Segmentation of occluded hematopoietic stem cells from tracking.
Segmentation of occluded hematopoietic stem cells from tracking.
复制标题
DOI：
10.1109/embc.2014.6944874
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
Cohen AR
中科院分区：
文献类型：
--
作者：
Mankowski WC;Winter MR;Wait E;Lodder M;Schumacher T;Naik SH;Cohen AR
活的增殖细胞的图像序列通常包含视觉模糊，即使是人类领域的专家也很难解决这些问题。在这里，我们提出了一种新的方法来分析图像序列，这些图像序列捕捉到了来自活细胞时间推移显微镜的造血干细胞克隆的发育过程。除非将其与第二种细胞类型OP9基质细胞一起培养，否则HSC无法长期存活。HSC经常消失在OP9细胞层之下，这使得从单个图像帧中分割变得困难或不可能，即使对于人类领域的专家也是如此。我们已经开发了一种新的方法来分割HSCs，以捕获这些闭塞的细胞。从使用蒙特卡罗技术估计接触细胞簇中细胞数量的先验分割开始，我们继续跟踪图像数据并进行谱系划分。在用户确认谱系信息之后，利用跟踪结果的后验重新分割步骤描绘了被OP9层遮挡的HSC。对77个音轨中的3031个遮挡段进行了再分割，正确恢复了84%以上的遮挡段。
Image sequences of live proliferating cells often contain visual ambiguities that are difficult even for human domain experts to resolve. Here we present a new approach to analyzing image sequences that capture the development of clones of hematopoietic stem cells (HSCs) from live cell time lapse microscopy. The HSCs cannot survive long term imaging unless they are cultured together with a secondary cell type, OP9 stromal cells. The HSCs frequently disappear under the OP9 cell layer, making segmentation difficult or impossible from a single image frame, even for a human domain expert. We have developed a new approach to the segmentation of HSCs that captures these occluded cells. Starting with an a priori segmentation that uses a Monte Carlo technique to estimate the number of cells in a clump of touching cells, we proceed to track and lineage the image data. Following user validation of the lineage information, an a posteriori resegmentation step utilizing tracking results delineates the HSCs occluded by the OP9 layer. Resegmentation has been applied to 3031 occluded segmentations from 77 tracks, correctly recovering over 84% of the occluded segmentations.