Model Card for BrainTumorClassifier: InceptionV3-Based Brain Tumor Detection

BrainTumorClassifier is a deep learning model built on InceptionV3 and trained to classify MRI brain scans into two categories: Brain Tumor and Healthy.
The model leverages transfer learning from ImageNet weights to accelerate training and improve generalization, supporting early detection of brain tumors.

⚠️ Disclaimer: This model is intended for research and educational purposes only.
It is not a substitute for professional medical diagnosis or treatment.
Always consult a licensed healthcare provider for medical decisions.

---

Model Details

Key Features:

• Binary classification of MRI brain images (Brain Tumor vs Healthy)
• Transfer learning using InceptionV3 pretrained on ImageNet
• Input size: 299×299 RGB images, normalized
• Custom dense head with batch normalization, dropout, and L1/L2 regularization
• Evaluated on separate validation and test sets with high accuracy

Skills & Technologies Used:

• TensorFlow / Keras for model design & training
• ImageDataGenerator for preprocessing and augmentation
• InceptionV3 for feature extraction and fine-tuning
• Matplotlib & Seaborn for visualization
• Hugging Face Hub for model hosting
• Kaggle for dataset and training environment

---

• Developed by: Rawan Alwadeya
• Model type: Convolutional Neural Network (CNN) with Transfer Learning
• Language(s): N/A (Image model)
• License: MIT

---

Uses

This model can be used for:

• Research in brain tumor detection and AI-assisted diagnosis
• Educational demonstrations of transfer learning on medical imaging data
• Portfolio projects showcasing preprocessing, model training, and deployment

---

Dataset

• Source: Brain Tumor MRI Dataset (Kaggle)
• Classes: Brain Tumor, Healthy
• Preprocessing:
  • Duplicate images removed
  • Images resized to 299×299 RGB and normalized
  • Balanced train, validation, and test splits

---

Performance

The final model demonstrated strong performance on the held-out test set:

• Accuracy: 98.04%
• Precision: 97.62%
• Recall: 98.09%
• F1 Score: 97.85%

---

👩‍💻 Author

Rawan Alwadeya
AI Engineer | Generative AI Engineer | Data Scientist

• 📧 Email: [email protected]
• 🌐 LinkedIn Profile

---

Example Usage

import numpy as np
from keras.models import load_model
from PIL import Image
import requests
from io import BytesIO
from huggingface_hub import hf_hub_download

# Download the model from Hugging Face Hub
model_path = hf_hub_download(repo_id="RawanAlwadeya/BrainTumorClassifier", filename="BrainTumorClassifier.h5")
model = load_model(model_path)

# Preprocess an MRI image
def preprocess_image(image):
    IMG_SIZE = (299, 299)
    image = image.convert("RGB")
    image = image.resize(IMG_SIZE)
    img_array = np.array(image) / 255.0
    img_array = np.expand_dims(img_array, axis=0)  # add batch dimension
    return img_array

# Example: load an image from URL
url = "https://example.com/sample_mri.jpg"
response = requests.get(url)
image = Image.open(BytesIO(response.content))

img_array = preprocess_image(image)
prediction = model.predict(img_array)[0][0]

if prediction >= 0.5:
    print("⚠️ Brain Tumor likely detected")
else:
    print("✅ Likely Healthy")