Multimodal AI for Gastrointestinal Diagnostics: Tackling VQA in MEDVQA-GI 2025

• URL: http://arxiv.org/abs/2507.14544v1
• Date: Sat, 19 Jul 2025 09:04:13 GMT
• Title: Multimodal AI for Gastrointestinal Diagnostics: Tackling VQA in MEDVQA-GI 2025
• Authors: Sujata Gaihre, Amir Thapa Magar, Prasuna Pokharel, Laxmi Tiwari,
• Abstract summary: This paper describes our approach to Subtask 1 of the ImageCLEFmed MEDVQA 2025 Challenge.<n>We adopt the Florence model-a large-scale multimodal foundation model-as the backbone of our VQA pipeline.<n>Experiments on the KASVIR dataset show that fine-tuning Florence yields accurate responses on the official challenge metrics.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper describes our approach to Subtask 1 of the ImageCLEFmed MEDVQA 2025 Challenge, which targets visual question answering (VQA) for gastrointestinal endoscopy. We adopt the Florence model-a large-scale multimodal foundation model-as the backbone of our VQA pipeline, pairing a powerful vision encoder with a text encoder to interpret endoscopic images and produce clinically relevant answers. To improve generalization, we apply domain-specific augmentations that preserve medical features while increasing training diversity. Experiments on the KASVIR dataset show that fine-tuning Florence yields accurate responses on the official challenge metrics. Our results highlight the potential of large multimodal models in medical VQA and provide a strong baseline for future work on explainability, robustness, and clinical integration. The code is publicly available at: https://github.com/TiwariLaxuu/VQA-Florence.git

Related papers

• Querying GI Endoscopy Images: A VQA Approach [0.0]
  VQA (Visual Question Answering) combines Natural Language Processing (NLP) with image understanding to answer questions about a given image.<n>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.
  arXiv  Detail & Related papers  (2025-07-25T13:03:46Z)
• MedGemma Technical Report [75.88152277443179]
  We introduce MedGemma, a collection of medical vision-language foundation models based on Gemma 3 4B and 27B.<n>MedGemma demonstrates advanced medical understanding and reasoning on images and text.<n>We additionally introduce MedSigLIP, a medically-tuned vision encoder derived from SigLIP.
  arXiv  Detail & Related papers  (2025-07-07T17:01:44Z)
• Kvasir-VQA-x1: A Multimodal Dataset for Medical Reasoning and Robust MedVQA in Gastrointestinal Endoscopy [3.3091869879941687]
  We introduce Kvasir-VQA-x1, a new, large-scale dataset for gastrointestinal (GI) endoscopy.<n>Our work significantly expands upon the original Kvasir-VQA by incorporating 159,549 new question-answer pairs.<n>By providing a more challenging and clinically relevant benchmark, Kvasir-VQA-x1 aims to accelerate the development of more reliable and effective multimodal AI systems.
  arXiv  Detail & Related papers  (2025-06-11T17:31:38Z)
• OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM [48.16696073640864]
  We introduce OmniMedVQA, a novel comprehensive medical Visual Question Answering (VQA) benchmark. All images in this benchmark are sourced from authentic medical scenarios. We have found that existing LVLMs struggle to address these medical VQA problems effectively.
  arXiv  Detail & Related papers  (2024-02-14T13:51:56Z)
• MISS: A Generative Pretraining and Finetuning Approach for Med-VQA [16.978523518972533]
  We propose a large-scale MultI-task Self-Supervised learning based framework (MISS) for medical VQA tasks. We unify the text encoder and multimodal encoder and align image-text features through multi-task learning. Our method achieves excellent results with fewer multimodal datasets and demonstrates the advantages of generative VQA models.
  arXiv  Detail & Related papers  (2024-01-10T13:56:40Z)
• Med-Flamingo: a Multimodal Medical Few-shot Learner [58.85676013818811]
  We propose Med-Flamingo, a multimodal few-shot learner adapted to the medical domain. Based on OpenFlamingo-9B, we continue pre-training on paired and interleaved medical image-text data from publications and textbooks. We conduct the first human evaluation for generative medical VQA where physicians review the problems and blinded generations in an interactive app.
  arXiv  Detail & Related papers  (2023-07-27T20:36:02Z)
• PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering [56.25766322554655]
  Medical Visual Question Answering (MedVQA) presents a significant opportunity to enhance diagnostic accuracy and healthcare delivery. We propose a generative-based model for medical visual understanding by aligning visual information from a pre-trained vision encoder with a large language model. We train the proposed model on PMC-VQA and then fine-tune it on multiple public benchmarks, e.g., VQA-RAD, SLAKE, and Image-Clef 2019.
  arXiv  Detail & Related papers  (2023-05-17T17:50:16Z)
• Medical Visual Question Answering: A Survey [55.53205317089564]
  Medical Visual Question Answering(VQA) is a combination of medical artificial intelligence and popular VQA challenges. Given a medical image and a clinically relevant question in natural language, the medical VQA system is expected to predict a plausible and convincing answer.
  arXiv  Detail & Related papers  (2021-11-19T05:55:15Z)
• MMBERT: Multimodal BERT Pretraining for Improved Medical VQA [23.78515287446131]
  We propose a solution inspired by self-supervised pretraining of Transformer-style architectures for NLP, Vision and Language tasks. Our method involves learning richer medical image and text semantic representations using Masked Language Modeling. The proposed solution achieves new state-of-the-art performance on two VQA datasets for radiology images.
  arXiv  Detail & Related papers  (2021-04-03T13:01:19Z)
• Learning Contextualized Document Representations for Healthcare Answer Retrieval [68.02029435111193]
  Contextual Discourse Vectors (CDV) is a distributed document representation for efficient answer retrieval from long documents. Our model leverages a dual encoder architecture with hierarchical LSTM layers and multi-task training to encode the position of clinical entities and aspects alongside the document discourse. We show that our generalized model significantly outperforms several state-of-the-art baselines for healthcare passage ranking.
  arXiv  Detail & Related papers  (2020-02-03T15:47:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.