让AI像医生一样多轮对话理解医学图像，逐步推理病变区域。
MediRound: Multi-Round Entity-Level Reasoning Segmentation in Medical Images
- 通过多轮对话实现实体级医学推理分割，支持渐进式学习。
- 构建17.7万条多轮医学分割对话数据集，覆盖跨轮次实体推理。
- 提出轻量校验修正机制，有效缓解多轮推理中的误差累积。
尽管当前文本引导的医学图像分割取得显著进展，但现有方法仅支持单轮对话，无法实现多轮推理，而后者在医学教育场景中至关重要。本文提出多轮实体级医学推理分割（MEMR-Seg）新任务，要求通过多轮问答生成分割掩码，帮助学习者逐步建立医学知识理解。为此，我们构建了包含17.7万条多轮医学分割对话的大规模数据集MR-MedSeg，其特征在于跨轮次的实体级推理。同时提出MediRound基线模型，并在推理阶段引入轻量级校验与修正机制，以缓解多轮分割链中固有的误差传播问题。实验表明，该方法能有效解决MEMR-Seg任务，显著优于传统医学指代分割方法。项目代码已开源：https://github.com/Edisonhimself/MediRound。
原文摘要 · Abstract (English)
Despite notable progress in text-guided medical image segmentation nowadays, these methods are limited to single-round dialogues and fail to support multi-round reasoning, which is important for medical education scenarios. In this work, we introduce Multi-Round Entity-Level Medical Reasoning Segmentation (MEMR-Seg), a new task that requires generating segmentation masks through multi-round queries with entity-level reasoning, helping learners progressively develop their understanding of medical knowledge. To support this task, we construct MR-MedSeg, a large-scale dataset of 177K multi-round medical segmentation dialogues, featuring entity-based reasoning across rounds. Furthermore, we propose MediRound, an effective baseline model designed for multi-round medical reasoning segmentation. To mitigate the inherent error propagation within the chain-like pipeline of multi-round segmentation, we introduce a lightweight yet effective Judgment & Correction Mechanism during model inference. Experimental results demonstrate that our method effectively addresses the MEMR-Seg task and outperforms conventional medical referring segmentation methods. The project is available at https://github.com/Edisonhimself/MediRound.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。