Accession number BBBC027 · Version 1
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 is provided in two diferent levels of quality: high SNR and low SNR.
A set (both in high and low SNR variant) of 30 images is provided. Each image contains the collection of nuclei formed in clusters. The dataset was generated using the virtual microscope imitating the microscope Zeiss S100 (objective Zeiss 63x/1.40 Oil DIC) attached to confocal unit Atto CARV and CCD camera Micromax 1300-YHS.
Each image contains binary mask of all the cells located inside the ROI; this is the ground truth for counting. Ground truth for foreground/background segmentation are available as binary images:
"We used image set BBBC027 [Svoboda David, Homola Ondřej, Stejskal Stanislav. Generation of 3D Digital Phantoms of Colon Tissue, In International Conference on Image Analysis and Recognition - ICIAR 2011, Part II, LNCS 6754, Berlin, Heidelberg: Springer-Verlag, pp 31-39, June 2011] from the Broad Bioimage Benchmark Collection."