devanshty/brain-cancer-detection

Brain Cancer Detection

Model Description

A fine-tuned EfficientNet-B0 model for classifying brain MRI scans into tumor vs. non-tumor categories. Trained to assist radiologists and medical professionals in the early detection of brain cancer from MRI images.

Model Architecture

• Base Model: EfficientNet-B0
• Framework: PyTorch
• Task: Binary / Multi-class image classification
• Input: MRI brain scan images (RGB, resized to model input size)

Training Details

• Dataset: Brain MRI tumor classification dataset (e.g., Kaggle Brain MRI Dataset)
• Approach: Transfer learning with EfficientNet-B0 pre-trained on ImageNet, fine-tuned on brain MRI data
• Augmentations: Random flips, rotations, normalization

Performance

Evaluated on held-out test split from the brain MRI dataset. Achieves high accuracy in distinguishing tumor from non-tumor MRI scans.

Files

File	Description
brain_model.pth	Final fine-tuned model weights
efficientnet_b0.pth	EfficientNet-B0 backbone weights

Usage

import torch
import torchvision.transforms as transforms
from PIL import Image
from huggingface_hub import hf_hub_download

# Download model
model_path = hf_hub_download(repo_id='devanshty/brain-cancer-detection', filename='brain_model.pth')

# Load model (adjust to your model class definition)
model = torch.load(model_path, map_location='cpu')
model.eval()

# Preprocess image
transform = transforms.Compose([
    transforms.Resize((224, 224)),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])
img = Image.open('brain_mri.jpg').convert('RGB')
input_tensor = transform(img).unsqueeze(0)

# Inference
with torch.no_grad():
    output = model(input_tensor)
    prediction = torch.argmax(output, dim=1)
print("Predicted class:", prediction.item())

Download & Use

from huggingface_hub import hf_hub_download
model_path = hf_hub_download(repo_id='devanshty/brain-cancer-detection', filename='brain_model.pth')

Disclaimer

This model is intended for research and educational purposes only. It should not be used as a substitute for professional medical diagnosis.