S-BIAD634alpha
An annotated fluorescence image dataset for training nuclear segmentation methods
Released: 2023-03-07By: Sabine Taschner-Mandl, Inge M. Ambros, Peter F. Ambros, Klaus Beiske, Allan Hanbury, Wolfgang Doerr, Tamara Weiss, Maria Berneder, Magdalena Ambros, Eva Bozsaky, Florian Kromp, Teresa Zulueta-Coarasa
On this page
In a nutshell
- 388 images
- 388 annotations
- Study size: 472.2MiB
- Filetype breakdown:
- .jpg: 79 (16.6MiB)
- .png: 115 (1.5MiB)
- .svg: 79 (4.1MiB)
- .tif: 194 (450.0MiB)
- .txt: 1 (3.1KiB)
- License : CC0
This dataset has
- segmentation masks
- test data
- training data
- ground truth annotations
|
|
Study Summary
Ground-truth annotated fluorescence image dataset for training nuclear segmentation methods
Organism
Homo sapiens
Imaging type
confocal fluorescence microscopy
Viewable images Images that have been converted to ome-ngff for in-browser viewing
Showing 1 to 8 of 8 entries
Annotations Annotation in the context of AI, is the task of marking up data, such as images, so it can be recognised by models and used to make predictions.
- Annotation type(s):Click on the Annotation type(s) to go to the page with a glossary segmentation masks
- Annotation method(s): human(expert)
Models Models can mean two things: models that are used to derive the annotations in this study, OR this dataset is used to train these models
Deep Learning models trained with this dataset : https://github.com/perlfloccri/NuclearSegmentationPipeline
