Skip to content
ML experiment for classifying malaria cell images
Jupyter Notebook Python
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
saved-models
.gitignore
LICENSE
Malaria CNN Visualizations.ipynb
Malaria Data Exploration.ipynb
Malaria.ipynb
README.md
cv_utils.py
fetch_malaria.py
kaggle.py
load_malaria.py
malaria_images.py
requirements-freeze.txt
requirements.txt

README.md

Malaria detection with cell images

Experimenting with ML models to classify pre-segmented red blood cell images as uninfected or infected with P. falciparum. Main work is kept in the Malaria.ipynb Jupyter notebook.

Data

Source data originally comes from the publication:

Rajaraman S, Antani SK, Poostchi M, Silamut K, Hossain MA, Maude, RJ, Jaeger S, Thoma GR. (2018) Pre-trained convolutional neural networks as feature extractors toward improved Malaria parasite detection in thin blood smear images. PeerJ6:e4568 https://doi.org/10.7717/peerj.4568

The data was made available by NIH here. It was posted on Kaggle by user Arunava at iarunava/cell-images-for-detecting-malaria.

Setup

Work was developed with Python 3.7 and JupyterLab 0.35. Core Python dependencies are listed in requirements.txt, and the full venv contents are listed in requirements-freeze.txt.

Assuming you have already set up Python, Jupyter, and, if desired, a venv and corresponding Jupyter kernel:

$ pip install -r requirements.txt
$ jupyter lab
You can’t perform that action at this time.