Pneumonia Detection Model (VGG16)
A VGG16 model fine-tuned for binary classification of chest X-ray images.
Model Performance
| Metric | Value |
|---|---|
| AUC-ROC | 0.8625 |
| Accuracy | 0.7734 |
| F1-Score | 0.6116 |
| Recall | 0.7916 |
| Specificity | 0.7681 |
| Precision | 0.4983 |
Training Details
- Base Model: VGG16 (ImageNet pre-trained)
- Fine-tuning: 2-phase (feature extraction + fine-tuning)
- Dataset: RSNA Pneumonia Detection Challenge (26,684 patients)
- Input Size: 224x224x3
- Optimal Threshold: 0.4376 (Youden's J)
Usage
import tensorflow as tf
from huggingface_hub import hf_hub_download
model_path = hf_hub_download(repo_id="vksfdc2024/pneumonia-detection-model", filename="best_pneumonia_model.keras")
model = tf.keras.models.load_model(model_path)
Live Demo
Try the model: Hugging Face Space
Author
Vamsee Krishna Kondapalli | AIML Program Capstone Project
- Downloads last month
- 2