CIL:27856

One of the principal challenges in counting or segmenting nuclei is dealing with clustered nuclei. To help assess algorithms' performance in this regard, this synthetic image set consists of five subsets with increasing degree of clustering. Five subsets of 20 images each are provided. Each image contains 300 objects, but the objects overlap and cluster with overlap probability ranging from 0.0 to 0.6, and can be found with CIL 27833, 27853, 28754, 28734, and 28714, respectively. This image set has 0.15 probability overlap. The images were generated with the SIMCEP (http://www.cs.tut.fi/sgn/csb/simcep/tool.html) simulating platform for fluorescent cell population images (Lehmussola et al., IEEE T. Med. Imaging, 2007 and Lehmussola et al., P. IEEE, 2008). Ground truth for foreground/background segmentation are available as binary images as the second image in the tiff image stack.
Recommended citation We used the Synthetic 1 image set (Ruusuvuori et al., in Proc. of the 16th European Signal Processing Conference (EUSIPCO-2008), 2008), available from the Broad Bioimage Benchmark Collection (www.broad.mit.edu/bbbc).

细胞核计数与分割任务中面临的核心挑战之一，便是处理成团聚集的细胞核。为助力评估相关算法的性能，本合成图像集共包含五个子集，各子集的细胞核聚集程度依次递增。本次共提供五个子集，每个子集包含20张图像；每张图像内均包含300个目标对象，这些对象存在重叠与聚集现象，重叠概率介于0.0至0.6之间，五个子集分别对应CIL 27833、27853、28754、28734与28714。该图像集的目标重叠概率为0.15。所有图像均通过SIMCEP（http://www.cs.tut.fi/sgn/csb/simcep/tool.html）荧光细胞群体图像仿真平台生成，相关研究可参见Lehmussola等人于2007年发表于《IEEE医学成像汇刊》（IEEE T. Med. Imaging）以及2008年发表于《IEEE汇刊》（P. IEEE）的论文。前景/背景分割的真值（Ground Truth）以二值图像形式提供，对应TIFF图像栈中的第二张图像。
推荐引用格式：本研究使用的Synthetic 1图像集相关文献为Ruusuvuori等人收录于2008年第16届欧洲信号处理大会（EUSIPCO-2008）会议论文集的研究，该数据集可从布罗德生物图像基准数据集集合（Broad Bioimage Benchmark Collection，www.broad.mit.edu/bbbc）获取。