面向胸部X光的指令引导病灶分割及自动构建的大规模数据集
Instruction-Guided Lesion Segmentation for Chest X-rays with Automatically Generated Large-Scale Dataset
把指代图像分割（RIS）迁移到胸片病灶分割，用自动化多模态流水线从图像-报告对生成 110 万条指令-答案对，并微调 LISA 类多模态大模型实现指令驱动的像素级病灶定位与文本解释，为视觉研究者提供了「用报告自动造分割监督」的可复用范式。
原文依据 we construct MIMIC-ILS, the first large-scale instruction-answer dataset for CXR lesion segmentation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论当前胸部X光（CXR）病灶分割模型的适用性受到两方面限制：一是目标标签数量少，二是依赖复杂、专家级的文本输入，这为实际使用造成了障碍。为解决这些限制，我们提出指令引导病灶分割（ILS），这是指代图像分割（RIS）在医学领域的适配，旨在根据简单、易用的指令分割多种类型的病灶。在该任务下，我们构建了 MIMIC-ILS，这是首个面向 CXR 病灶分割的大规模指令-答案数据集，使用我们全自动的多模态流水线从 CXR 图像及其对应报告生成标注。MIMIC-ILS 包含 110 万条指令-答案对，源自 19.2 万张图像和 9.1 万个唯一分割掩码，覆盖七种主要病灶类型。为实证其效用，我们提出 ROSALIA，一个在 MIMIC-ILS 数据集上微调的 LISA 模型。ROSALIA 能够根据用户指令分割多种病灶并提供文本解释。该模型在我们新提出的任务上取得高准确率，凸显了我们流水线的有效性以及 MIMIC-ILS 作为像素级 CXR 病灶定位基础资源的价值。数据集与模型见 https://github.com/checkoneee/ROSALIA。
英文原文摘要 1345 字符
The applicability of current lesion segmentation models for chest X-rays (CXRs) has been limited both by a small number of target labels and the reliance on complex, expert-level text inputs, creating a barrier to practical use. To address these limitations, we introduce instruction-guided lesion segmentation (ILS), a medical-domain adaptation of referring image segmentation (RIS) designed to segment diverse lesion types based on simple, user-friendly instructions. Under this task, we construct MIMIC-ILS, the first large-scale instruction-answer dataset for CXR lesion segmentation, using our fully automated multimodal pipeline that generates annotations from CXR images and their corresponding reports. MIMIC-ILS contains 1.1M instruction-answer pairs derived from 192K images and 91K unique segmentation masks, covering seven major lesion types. To empirically demonstrate its utility, we present ROSALIA, a LISA model fine-tuned on the MIMIC-ILS dataset. ROSALIA can segment diverse lesions and provide textual explanations in response to user instructions. The model achieves high accuracy in our newly proposed task, highlighting the effectiveness of our pipeline and the value of MIMIC-ILS as a foundational resource for pixel-level CXR lesion grounding. The dataset and model are available at https://github.com/checkoneee/ROSALIA.