RaDialog Instruct Dataset

Conversational AI tools that can generate and discuss clinically correct
radiology reports for a given medical image have the potential to transform
radiology. Such a human-in-the-loop radiology assistant could facilitate a
collaborative diagnostic process, thus saving time and improving the quality
of reports. Towards this goal, we introduce RaDialog, the first thoroughly
evaluated and publicly available large vision-language model for radiology
report generation and interactive dialog. To keep the conversational abilities
of the underlying LLM, we propose a comprehensive, semi-automatically labeled,
image-grounded instruct dataset for chest X-ray radiology tasks. The dataset
includes a variety of tasks, such as report correction, summarization or
finding prediction. By training with this dataset, our method achieves state-
of-the-art clinical correctness in report generation and shows impressive
abilities in interactive tasks such as correcting reports and answering
questions, serving as a foundational step toward clinical dialog systems.

能够针对给定医学影像生成并讨论临床准确的放射科报告的对话式AI工具，有望推动放射学领域的变革。此类人机协作式放射学助手可助力协同诊断流程，从而节省时间并提升报告质量。为此，我们推出了RaDialog——首个经过全面评估且公开可用的、面向放射科报告生成与交互式对话的大型视觉语言模型（large vision-language model）。为保留底层大语言模型（Large Language Model）的对话能力，我们构建了一套面向胸部X光放射学任务的综合性、半自动化标注、基于影像的指令数据集。该数据集涵盖多种任务，例如报告修正、摘要生成与征象预测。通过该数据集训练后，我们的方法在报告生成任务中实现了当前最优的临床准确性，且在报告修正、问题解答等交互式任务中展现出出色的能力，为临床对话系统的研发奠定了基础。

搜集汇总

背景与挑战

背景概述

RaDialog Instruct Dataset是一个专门用于训练放射学交互式AI助手的大型视觉语言指令数据集。它基于胸部X光图像和报告构建，包含报告生成、修正、总结、病理预测等多种任务，旨在提升模型在临床正确性和对话能力方面的表现。数据集部分通过现有医疗数据集（如MIMIC-CXR）和大型语言模型自动生成，支持多样化的下游应用，但需注意自动生成内容可能存在医学准确性限制。