Pekka Ruusuvuori (2011) CIL:27858. CIL. Dataset

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)."

在核计数或分割领域，主要挑战之一在于处理簇状核。为评估算法在此方面的性能，本合成图像集包含五个子集，其簇状程度逐渐增加。提供了五个各含20张图像的子集。每张图像包含300个对象，但对象之间相互重叠并形成簇状，重叠概率介于0.0至0.6之间。这些对象可通过CIL 27833、27853、28754、28734和28714分别找到。该图像集的重叠概率为0.15。图像生成采用SIMCEP（http://www.cs.tut.fi/sgn/csb/simcep/tool.html）模拟平台，该平台模拟荧光细胞群体图像（Lehmussola等，IEEE T. Med. Imaging，2007及Lehmussola等，P. IEEE，2008）。前景/背景分割的地面真实值以二值图像的形式作为tif图像堆栈中的第二张图像提供。推荐引用：“我们使用了合成1图像集（Ruusuvuori等，在2008年第16届欧洲信号处理会议（EUSIPCO-2008）论文集中，2008年），该图像集可通过Broad生物图像基准集（www.broad.mit.edu/bbbc）获取。”}