Malaria Cell
Detector
Upload a blood cell microscopy image and our CNN will classify it as parasitized or uninfected in seconds.
Upload Multiple Images
Select up to 50 blood cell images for batch analysis
📊 Dashboard
How It Works
Upload
Upload a microscopy image of a thin blood smear cell sample.
Process
Image is resized to 64×64px and normalized for the CNN model.
Classify
3-layer CNN analyzes the cell for Plasmodium parasite presence.
Result
Get instant classification with confidence score and AI attention map.
🔬 Research & Methodology
Model Architecture
Dataset
NIH Malaria Cell Images Dataset — 27,558 cell images with equal instances of parasitized and uninfected cells from thin blood smear slide images of segmented cells.
Citation: Rajaraman S, et al. "Pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images." PeerJ. 2018;6:e4568.
Training & Validation
80/20 stratified train-test split · Binary cross-entropy loss · Adam optimizer · Accuracy: 95.43%
Confusion Matrix
Always consult a healthcare professional for malaria diagnosis and treatment.
Built by Scott Antwi · CNN trained on NIH Malaria Dataset · View Source