Causal-SAM-LLM：大型语言模型作为因果推理器用于稳健的医学分割
Causal-SAM-LLM: Large Language Models as Causal Reasoners for Robust Medical Segmentation
AI总结：
Causal-SAM-LLM利用大型语言模型作为因果推理器，提升医学图像分割的鲁棒性和泛化能力。
摘要：
深度学习模型在医学图像分割中的临床实用性严重受限于其无法泛化到未见领域的能力。这种失败往往源于模型学习了解剖内容与领域特定成像风格之间的虚假相关性。为克服这一根本挑战，我们引入了Causal-SAM-LLM，一种新的框架，将大型语言模型（LLMs）提升到因果推理器的角色。我们的框架基于冻结的Segment Anything Model（SAM）编码器，集成了两个协同创新。首先，Linguistic Adversarial Disentanglement（LAD）利用视觉语言模型生成丰富的文本描述，以描述混淆的图像风格。通过训练分割模型的特征使其在对比上与这些风格描述不同，它学习了一种鲁棒地去除非因果信息的表示。其次，Test-Time Causal Intervention（TCI）提供了一种交互机制，其中LLM解读医生的自然语言命令，以实时调节分割解码器的特征，实现有针对性的错误纠正。我们在四个公开数据集（BTCV、CHAOS、AMOS、BraTS）的复合基准上进行了广泛的实证评估，评估在跨扫描仪、跨模态和跨解剖设置下的泛化能力。Causal-SAM-LLM在分布外（OOD）鲁棒性上建立了新的状态，平均Dice分数提高了最高6.2分，Hausdorff距离减少了15.8毫米，同时使用少于完整模型9%的可训练参数。我们的工作为构建稳健、高效且可交互控制的医学AI系统开辟了新道路。
英文摘要：
The clinical utility of deep learning models for medical image segmentation is severely constrained by their inability to generalize to unseen domains. This failure is often rooted in the models learning spurious correlations between anatomical content and domain-specific imaging styles. To overcome this fundamental challenge, we introduce Causal-SAM-LLM, a novel framework that elevates Large Language Models (LLMs) to the role of causal reasoners. Our framework, built upon a frozen Segment Anything Model (SAM) encoder, incorporates two synergistic innovations. First, Linguistic Adversarial Disentanglement (LAD) employs a Vision-Language Model to generate rich, textual descriptions of confounding image styles. By training the segmentation model's features to be contrastively dissimilar to these style descriptions, it learns a representation robustly purged of non-causal information. Second, Test-Time Causal Intervention (TCI) provides an interactive mechanism where an LLM interprets a clinician's natural language command to modulate the segmentation decoder's features in real-time, enabling targeted error correction. We conduct an extensive empirical evaluation on a composite benchmark from four public datasets (BTCV, CHAOS, AMOS, BraTS), assessing generalization under cross-scanner, cross-modality, and cross-anatomy settings. Causal-SAM-LLM establishes a new state of the art in out-of-distribution (OOD) robustness, improving the average Dice score by up to 6.2 points and reducing the Hausdorff Distance by 15.8 mm over the strongest baseline, all while using less than 9% of the full model's trainable parameters. Our work charts a new course for building robust, efficient, and interactively controllable medical AI systems.
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。
