Scaling Large Vision-Language Models for Enhanced Multimodal Comprehension In Biomedical Image Analysis

• URL: http://arxiv.org/abs/2501.15370v1
• Date: Sun, 26 Jan 2025 02:48:01 GMT
• Title: Scaling Large Vision-Language Models for Enhanced Multimodal Comprehension In Biomedical Image Analysis
• Authors: Robinson Umeike, Neil Getty, Fangfang Xia, Rick Stevens,
• Abstract summary: Vision language models (VLMs) address this by incorporating a pretrained vision backbone for processing images and a cross-modal projector. We developed intelligent assistants finetuned from LLaVA models to enhance multimodal understanding in low-dose radiation therapy.
• Score: 0.1984949535188529
• License:
• Abstract: Large language models (LLMs) have demonstrated immense capabilities in understanding textual data and are increasingly being adopted to help researchers accelerate scientific discovery through knowledge extraction (information retrieval), knowledge distillation (summarizing key findings and methodologies into concise forms), and knowledge synthesis (aggregating information from multiple scientific sources to address complex queries, generate hypothesis and formulate experimental plans). However, scientific data often exists in both visual and textual modalities. Vision language models (VLMs) address this by incorporating a pretrained vision backbone for processing images and a cross-modal projector that adapts image tokens into the LLM dimensional space, thereby providing richer multimodal comprehension. Nevertheless, off-the-shelf VLMs show limited capabilities in handling domain-specific data and are prone to hallucinations. We developed intelligent assistants finetuned from LLaVA models to enhance multimodal understanding in low-dose radiation therapy (LDRT)-a benign approach used in the treatment of cancer-related illnesses. Using multilingual data from 42,673 articles, we devise complex reasoning and detailed description tasks for visual question answering (VQA) benchmarks. Our assistants, trained on 50,882 image-text pairs, demonstrate superior performance over base models as evaluated using LLM-as-a-judge approach, particularly in reducing hallucination and improving domain-specific comprehension.

Related papers

• RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training [55.54020926284334]
  Multimodal Large Language Models (MLLMs) have recently received substantial interest, which shows their emerging potential as general-purpose models for various vision-language tasks. Retrieval augmentation techniques have proven to be effective plugins for both LLMs and MLLMs. In this study, we propose multimodal adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training (RA-BLIP), a novel retrieval-augmented framework for various MLLMs.
  arXiv  Detail & Related papers  (2024-10-18T03:45:19Z)
• LLM4Brain: Training a Large Language Model for Brain Video Understanding [9.294352205183726]
  We introduce an LLM-based approach for reconstructing visual-semantic information from fMRI signals elicited by video stimuli. We employ fine-tuning techniques on an fMRI encoder equipped with adaptors to transform brain responses into latent representations aligned with the video stimuli. In particular, we integrate self-supervised domain adaptation methods to enhance the alignment between visual-semantic information and brain responses.
  arXiv  Detail & Related papers  (2024-09-26T15:57:08Z)
• Beyond the Hype: A dispassionate look at vision-language models in medical scenario [3.4299097748670255]
  Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across diverse tasks. Their performance and reliability in specialized domains such as medicine remain insufficiently assessed. We introduce RadVUQA, a novel benchmark to comprehensively evaluate existing LVLMs.
  arXiv  Detail & Related papers  (2024-08-16T12:32:44Z)
• X-Former: Unifying Contrastive and Reconstruction Learning for MLLMs [49.30255148577368]
  X-Former is a lightweight transformer module designed to exploit the complementary strengths of CL and MIM. X-Former first bootstraps vision-language representation learning and multimodal-to-multimodal generative learning from two frozen vision encoders. It further bootstraps vision-to-language generative learning from a frozen LLM to ensure visual features from X-Former can be interpreted by the LLM.
  arXiv  Detail & Related papers  (2024-07-18T18:39:54Z)
• Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge [76.45868419402265]
  multimodal large language models (MLLMs) have made significant strides by training on vast high-quality image-text datasets. However, the inherent difficulty in explicitly conveying fine-grained or spatially dense information in text, such as masks, poses a challenge for MLLMs. This paper proposes a new visual prompt approach to integrate fine-grained external knowledge, gleaned from specialized vision models, into MLLMs.
  arXiv  Detail & Related papers  (2024-07-05T17:43:30Z)
• On Large Visual Language Models for Medical Imaging Analysis: An Empirical Study [13.972931873011914]
  Large language models (LLMs) have taken the spotlight in natural language processing. Visual language models (VLMs), such as LLaVA, Flamingo, or CLIP, have demonstrated impressive performance on various visio-linguistic tasks.
  arXiv  Detail & Related papers  (2024-02-21T23:01:38Z)
• Incorporating Visual Experts to Resolve the Information Loss in Multimodal Large Language Models [121.83413400686139]
  This paper proposes to improve the visual perception ability of MLLMs through a mixture-of-experts knowledge enhancement mechanism. We introduce a novel method that incorporates multi-task encoders and visual tools into the existing MLLMs training and inference pipeline.
  arXiv  Detail & Related papers  (2024-01-06T02:02:34Z)
• Behind the Magic, MERLIM: Multi-modal Evaluation Benchmark for Large Image-Language Models [50.653838482083614]
  This paper introduces a scalable test-bed to assess the capabilities of IT-LVLMs on fundamental computer vision tasks. MERLIM contains over 300K image-question pairs and has a strong focus on detecting cross-modal "hallucination" events in IT-LVLMs.
  arXiv  Detail & Related papers  (2023-12-03T16:39:36Z)
• XrayGPT: Chest Radiographs Summarization using Medical Vision-Language Models [60.437091462613544]
  We introduce XrayGPT, a novel conversational medical vision-language model. It can analyze and answer open-ended questions about chest radiographs. We generate 217k interactive and high-quality summaries from free-text radiology reports.
  arXiv  Detail & Related papers  (2023-06-13T17:59:59Z)

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.