HAPPY: a deep learning pipeline for mapping cell-to-tissue graphs across placenta histology whole slide images
Authors/Creators
-
Vanea, Claudia
(Researcher)1
- Džigurski, Jelisaveta (Researcher)2
- Rukins, Valentina (Researcher)2
- Dodi, Omri (Researcher)3
- Siigur, Siim (Researcher)2
- Salumäe, Liis (Researcher)2
- Meir, Karen (Researcher)3
- Parks, W. Tony (Researcher)4
- Hochner-Celnikier, Drorith (Researcher)3
- Fraser, Abigail (Researcher)5, 6
- et al. Show all 15 authors
-
Vanea, Claudia
(Researcher)1
- Džigurski, Jelisaveta (Researcher)2
- Rukins, Valentina (Researcher)2
- Dodi, Omri (Researcher)3
- Siigur, Siim (Researcher)2
- Salumäe, Liis (Researcher)2
- Meir, Karen (Researcher)3
- Parks, W. Tony (Researcher)4
- Hochner-Celnikier, Drorith (Researcher)3
- Fraser, Abigail (Researcher)5, 6
- Hochner, Hagit (Researcher)7
- Laisk, Triin (Researcher)2
- Ernst, Linda M. (Researcher)8, 9
-
Lindgren, Cecilia M.
(Supervisor)1, 10, 11
-
Nellåker, Christoffer
(Supervisor)1
-
1.
University of Oxford
-
2.
University of Tartu
-
3.
Hadassah Medical Center
-
4.
University of Toronto
- 5. Bristol Medical School
-
6.
University of Bristol
-
7.
Hebrew University of Jerusalem
-
8.
Endeavor Health
-
9.
University of Chicago
-
10.
Broad Institute
-
11.
Centre for Human Genetics
Description
These two zipped folders contain all data necessary to train, validate and reproduce results from the paper.
Unzipping the files will create 6 folders. Data from folders with the same name across both zips should be combined into one folder. The 'annotations' folder contains all ground truth annotations for training all three deep learning models. The 'datasets' folder contains images for training the nuclei localisation and cell classification models. The 'embeddings' folder contains cell embedding vectors and nuclei coordinates from two slides used to create nodes to train the graph tissue classification model. The 'graph_splits' folder contains regions defining the validation and test splits for the graph model. The 'slides' folder contains a sample region of a whole slide image as a .tiff file for running the inference demo. The 'trained_models' folder contains trained weights for each of the three models.
Further instructions for dataset use and creation of custom datasets are available in the GitHub readme: https://github.com/Nellaker-group/happy.
Files
HAPPYData-20240119T100520Z-001.zip
Additional details
Related works
- Is source of
- Software: 10.5281/zenodo.10529240 (DOI)