Using multimodal information for the segmentation of fluorescent micrographs with application to Virology and microbiology
Using multimodal information for the segmentation of fluorescent micrographs with application to Virology and microbiology
复制标题
使用多模态信息分割荧光显微照片并应用于病毒学和微生物学
DOI：
--
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
T. Wittenberg
中科院分区：
文献类型：
--
作者：
C. Held;J. Wenzel;Rike Webel;M. Marschall;R. Lang;R. Palmisano;T. Wittenberg
为了提高基于荧光显微镜的实验的可重复性和客观性，并能够评估大型数据集，需要能够适应不同染色和细胞类型的灵活分割方法。这种适应通常是通过手动调整分割方法参数来实现的，这对于没有图像处理知识的生物学家来说既耗时又具有挑战性。为了避免这种情况，所提出方法的参数自动适应用户生成的地面实况，以确定最佳方法和最佳参数设置。然后，这些设置可用于剩余图像的分割。由于稳健的分割方法形成了此类系统的核心，因此当前使用的基于分水岭变换的分割例程被基于快速行进水平集的分割例程所取代，该分割例程结合了细胞核的知识。我们的评估表明，多模态信息的结合提高了所呈现的荧光数据集的分割质量。
In order to improve reproducibility and objectivity of fluorescence microscopy based experiments and to enable the evaluation of large datasets, flexible segmentation methods are required which are able to adapt to different stainings and cell types. This adaption is usually achieved by the manual adjustment of the segmentation methods parameters, which is time consuming and challenging for biologists with no knowledge on image processing. To avoid this, parameters of the presented methods automatically adapt to user generated ground truth to determine the best method and the optimal parameter setup. These settings can then be used for segmentation of the remaining images. As robust segmentation methods form the core of such a system, the currently used watershed transform based segmentation routine is replaced by a fast marching level set based segmentation routine which incorporates knowledge on the cell nuclei. Our evaluations reveal that incorporation of multimodal information improves segmentation quality for the presented fluorescent datasets.