Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,7 +4,7 @@ emoji: 🫁
|
|
| 4 |
colorFrom: purple
|
| 5 |
colorTo: red
|
| 6 |
sdk: gradio
|
| 7 |
-
sdk_version: 6.
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
license: mit
|
|
@@ -33,6 +33,31 @@ Medical AI system for detecting pneumonia from chest X-ray images using Vision T
|
|
| 33 |
| AUC-ROC | 0.98 |
|
| 34 |
| Input size | 224x224 pixels |
|
| 35 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
## How to Use
|
| 37 |
|
| 38 |
1. Upload a chest X-ray image (frontal view preferred)
|
|
@@ -52,11 +77,10 @@ Medical AI system for detecting pneumonia from chest X-ray images using Vision T
|
|
| 52 |
- Grad-CAM
|
| 53 |
- Gradio
|
| 54 |
|
| 55 |
-
##
|
| 56 |
-
|
| 57 |
-
This tool is for **educational and research purposes only**. Not intended for clinical diagnosis. Always consult a qualified healthcare professional.
|
| 58 |
-
|
| 59 |
-
## Links
|
| 60 |
|
| 61 |
-
|
| 62 |
-
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
colorFrom: purple
|
| 5 |
colorTo: red
|
| 6 |
sdk: gradio
|
| 7 |
+
sdk_version: 6.12.0
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
license: mit
|
|
|
|
| 33 |
| AUC-ROC | 0.98 |
|
| 34 |
| Input size | 224x224 pixels |
|
| 35 |
|
| 36 |
+
## Training Details
|
| 37 |
+
|
| 38 |
+
| Parameter | Value |
|
| 39 |
+
|-----------|-------|
|
| 40 |
+
| Dataset | Chest X-ray (Pneumonia) |
|
| 41 |
+
| Train/Val/Test split | 80/10/10 |
|
| 42 |
+
| Epochs | 20 |
|
| 43 |
+
| Batch size | 32 |
|
| 44 |
+
| Learning rate | 1e-4 |
|
| 45 |
+
| Optimizer | AdamW |
|
| 46 |
+
| Hardware | Kaggle P100 (16GB) |
|
| 47 |
+
| Training time | ~3 hours |
|
| 48 |
+
|
| 49 |
+
## Performance Metrics
|
| 50 |
+
|
| 51 |
+
| Metric | Score |
|
| 52 |
+
|--------|-------|
|
| 53 |
+
| Accuracy | 87% |
|
| 54 |
+
| AUC-ROC | 0.98 |
|
| 55 |
+
| Precision | 85% |
|
| 56 |
+
| Recall | 89% |
|
| 57 |
+
| F1-Score | 87% |
|
| 58 |
+
|
| 59 |
+
*Tested on held-out test set of 624 images*
|
| 60 |
+
|
| 61 |
## How to Use
|
| 62 |
|
| 63 |
1. Upload a chest X-ray image (frontal view preferred)
|
|
|
|
| 77 |
- Grad-CAM
|
| 78 |
- Gradio
|
| 79 |
|
| 80 |
+
## Run Locally
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
|
| 82 |
+
```bash
|
| 83 |
+
git clone https://huggingface.co/spaces/mou11/pneumonia-detector
|
| 84 |
+
cd pneumonia-detector
|
| 85 |
+
pip install -r requirements.txt
|
| 86 |
+
python app.py
|