X-ray Cancer Detection (DenseNet-121)

This project implements a deep learning pipeline for lung cancer detection from chest X-ray images using DenseNet-121.

Structure

• Notebooks/: Training, evaluation, Grad-CAM analysis
• Reports/: Metrics, figures, documentation
• Preprocessing_pipeline.py: Dataset preparation

Data & Models

Due to size constraints, datasets and trained models are stored in Google Drive.

🔗 Data: [link] 🔗 Models: [link]

Model

• Architecture: DenseNet-121
• Loss: Weighted Cross-Entropy
• Metrics: Accuracy, Recall, F1, ROC-AUC, MCC, ECE
• Explainability: Grad-CAM