A Refer-and-Ground Multimodal Large Language Model for Biomedicine
- URL: http://arxiv.org/abs/2406.18146v2
- Date: Fri, 28 Jun 2024 06:43:39 GMT
- Title: A Refer-and-Ground Multimodal Large Language Model for Biomedicine
- Authors: Xiaoshuang Huang, Haifeng Huang, Lingdong Shen, Yehui Yang, Fangxin Shang, Junwei Liu, Jia Liu,
- Abstract summary: The Med-GRIT-270k dataset is the first dedicated to the biomedical domain and integrates refer and ground conversations.
We introduce a Refer-and-Ground Multimodal Large Language Model for Biomedicine (BiRD) by using this dataset and multi-task instruction learning.
- Score: 10.519866875035003
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: With the rapid development of multimodal large language models (MLLMs), especially their capabilities in visual chat through refer and ground functionalities, their significance is increasingly recognized. However, the biomedical field currently exhibits a substantial gap in this area, primarily due to the absence of a dedicated refer and ground dataset for biomedical images. To address this challenge, we devised the Med-GRIT-270k dataset. It comprises 270k question-and-answer pairs and spans eight distinct medical imaging modalities. Most importantly, it is the first dedicated to the biomedical domain and integrating refer and ground conversations. The key idea is to sample large-scale biomedical image-mask pairs from medical segmentation datasets and generate instruction datasets from text using chatGPT. Additionally, we introduce a Refer-and-Ground Multimodal Large Language Model for Biomedicine (BiRD) by using this dataset and multi-task instruction learning. Extensive experiments have corroborated the efficacy of the Med-GRIT-270k dataset and the multi-modal, fine-grained interactive capabilities of the BiRD model. This holds significant reference value for the exploration and development of intelligent biomedical assistants.
Related papers
- BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature [73.39593644054865]
BIOMEDICA is a scalable, open-source framework to extract, annotate, and serialize the entirety of the PubMed Central Open Access subset into an easy-to-use, publicly accessible dataset.
Our framework produces a comprehensive archive with over 24 million unique image-text pairs from over 6 million articles.
BMCA-CLIP is a suite of CLIP-style models continuously pretrained on the BIOMEDICA dataset via streaming, eliminating the need to download 27 TB of data locally.
arXiv Detail & Related papers (2025-01-13T09:58:03Z) - MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants [28.04215981636089]
We present MedMax, the first large-scale multimodal biomedical instruction-tuning dataset for mixed-modal foundation models.
With 1.47 million instances, MedMax encompasses a diverse range of tasks, including multimodal content generation (interleaved image-text data), biomedical image captioning and generation, visual chatting, and report understanding.
We fine-tune a mixed-modal foundation model on the MedMax dataset, achieving significant performance improvements.
arXiv Detail & Related papers (2024-12-17T08:30:00Z) - Towards a Multimodal Large Language Model with Pixel-Level Insight for Biomedicine [9.881981672848598]
We introduce a novel end-to-end multimodal large language model for the biomedical domain, named MedPLIB.
It supports visual question answering (VQA), arbitrary pixel-level prompts (points, bounding boxes, and free-form shapes), and pixel-level grounding.
Results indicate that MedPLIB has achieved state-of-the-art outcomes across multiple medical visual language tasks.
arXiv Detail & Related papers (2024-12-12T13:41:35Z) - A Survey of Medical Vision-and-Language Applications and Their Techniques [48.268198631277315]
Medical vision-and-language models (MVLMs) have attracted substantial interest due to their capability to offer a natural language interface for interpreting complex medical data.
Here, we provide a comprehensive overview of MVLMs and the various medical tasks to which they have been applied.
We also examine the datasets used for these tasks and compare the performance of different models based on standardized evaluation metrics.
arXiv Detail & Related papers (2024-11-19T03:27:05Z) - 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) - MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine [53.01393667775077]
This paper introduces MedTrinity-25M, a comprehensive, large-scale multimodal dataset for medicine.
It covers over 25 million images across 10 modalities, with multigranular annotations for more than 65 diseases.
Unlike existing approach which is limited by the availability of image-text pairs, we have developed the first automated pipeline.
arXiv Detail & Related papers (2024-08-06T02:09:35Z) - Towards Generalist Biomedical AI [28.68106423175678]
We introduce Med-PaLM Multimodal (Med-PaLM M), our proof of concept for a generalist biomedical AI system.
Med-PaLM M is a large multimodal generative model that flexibly encodes and interprets biomedical data.
We conduct a radiologist evaluation of model-generated (and human) chest X-ray reports and observe encouraging performance across model scales.
arXiv Detail & Related papers (2023-07-26T17:52:22Z) - 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) - BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs [46.87322157229728]
We present PMC-15M, a novel dataset that is two orders of magnitude larger than existing biomedical multimodal datasets.
PMC-15M contains 15 million biomedical image-text pairs collected from 4.4 million scientific articles.
Based on PMC-15M, we have pretrained BiomedCLIP, a multimodal foundation model, with domain-specific adaptations tailored to biomedical vision-language processing.
arXiv Detail & Related papers (2023-03-02T02:20:04Z)
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.