Cell Counting Dataset (cell_counting_dataset)

Overview

This DeepTrackAI repository provides a copy of the BBBC039v1 dataset Caicedo et al., Cytometry Part A, 2019, available from the Broad Bioimage Benchmark Collection (BBBC) (Ljosa et al., Nature Methods, 2012).

The dataset contains fluorescence microscopy images of Hoechst-stained nuclei of U2OS cells, intended for segmentation and cell counting benchmarking.

Summary

• Number of images: 200
• Approximate nuclei count: 23,000
• Image size: 520 × 696 pixels
• Image format: 16-bit grayscale TIFF
• Labels: 8-bit RGB PNG (segmentation masks)

---

Original Source

• Title: BBBC039v1 — Nuclei of U2OS cells in a chemical screen
• Authors: Caicedo et al.
• Source: BBBC039 dataset page
• References:
  • Caicedo J.C. et al. Cytometry Part A, 95(5): 473–485 (2019). DOI: 10.1002/cyto.a.23863
  • Ljosa V. et al. Nature Methods, 9: 637 (2012). DOI: 10.1038/nmeth.2083
• License: Creative Commons 1.0 Universal (CC0)

If you use this dataset in your research, please follow the licensing requirements and properly attribute the original authors.

---

Dataset Structure

/cell_counting_dataset
└── cell_nuclei/
    ├── images/        # Raw microscopy images
    │   ├── <filename_1>.tif
    │   ├── <filename_2>.tif
    │   └── ...
    └── labels/        # Segmentation masks
        ├── <filename_1>.png
        ├── <filename_2>.png
        └── ...

Each filename in images/ has a corresponding segmentation mask in labels/ with the same basename.

---

How to Access the Data

Clone the Repository

git clone https://github.com/DeepTrackAI/cell_counting_dataset
cd cell_counting_dataset

---

Attribution

When using this replication dataset, please cite the original dataset as follows:
"We used image set BBBC039v1 (Caicedo et al., Cytometry Part A, 2019), available from the Broad Bioimage Benchmark Collection (Ljosa et al., Nature Methods, 2012)."

Cite the papers:

Caicedo JC, et al. Evaluation of Deep Learning Strategies for Nucleus Segmentation in Fluorescence Images. Cytometry Part A 95(9): 952-965 (2019). https://doi.org/10.1002/cyto.a.23863

@article{caicedo2019evaluation,
  title={Evaluation of deep learning strategies for nucleus segmentation in fluorescence images},
  author={Caicedo, Juan C and Roth, Jonathan and Goodman, Allen and Becker, Tim and Karhohs, Kyle W and Broisin, Matthieu and Molnar, Csaba and McQuin, Claire and Singh, Shantanu and Theis, Fabian J and others},
  journal={Cytometry Part A},
  volume={95},
  number={9},
  pages={952--965},
  year={2019},
  publisher={Wiley Online Library},
  doi={10.1002/cyto.a.23863}
}

Ljosa V, et al. Annotated high-throughput microscopy image sets for validation. Nature Methods 9: 637–637 (2012). https://doi.org/10.1038/nmeth.2083

@article{ljosa2012annotated,
  title={Annotated high-throughput microscopy image sets for validation},
  author={Ljosa, Vebjorn and Sokolnicki, Katherine L and Carpenter, Anne E},
  journal={Nature methods},
  volume={9},
  number={7},
  pages={637},
  year={2012},
  publisher={Nature Publishing Group},
  doi={10.1038/nmeth.2083}
}

---

License

This replication dataset is shared under the CC0 1.0 Public Domain Dedication, following the original licensing terms.