Mosaliganti Kishore, Gelas Arnaud, Gouaillard Alexandre, Noche Ramil, Obholzer Nikolaus, Megason Sean
Department of Systems Biology, Harvard Medical School, Boston, MA 02115, USA.
Med Image Comput Comput Assist Interv. 2009;12(Pt 2):641-8. doi: 10.1007/978-3-642-04271-3_78.
We consider the problem of segmenting 3D images that contain a dense collection of spatially correlated objects, such as fluorescent labeled cells in tissue. Our approach involves an initial modeling phase followed by a data-fitting segmentation phase. In the first phase, cell shape (membrane bound) is modeled implicitly using a parametric distribution of correlation function estimates. The nucleus is modeled for its shape as well as image intensity distribution inspired from the physics of its image formation. In the second phase, we solve the segmentation problem using a variational level-set strategy with coupled active contours to minimize a novel energy functional. We demonstrate the utility of our approach on multispectral fluorescence microscopy images.
我们考虑对包含大量空间相关对象的三维图像进行分割的问题，比如组织中的荧光标记细胞。我们的方法包括初始建模阶段，随后是数据拟合分割阶段。在第一阶段，使用相关函数估计的参数分布隐式地对细胞形状（膜边界）进行建模。根据细胞核图像形成的物理原理，对其形状以及图像强度分布进行建模。在第二阶段，我们使用具有耦合活动轮廓的变分水平集策略来解决分割问题，以最小化一个新的能量泛函。我们在多光谱荧光显微镜图像上展示了我们方法的实用性。
