Dataset Open Access

CellTypeGraph Benchmark

Cerrone, Lorenzo; Vijayan, Athul; Mody, Tejasvinee; Schneitz, Kay; Hamprecht, Fred A

This repository contains the benchmark dataset proposed in: 

CellTypeGraph: A New Geometric Computer Vision Benchmark, Cerrone et al., CVPR2022

Paper Abstract:

Classifying all cells in an organ is a relevant and difficult problem from plant developmental biology. We here abstract the problem into a new benchmark for node classification in a geo-referenced graph. Solving it requires learning the spatial layout of the organ including symmetries. 
To allow the convenient testing of new geometrical learning methods, the benchmark of Arabidopsis thaliana ovules is made available as a  PyTorch data loader, along with a large number of precomputed features.

Raw Data Source:

The benchmark raw data is derived from "A digital 3D reference atlas reveals cellular growth patterns shaping the Arabidopsis ovule, A. Vijayan et al., eLife 2021".

Source code:

  • Repository for using the benchmark: https://github.com/hci-unihd/celltype-graph-benchmark
  • Repository for reproducing the experiments in the manuscript:  https://github.com/hci-unihd/plant-celltype

Index:

Download integrity check (md5sum):

  • raw_data.zip: fd0ecccdea684d156fd8ac182a22251b
  • label_grs_surface.zip: 51e21dc509a9205b9ec47f38a307b156
Files (4.1 GB)
Name Size
label_grs_surface.zip
md5:51e21dc509a9205b9ec47f38a307b156
3.8 GB Download
raw_data.zip
md5:fd0ecccdea684d156fd8ac182a22251b
283.0 MB Download
139
23
views
downloads
All versions This version
Views 13996
Downloads 2319
Data volume 64.5 GB47.7 GB
Unique views 11079
Unique downloads 1612

Share

Cite as