MedAI Vision
2025 · GAN super-resolution and MRI-to-CT translation, a ViT-CNN classifier for brain, breast and lung scans, and a fine-tuned Llama 3.2 that explains the results.
- Python
- PyTorch
- TensorFlow
- Llama
- React
- Node.js
- MongoDB
- Git
Highlights
- Built a super-resolution GAN (TensorFlow) for MRI/CT clarity achieving 92% accuracy on 54,000 samples, and a CycleGAN (PyTorch) for bidirectional MRI-to-CT translation; designed a hybrid Vision Transformer-CNN for multi-label disease classification across brain, breast, and lung scans with 88.4% accuracy.
- Fine-tuned Llama 3.2 11B on medical literature to deliver explainable AI insights with diagnosis, severity levels, and treatment recommendations, achieving 74% user retention.