Model-based automatic detection of the anterior and posterior commissures on MRI scans.
Model-based automatic detection of the anterior and posterior commissures on MRI scans.
复制标题
DOI：
10.1016/j.neuroimage.2009.02.030
复制
发表时间：
2009-07-01
期刊：
影响因子：
5.7
通讯作者：
Bachman, Alvin H.
中科院分区：
文献类型：
--
作者：
Ardekani, Babak A.;Bachman, Alvin H.
前连合和后连合（AC/PC）在人脑正中矢状面上的投影是神经影像学的重要标志。例如，它们可以在MRI扫描期间用于以标准取向采集成像切片。在采集后图像处理中，这些标志用于在大脑内建立基于解剖学的参考系，这在设计自动图像分析算法（例如图像分割和配准方法）时非常有用。本文提出了一种基于模型的全自动算法，用于MRI扫描的AC/PC检测。该算法利用来自多个模型图像的信息，在所述模型图像上AC/PC和参考点（上级脑桥沟的顶点）的位置是已知的。该信息然后用于通过模板匹配在测试扫描上定位界标。该算法被设计为快速、鲁棒和准确。该方法是灵活的，因为它可以被训练以在不同的图像对比度上工作，针对不同的人群或扫描模式进行优化。为了评估该技术的有效性，我们比较了84次T1加权和42次T2加权测试扫描中自动和手动检测到的标志位置。总的来说，自动和手动检测到的地标之间的平均欧几里得距离为1.1 mm。该算法的软件实现可在www.nitrc.org/projects/art上免费获得。
The projections of the anterior and posterior commissures (AC/PC) on the mid-sagittal plane of the human brain are important landmarks in neuroimaging. They can be used, for example, during MRI scanning for acquiring the imaging sections in a standard orientation. In post-acquisition image processing, these landmarks serve to establish an anatomically-based frame of reference within the brain that can be extremely useful in designing automated image analysis algorithms such as image segmentation and registration methods. This paper presents a fully automatic model-based algorithm for AC/PC detection on MRI scans. The algorithm utilizes information from a number of model images on which the locations of the AC/PC and a reference point (the vertex of the superior pontine sulcus) are known. This information is then used to locate the landmarks on test scans by template matching. The algorithm is designed to be fast, robust, and accurate. The method is flexible in that it can be trained to work on different image contrasts, optimized for different populations, or scanning modes. To assess the effectiveness of this technique, we compared automatically and manually detected landmark locations on 84 T1-weighted and 42 T2-weighted test scans. Overall, the average Euclidean distance between automatically and manually detected landmarks was 1.1 mm. A software implementation of the algorithm is freely available online at www.nitrc.org/projects/art.
登录
查看更多内容
影响因子：
1.3
作者：
Lee, C;Huh, S;Unser, M
通讯作者：
Unser, M
影响因子：
4.8
作者：
Prakash, KNB;Hu, QM;Nowinski, WL
通讯作者：
Nowinski, WL
影响因子：
10.6
作者：
Liu, YX;Collins, RT;Rothfus, WE
通讯作者：
Rothfus, WE
影响因子：
4.4
作者：
Han, Y;Park, HW
通讯作者：
Park, HW
影响因子：
2.8
作者：
SANDOR, T;TIEMAN, J;ALBERT, M
通讯作者：
ALBERT, M