Querying GI Endoscopy Images: A VQA Approach
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918106646970368 |
|---|---|
| author | Parajuli, Gaurav |
| author_facet | Parajuli, Gaurav |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_21165 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Querying GI Endoscopy Images: A VQA Approach Parajuli, Gaurav Image and Video Processing Computer Vision and Pattern Recognition 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 |
| title | Querying GI Endoscopy Images: A VQA Approach |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.21165 |