Salmonella Serovar Hyperspectral Microscopy: 500 Hypercube Images of Five Serovars for AI Classification

Provider
Papa, Bhattacharya, Park and Yi (Food AI Nexus)
License
CC-BY-4.0 (source)
Size
504 files
Format
PNG, Parquet (in sampled files)
Stored at
Hugging Face (https://huggingface.co/datasets/food-ai-nexus/salmonella-serovar-hyperspectral)
Access
Free and public. No account with the data provider is needed.
DOI
10.3390/foods14152737
Category
Health & Biomedical
Source
https://huggingface.co/datasets/food-ai-nexus/salmonella-serovar-hyperspectral

About this dataset

Hyperspectral microscopy images of five Salmonella enterica serovars relevant to poultry and foodborne illness (Enteritidis, Infantis, Kentucky, Johannesburg and the monophasic variant 4,[5],12:i:-), released with Papa, Bhattacharya, Park and Yi (2025), Foods 14(15):2737, doi:10.3390/foods14152737. Cultures at 10^5 CFU/mL were imaged with an Olympus BX43 upright microscope, a 100x oil-immersion objective and a HinaLea 4250 hyperspectral camera; 500 hypercubes (100 per serovar) were acquired. images/ holds RGB composites rendered from each hypercube at 620, 550 and 450 nm, one full 1936 x 1216 field of view per PNG, split 70/30 into 350 train and 150 test images balanced by serovar; spectra/ holds single-cell spectral features in Parquet (the same table is published separately as salmonella-serovar-hyperspectral-spectra, 25,972 cells). Supports rapid pathogen identification, hyperspectral image classification and image-spectra fusion. About 0.7 GB; load with datasets.load_dataset. Licensed CC BY 4.0 by the authors; cite the Foods paper.

How to load this dataset in Python

from datasets import load_dataset
ds = load_dataset("food-ai-nexus/salmonella-serovar-hyperspectral")
print(ds)

Data structure

File types in sampled files: PNG, Parquet

Files

Example file: spectra/test.parquet

Analyze this dataset without downloading it

On Scigantic, Salmonella Serovar Hyperspectral Microscopy: 500 Hypercube Images of Five Serovars for AI Classification 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