View Proposal

Proposer
Heba Elshimy
Title
Medical Visual Question Answering with Reasoning Chains
Goal
This project explores reasoning-augmented medical VQA, wherein models generate not only answers but also interpretable chains of reasoning that can be audited for clinical sensibility
Description
Current medical Visual Question Answering (VQA) systems typically treat questions as classification problems, producing answers without explanation of the underlying reasoning process. This opacity limits clinical trust and adoption, as healthcare professionals require transparent decision-making to validate AI recommendations.
Resources
Datasets: VQA-RAD (https://huggingface.co/datasets/flaviagiammarino/vqa-rad), PathVQA (https://github.com/UCSD-AI4H/PathVQA), PMC-VQA (https://huggingface.co/datasets/xmcmic/PMC-VQA)
Background
Working with huggingface models
Url
Difficulty Level
High
Ethical Approval
None
Number Of Students
1
Supervisor
Heba Elshimy
Keywords
vqa, vlms, ai for healthcare
Degrees
Master of Science in Artificial Intelligence
Master of Science in Computer Science for Cyber Security
Master of Science in Data Science
Master of Science in Network Security
MSc Applied Cyber Security
Back to List