fidoptBBBC050, nuclei of mouse embryonic cells
A three-dimensional fluorescence volume of an early mouse embryo at one annotated time point, its manually annotated nuclei merged into one foreground label (BBBC050).
10 test casescellimage FLUORESCENCE
Read before comparing (3)
- Imaging. The training embryos were imaged on IX71 with H2B-mRFP1 and the test embryos on CV1000 with H2B-mCherry, at published spacings of (0.8, 0.8, 1.75) and (0.8, 0.8, 2.0) micrometres. The TIFF headers carry no spacing: prepare.py assigns the published values without resampling.
- Truth. Only the whole-nucleus instance maps are used, all positive IDs merged: this is semantic nuclei segmentation, not instance separation or tracking.
- Ranked apart. The test set holds four embryos, not ten independent subjects, and the time points of one embryo are correlated.
No method has a result on every case of this dataset yet.
Case by case
Click a score to look at that result: the image, the truth in green and the method's map in red. Underlined scores have their image; for the others you see the case without the result.
About the data
The first test caseClick to look at every case.
- Test cases
- The 10 test volumes are time points of the provider's four test embryos, Emb1 to Emb4, drawn with seed 2026 and stratified by embryo; four embryos cannot give ten independent subjects, so the set stays as drawn under the 10% rule. The 11 development cases are one seeded time point from each of the provider's eleven training embryos: no embryo crosses the provider split.
- Truth
- contours by experts all nonzero instances of the manually annotated GroundTruth_QCANet map, merged into one nuclei foreground label
- Licence
- CC BY 3.0
11 cases for tuning, never tested
train_Emb09_t001, train_Emb06_t301, train_Emb03_t051, train_Emb08_t051, train_Emb07_t451, train_Emb04_t451, train_Emb01_t001, train_Emb02_t001, train_Emb10_t351, train_Emb11_t301, train_Emb05_t151