CG-Reasoner：质心引导的位置推理分割用于医学影像及一个鲁棒的视觉-文本一致性指标
CG-Reasoner: Centroid-Guided Positional Reasoning Segmentation for Medical Imaging with a Robust Visual-Text Consistency Metric
将多模态大语言模型的推理能力与轻量级分割网络结合，通过Text2Centroid模块从推理嵌入预测病灶质心，为医学图像分割提供可解释的位置推理；提出的PRScore指标可评估生成文本与分割掩码的空间语义对齐，可复用于其他视觉-语言分割任务。
原文依据 We introduce CG-Reasoner, a novel centroid-guided cross-modal framework that jointly performs medical image segmentation and positional reasoning.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论准确且可解释的医学图像分割仍是一项重大挑战，因为现有深度学习模型主要优化像素级准确率，而忽视了位置推理——这是自动化报告生成和临床可解释性的关键组成部分。我们提出CG-Reasoner，一种新颖的质心引导跨模态框架，联合执行医学图像分割和位置推理。CG-Reasoner集成了多模态大语言模型（LLM）、新设计的轻量级编码器-解码器架构以及一个Text2Centroid模块，该模块从推理嵌入中预测病灶质心，使模型能够同时生成准确的分割掩码和空间连贯、具有临床意义的推理解释。此外，我们提出PRScore（位置推理分数），一种鲁棒的评估指标，联合衡量生成的推理文本与分割掩码之间的空间和语义对齐。在六个不同成像模态的医学数据集上的实验表明，CG-Reasoner达到了最优性能，在一个统一框架内提供了精确分割、空间连贯推理以及临床可解释的视觉-文本解释。源代码见https://github.com/lpmm2025/CG-Reasoner。
英文原文摘要 1330 字符
Accurate and interpretable medical image segmentation remains a major challenge, as existing deep learning models primarily optimize pixel-level accuracy while overlooking positional reasoning--an essential component for automated report generation and clinical interpretability. We introduce CG-Reasoner, a novel centroid-guided cross-modal framework that jointly performs medical image segmentation and positional reasoning. CG-Reasoner integrates a multimodal large language model (LLM), a newly designed light-weight encoder-decoder architecture, and a Text2Centroid module that predicts lesion centroids from reasoning embeddings--enabling the model to produce both accurate segmentation masks and spatially coherent, clinically meaningful reasoning explanations. Furthermore, we propose PRScore (Positional-Reasoning Score), a robust evaluation metric that jointly measures the spatial and semantic alignment between generated reasoning text and segmentation masks. Experiments on six medical datasets across different imaging modalities demonstrate that CG-Reasoner achieves state-of-the-art performance, offering precise segmentation, spatially coherent reasoning, and clinically interpretable visual-textual explanations within a unified framework. The source code is available at https://github.com/lpmm2025/CG-Reasoner.