affable-shark alpha
Nuclei Segmentation Boundary Model
Constantin Pape
10.5281/zenodo.5764892/6647674
On this page
Model Information
Description: This model segments nuclei in fluorescence microscopy images. It predicts boundary maps and foreground probabilities for nucleus segmentation in different light microscopy modalities, mainly with DAPI staining. The boundaries can be processed e.g. with Multicut or Watershed to obtain an instance segmentation.
Task: 2D nucleus segmentation
Licence: CC-BY-4.0
Tags: 2D, nuclei, fluorescence microscopy, instance segmentation, U-Net
Benchmarking
This model was not tested on datasets with reference annotations, so we cannot produce benchmarking metrics.
Model predictions
| Study | Dataset | Original image | Prediction | Analysis parameters |
|---|---|---|---|---|
| S-BIAD1518 | Human kidney nephrectomy | 
Download | 
Download | z_slices_analysed: 16,17 |
| S-BIAD1518 | Scale-cleared rat kidney | 
Download | 
Download | z_slices_analysed: 5,6 |
| S-BIAD1518 | BABB-cleared kidney | 
Download | 
Download | z_slices_analysed: 63,64 |
| S-BIAD1492 | Simulated fluorescence images | 
Download | 
Download | z_slices_analysed: 63,64 xy_image_crop_size: 560,560 |
| S-BIAD1026 | Go-Nuclear image dataset | 
Download | 
Download | z_slices_analysed: 131,132 |
| S-BIAD1518 | Cleared mouse intestine | 
Download | 
Download | z_slices_analysed: 19,20 |
| S-BIAD1518 | Synthetic cell nuclei | 
Download | 
Download | z_slices_analysed: 63,64 |
| S-BIAD1518 | Human kidney cortex | 
Download | 
Download | z_slices_analysed: 8,9 |
| S-BIAD1196 | brain cell nucleus patches | 
Download | 
Download | z_slices_analysed: 99,100 xy_image_crop_size: 192,192 |
| S-BIAD1518 | Biopsy of diabetic human kidney | 
Download | 
Download | z_slices_analysed: 16,17 |