ChronoRoot 2.0 segmentation dataset: annotated infrared images of Arabidopsis and tomato seedlings
- Provider
- ChronoRoot team (ngaggion)
- License
- CC0-1.0 (source)
- Size
- 2,785 files
- Format
- NIfTI, PNG (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/datasets/ngaggion/ChronoRoot2)
- Access
- Free and public. No account with the data provider is needed.
- Category
- Biology
- Source
- https://arxiv.org/abs/2504.14736
About this dataset
Training data for ChronoRoot 2.0, an open plant phenotyping system for time-lapse root imaging . The set has 913 infrared images of Arabidopsis thaliana seedlings and 480 of tomato seedlings, 3280 x 2464 pixels, captured with the ChronoRoot hardware, each with an expert multi-class segmentation mask of six structures: main root, lateral roots, seed, hypocotyl, leaves and petiole (petiole is not annotated for tomato). Masks were drawn in ITK-SNAP and checked in a multi-stage quality control process, and are stored as .nii.gz in an nnU-Net style layout under ArabidopsisDataset/ and TomatoDataset/; read them with nibabel or SimpleITK. About 19 GB. Supports root system architecture analysis, plant development studies and training segmentation models for seedling phenotyping. The card states the dataset is released under Creative Commons Zero (CC0); cite the ChronoRoot 2.0 paper (arXiv 2504.14736) and see chronoroot.github.io.
How to load this dataset in Python
from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="ngaggion/ChronoRoot2", filename="ArabidopsisDataset/Etiolation/MultipleVids/Primeras/2024-05-30_09-29-07_1.nii.gz", repo_type="dataset")
print(path)Data structure
File types in sampled files: NIfTI, PNG
Files
Example file: ArabidopsisDataset/Etiolation/MultipleVids/Primeras/2024-05-30_09-29-07_1.nii.gz
Analyze this dataset without downloading it
On Scigantic, ChronoRoot 2.0 segmentation dataset: annotated infrared images of Arabidopsis and tomato seedlings opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Biology datasets
- ESM-2 650M protein language model weights (esm2_t33_650M_UR50D)
- An MGRS-based 4km grid for the FTW Benchmark Dataset
- PRISM Antibody Training Data: 66 Million Unpaired and 764k Paired Human Antibody Sequences from OAS with Germline Labels (Romero Lab, Duke)
- PDB seqres FASTA 2022-09-28 (AlphaFold 3 training set)
- RNAcentral clustered ncRNA 90% identity (AlphaFold 3 training set)
- PDB mmCIF structures 2022-09-28 (AlphaFold 3 training set)
- Raw flow cytometry FCS files from a BD FACSAria II: 29 specimens and 9 compensation controls (Caerin 1.1/1.9 antitumour immunity study)
- Observed Antibody Space (OAS) unpaired heavy and light chains, Parquet