Bazin Pierre-Louis, Pham Dzung L
Laboratory of Medical Image Computing, Neuroradiology Division, Department of Radiology and Radiological Science, Johns Hopkins University, Baltimore, MD 21287, USA.
Inf Process Med Imaging. 2005;19:234-45. doi: 10.1007/11505730_20.
This paper presents a novel approach for object segmentation in medical images that respects the topological relationships of multiple structures as given by a template. The algorithm combines advantages of tissue classification, digital topology, and level-set evolution into a topology-invariant multiple-object fast marching method. The technique can handle any given topology and enforces object-level relationships with little constraint over the geometry. Applied to brain segmentation, it sucessfully extracts gray matter and white matter structures with the correct spherical topology without topology correction or editing of the subcortical structures.
本文提出了一种用于医学图像中对象分割的新方法，该方法尊重模板所给出的多个结构的拓扑关系。该算法将组织分类、数字拓扑和水平集演化的优点结合到一种拓扑不变的多对象快速行进方法中。该技术可以处理任何给定的拓扑结构，并在对几何形状几乎没有约束的情况下强制对象级关系。应用于脑部分割时，它能够成功提取具有正确球形拓扑结构的灰质和白质结构，而无需对皮质下结构进行拓扑校正或编辑。
