Kassim Yasmin M, Surya Prasath V B, Pelapur Rengarajan, Glinskii Olga V, Maude Richard J, Glinsky Vladislav V, Huxley Virginia H, Palaniappan Kannappan
Computational Imaging and VisAnalysis (CIVA) Lab, Department of Computer Science, Columbia, MO 65201 USA.
Research Service, Harry S. Truman Memorial Veterans Hospital, Columbia, MO 65201 USA; Department of Medical Pharmacology and Physiology, University of Missouri-Columbia, MO 65211 USA.
Annu Int Conf IEEE Eng Med Biol Soc. 2016 Aug;2016:2901-2904. doi: 10.1109/EMBC.2016.7591336.
Automatic segmentation of microvascular structures is a critical step in quantitatively characterizing vessel remodeling and other physiological changes in the dura mater or other tissues. We developed a supervised random forest (RF) classifier for segmenting thin vessel structures using multiscale features based on Hessian, oriented second derivatives, Laplacian of Gaussian and line features. The latter multiscale line detector feature helps in detecting and connecting faint vessel structures that would otherwise be missed. Experimental results on epifluorescence imagery show that the RF approach produces foreground vessel regions that are almost 20 and 25 percent better than Niblack and Otsu threshold-based segmentations respectively.
微血管结构的自动分割是定量表征硬脑膜或其他组织中血管重塑及其他生理变化的关键步骤。我们开发了一种监督随机森林（RF）分类器，用于基于Hessian矩阵、定向二阶导数、高斯拉普拉斯算子和线特征的多尺度特征分割细血管结构。后一种多尺度线检测器特征有助于检测和连接那些否则会被遗漏的微弱血管结构。在落射荧光图像上的实验结果表明，随机森林方法产生的前景血管区域分别比基于Niblack和Otsu阈值的分割方法好近20%和25%。
