PBC: 17,092 microscopy images of normal peripheral blood cells in eight classes (CellaVision, Hospital Clinic of Barcelona)

Provider
Andrea Acevedo, Anna Merino et al. (Hospital Clinic of Barcelona); repackaged by Chehab Lab
License
CC-BY-4.0 (source)
Size
3 files
Format
Parquet (in sampled files)
Stored at
Hugging Face (https://huggingface.co/datasets/chehablab/PBC)
Access
Free and public. No account with the data provider is needed.
DOI
10.17632/snkd93bnjr.1
Category
Health & Biomedical
Source
https://doi.org/10.1016/j.dib.2020.105474

About this dataset

The PBC dataset holds 17,092 images of individual normal peripheral blood cells acquired with a CellaVision DM96 analyzer in the core laboratory of the Hospital Clinic of Barcelona and labeled by expert clinical pathologists. Cells fall into eight groups: neutrophils (3,329), eosinophils (3,117), basophils (1,218), lymphocytes (1,214), monocytes (1,420), immature granulocytes (2,895), erythroblasts (1,551) and platelets (2,348). Images are 360x363 pixel JPEGs, kept unchanged; columns add the cell type, a finer subtype code from the filename prefix (such as SNE, BNE or MY) and an integer label. One Parquet file under data/, about 280 MB (measured 2026-11-21); read with Hugging Face datasets. Use for automated white blood cell differential counting and hematology image classification. Original data on Mendeley Data (DOI 10.17632/snkd93bnjr.1), released under CC BY 4.0. Cite Acevedo et al., Data in Brief 30:105474 (2020).

How to load this dataset in Python

from datasets import load_dataset
ds = load_dataset("chehablab/PBC")
print(ds)

Data structure

File types in sampled files: Parquet

Files

Example file: data/train-00000-of-00001.parquet

Analyze this dataset without downloading it

On Scigantic, PBC: 17,092 microscopy images of normal peripheral blood cells in eight classes (CellaVision, Hospital Clinic of Barcelona) 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 Health & Biomedical datasets