Visual Question Answering (VQA) for Medical Imaging

This project addresses the challenge of accurate and efficient medical imaging analysis in healthcare, aiming to reduce human error and workload for radiologists. The proposed solution involves developing advanced AI models for Visual Question Answering (VQA) to assist healthcare professionals in analyzing medical images (radiology images) quickly and accurately. We fine-tune HuggingFace multimodal model Idefics2-8b using radiology VQA datasets.

We fine-tune pre-trained model using these datasets :

• VQA-RAD dataset
• SLAKE dataset
• ROCO dataset

The model is trained using Idefics2-8b.