方法可以分割不同对比度区域的各种大小的血管，特别是在低对比度区域的小血管上表现更好。
我们的方法在视觉和定量评估中均取得了令人满意的结果。所提出的方法能够准确地分割脑血管，并有效地分离 CA/CV。此外，根据神经外科医生的建议，它可以为计算机辅助脑血管介入提供有价值的临床应用。
