M4CXR：探索多任务潜力的多模态大语言模型在胸部X光解读中的应用
M4CXR: Exploring Multi-task Potentials of Multi-modal Large Language Models for Chest X-ray Interpretation
AI总结：
本文提出M4CXR，一种多模态大语言模型，通过链式推理策略提升胸部X光报告生成的临床准确性，并在视觉问答和视觉 grounding 任务中表现出色。
摘要：
人工智能的快速发展，尤其是大语言模型（LLMs）的演进，已显著影响多个领域，包括医疗保健。在胸部X光（CXR）分析中，先前研究使用了LLMs，但存在局限：要么未充分利用LLMs的多任务能力，要么缺乏临床准确性。本文提出了M4CXR，一种多模态LLM，旨在增强CXR解读。该模型在视觉指令遵循数据集上进行训练，该数据集整合了各种任务特定数据集，以对话格式呈现。因此，该模型支持多种任务，如医疗报告生成（MRG）、视觉定位和视觉问答（VQA）。M4CXR通过采用链式推理提示策略，在MRG任务中实现了最先进的临床准确性，通过识别CXR图像中的发现并生成相应报告。该模型可根据可用输入适应各种MRG场景，如单图像、多图像和多研究情境。除了MRG之外，M4CXR在视觉定位任务中表现与专用模型相当，并在VQA任务中表现出色。定量和定性评估表明，M4CXR在MRG、视觉定位和VQA任务中表现出多任务能力，同时始终保持临床准确性。
英文摘要：
The rapid evolution of artificial intelligence, especially in large language models (LLMs), has significantly impacted various domains, including healthcare. In chest X-ray (CXR) analysis, previous studies have employed LLMs, but with limitations: either underutilizing the multi-tasking capabilities of LLMs or lacking clinical accuracy. This paper presents M4CXR, a multi-modal LLM designed to enhance CXR interpretation. The model is trained on a visual instruction-following dataset that integrates various task-specific datasets in a conversational format. As a result, the model supports multiple tasks such as medical report generation (MRG), visual grounding, and visual question answering (VQA). M4CXR achieves state-of-the-art clinical accuracy in MRG by employing a chain-of-thought prompting strategy, in which it identifies findings in CXR images and subsequently generates corresponding reports. The model is adaptable to various MRG scenarios depending on the available inputs, such as single-image, multi-image, and multi-study contexts. In addition to MRG, M4CXR performs visual grounding at a level comparable to specialized models and also demonstrates outstanding performance in VQA. Both quantitative and qualitative assessments reveal M4CXR's versatility in MRG, visual grounding, and VQA, while consistently maintaining clinical accuracy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
