# Querying GI Endoscopy Images: A VQA Approach

Source: [Querying GI Endoscopy Images: A VQA Approach](<https://www.sota2.com/research/paper/68fa7a4e1e209131cea825a3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:58:49.434Z

Authors: Gaurav Parajuli

Published: 2025-07-25T13:03:46.000Z

## Abstract

VQA (Visual Question Answering) combines Natural Language Processing (NLP) with image understanding to answer questions about a given image. It has enormous potential for the development of medical diagnostic AI systems. Such a system can help clinicians diagnose gastro-intestinal (GI) diseases accurately and efficiently. Although many of the multimodal LLMs available today have excellent VQA capabilities in the general domain, they perform very poorly for VQA tasks in specialized domains such as medical imaging. This study is a submission for ImageCLEFmed-MEDVQA-GI 2025 subtask 1 that explores the adaptation of the Florence2 model to answer medical visual questions on GI endoscopy images. We also evaluate the model performance using standard metrics like ROUGE, BLEU and METEOR

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2507.21165>)

[PDF](<https://arxiv.org/pdf/2507.21165.pdf>)
