-
Upload 4 files
-
Update README.md
---
title: AI Malaria Parasite Detector (Ghana Model)
emoji: 🦟
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 4.36.1
app_file: app.py
pinned: false
license: mit
---
# 🦟 AI Malaria Parasite Detector
## Overview
This model detects malaria parasites in blood smear images using **MobileNetV2** with transfer learning. It has been fine-tuned on **Ghanaian blood smear samples** to ensure accuracy with local staining and imaging conditions.
## Model Details
- **Architecture:** MobileNetV2 (pre-trained on ImageNet)
- **Fine-tuning:** Ghanaian whole-slide blood smear images
- **Analysis Method:** Patch-based scanning (224x224 patches)
- **Output:** Binary classification (Parasitized / Uninfected)
## Performance Metrics
| Metric | Value |
| :--- | :--- |
| Overall Accuracy | **97.2%** |
| Parasitized Detection (Sensitivity) | **97.8%** |
| Uninfected Rejection (Specificity) | **92.3%** |
| Test Samples | 250 |
| Model Size (TFLite) | 2.54 MB |
## Usage
### Python
```python
import… -
initial commit