R-LLaVA: Improving Med-VQA Understanding through Visual Region of Interest

• URL: http://arxiv.org/abs/2410.20327v4
• Date: Fri, 07 Feb 2025 10:33:52 GMT
• Title: R-LLaVA: Improving Med-VQA Understanding through Visual Region of Interest
• Authors: Xupeng Chen, Zhixin Lai, Kangrui Ruan, Shichu Chen, Jiaxiang Liu, Zuozhu Liu,
• Abstract summary: R-LLaVA is designed to enhance biomedical VQA understanding by integrating simple medical annotations as prior knowledge directly into the image space through CLIP. These annotated visual regions of interest are then fed into the LLaVA model during training, aiming to enrich the model's understanding of biomedical queries.
• Score: 9.090795755887067
• License:
• Abstract: Artificial intelligence has made significant strides in medical visual question answering (Med-VQA), yet prevalent studies often interpret images holistically, overlooking the visual regions of interest that may contain crucial information, potentially aligning with a doctor's prior knowledge that can be incorporated with minimal annotations (e.g., bounding boxes). To address this gap, this paper introduces R-LLaVA, designed to enhance biomedical VQA understanding by integrating simple medical annotations as prior knowledge directly into the image space through CLIP. These annotated visual regions of interest are then fed into the LLaVA model during training, aiming to enrich the model's understanding of biomedical queries. Experimental evaluation on four standard Med-VQA datasets demonstrates R-LLaVA's superiority over existing state-of-the-art (SoTA) methods. Additionally, to verify the model's capability in visual comprehension, a novel multiple-choice medical visual understanding dataset is introduced, confirming the positive impact of focusing on visual regions of interest in advancing biomedical VQA understanding.

Related papers

• ClinKD: Cross-Modal Clinic Knowledge Distiller For Multi-Task Medical Images [4.353855760968461]
  Med-VQA (Medical Visual Question Answering) is a crucial subtask within the broader VQA (Visual Question Answering) domain. We introduce the ClinKD model, which incorporates modifications to model position encoding and a diversified training process. We achieve a new state-of-the-art performance on the Med-GRIT-270k dataset.
  arXiv  Detail & Related papers  (2025-02-09T15:08:10Z)
• Guiding Medical Vision-Language Models with Explicit Visual Prompts: Framework Design and Comprehensive Exploration of Prompt Variations [15.052986179046076]
  We introduce MedVP, a pioneering framework that integrates medical entity extraction, visual prompt generation, and dataset adaptation for visual prompt guided fine-tuning. We successfully outperform recent state-of-the-art large models across multiple medical VQA datasets.
  arXiv  Detail & Related papers  (2025-01-04T21:23:36Z)
• ViKL: A Mammography Interpretation Framework via Multimodal Aggregation of Visual-knowledge-linguistic Features [54.37042005469384]
  We announce MVKL, the first multimodal mammography dataset encompassing multi-view images, detailed manifestations and reports. Based on this dataset, we focus on the challanging task of unsupervised pretraining. We propose ViKL, a framework that synergizes Visual, Knowledge, and Linguistic features.
  arXiv  Detail & Related papers  (2024-09-24T05:01:23Z)
• MLIP: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning [48.97640824497327]
  We propose a novel framework leveraging domain-specific medical knowledge as guiding signals to integrate language information into the visual domain through image-text contrastive learning. Our model includes global contrastive learning with our designed divergence encoder, local token-knowledge-patch alignment contrastive learning, and knowledge-guided category-level contrastive learning with expert knowledge. Notably, MLIP surpasses state-of-the-art methods even with limited annotated data, highlighting the potential of multimodal pre-training in advancing medical representation learning.
  arXiv  Detail & Related papers  (2024-02-03T05:48:50Z)
• Visual Question Answering in the Medical Domain [13.673890873313354]
  We present a novel contrastive learning pretraining method to mitigate the problem of small datasets for the Med-VQA task. Our proposed model obtained an accuracy of 60% on the VQA-Med 2019 test set, giving comparable results to other state-of-the-art Med-VQA models.
  arXiv  Detail & Related papers  (2023-09-20T06:06:10Z)
• LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day [85.19963303642427]
  We propose a cost-efficient approach for training a vision-language conversational assistant that can answer open-ended research questions of biomedical images. The model first learns to align biomedical vocabulary using the figure-caption pairs as is, then learns to master open-ended conversational semantics. This enables us to train a Large Language and Vision Assistant for BioMedicine in less than 15 hours (with eight A100s)
  arXiv  Detail & Related papers  (2023-06-01T16:50:07Z)
• 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)
• A Dual-Attention Learning Network with Word and Sentence Embedding for Medical Visual Question Answering [2.0559497209595823]
  Research in medical visual question answering (MVQA) can contribute to the development of computer-aided diagnosis. Existing MVQA question extraction schemes mainly focus on word information, ignoring medical information in the text. In this study, a dual-attention learning network with word and sentence embedding (WSDAN) is proposed.
  arXiv  Detail & Related papers  (2022-10-01T08:32:40Z)
• Align, Reason and Learn: Enhancing Medical Vision-and-Language Pre-training with Knowledge [68.90835997085557]
  We propose a systematic and effective approach to enhance structured medical knowledge from three perspectives. First, we align the representations of the vision encoder and the language encoder through knowledge. Second, we inject knowledge into the multi-modal fusion model to enable the model to perform reasoning using knowledge as the supplementation of the input image and text. Third, we guide the model to put emphasis on the most critical information in images and texts by designing knowledge-induced pretext tasks.
  arXiv  Detail & Related papers  (2022-09-15T08:00:01Z)
• REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering [75.53187719777812]
  This paper revisits visual representation in knowledge-based visual question answering (VQA) We propose a new knowledge-based VQA method REVIVE, which tries to utilize the explicit information of object regions. We achieve new state-of-the-art performance, i.e., 58.0% accuracy, surpassing previous state-of-the-art method by a large margin.
  arXiv  Detail & Related papers  (2022-06-02T17:59:56Z)

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.