ScottT2-spec/malaria-cell-detection

CNN-based malaria detection from blood cell microscope images — 95.43% test accuracy on NIH dataset (27,558 images)

18
/ 100
Experimental

This project helps medical professionals and lab technicians quickly classify red blood cells as either malaria-infected (parasitized) or uninfected. It takes a microscopic image of a blood cell as input and outputs a prediction of whether the Plasmodium parasite is present. This tool is designed for those involved in malaria diagnosis who need an automated method to screen blood smears.

Use this if you need an automated, image-based system to detect malaria parasites in red blood cell microscope images.

Not ideal if you require a diagnostic tool for other bloodborne diseases or if your input images are not standard 64x64 pixel thin blood smear photographs.

malaria-diagnosis parasitology blood-smear-analysis medical-imaging disease-screening
No License No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 3 / 25
Community 0 / 25

How are scores calculated?

Stars

14

Forks

Language

Jupyter Notebook

License

Last pushed

Mar 13, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ScottT2-spec/malaria-cell-detection"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.