View Proposal

Proposer
Heba Elshimy
Title
VLM-Powered Radiology Report Generation with Faithfulness Verification
Goal
This project develops a dual-purpose system that both generates radiology reports and implements a self-verification mechanism to detect inconsistencies between generated findings and image evidence
Description
Automated radiology report generation has advanced considerably with vision-language models; however, a critical unsolved challenge remains: ensuring that generated text faithfully reflects the actual image content rather than producing plausible but clinically incorrect statements (hallucinations).
Resources
Datasets: IU X-Ray (https://www.kaggle.com/datasets/raddar/chest-xrays-indiana-university)
Background
Working with huggingface models and VLMs
Url
Difficulty Level
Challenging
Ethical Approval
None
Number Of Students
1
Supervisor
Heba Elshimy
Keywords
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