Guo Zhihui, Kashyap Satyananda, Sonka Milan, Oguz Ipek
Dept. of Biomedical Engineering, Univ. of Iowa, Iowa City, IA, USA 52242.
Iowa Institute for Biomedical Imaging, Univ. of Iowa, Iowa City, IA, USA 52242.
Proc SPIE Int Soc Opt Eng. 2017 Feb 11;10133. doi: 10.1117/12.2254874. Epub 2017 Feb 24.
Automated and reliable segmentation of subcortical structures from human brain magnetic resonance images is of great importance for volumetric and shape analyses in quantitative neuroimaging studies. However, poor boundary contrast and variable shape of these structures make the automated segmentation a tough task. We propose a 3D graph-based machine learning method, called LOGISMOS-RF, to segment the caudate and the putamen from brain MRI scans in a robust and accurate way. An atlas-based tissue classification and bias-field correction method is applied to the images to generate an initial segmentation for each structure. Then a 3D graph framework is utilized to construct a geometric graph for each initial segmentation. A locally trained random forest classifier is used to assign a cost to each graph node. The max-flow algorithm is applied to solve the segmentation problem. Evaluation was performed on a dataset of T1-weighted MRI's of 62 subjects, with 42 images used for training and 20 images for testing. For comparison, FreeSurfer and FSL approaches were also evaluated using the same dataset. Dice overlap coefficients and surface-to-surfaces distances between the automated segmentation and expert manual segmentations indicate the results of our method are statistically significantly more accurate than the other two methods, for both the caudate (Dice: 0.89 ± 0.03) and the putamen (0.89 ± 0.03).
从人脑磁共振图像中自动且可靠地分割皮层下结构，对于定量神经成像研究中的体积和形状分析非常重要。然而，这些结构的边界对比度差和形状多变，使得自动分割成为一项艰巨的任务。我们提出了一种基于3D图形的机器学习方法，称为LOGISMOS-RF，以稳健且准确的方式从脑部MRI扫描中分割尾状核和壳核。一种基于图谱的组织分类和偏置场校正方法应用于图像，为每个结构生成初始分割。然后利用3D图形框架为每个初始分割构建一个几何图形。使用局部训练的随机森林分类器为每个图形节点分配一个代价。应用最大流算法来解决分割问题。在一个包含62名受试者的T1加权MRI数据集上进行了评估，其中42幅图像用于训练，20幅图像用于测试。为了进行比较，还使用相同的数据集对FreeSurfer和FSL方法进行了评估。自动分割与专家手动分割之间的骰子重叠系数和表面到表面的距离表明，对于尾状核（骰子系数：0.89±0.03）和壳核（0.89±0.03），我们方法的结果在统计学上显著比其他两种方法更准确。
