关键在于提示：用于肺结节分割的基础模型中的提示敏感性与提示生成
What Matters is the Prompt: Prompt Sensitivity and Prompt Generation in Foundation Models for Lung Nodule Segmentation
浏览论文内容
中文总结 AI 辅助
本研究针对肺结节分割的基础模型，分析其对提示的敏感性，提出合成提示生成模型，实验显示该方法戴斯系数达0.85，为相关分割提供了有前景的策略。
中文摘要 AI 辅助
计算机断层扫描中的肺结节分割对于提取与肺癌评估及治疗规划相关的临床信息至关重要。基础模型已展现出显著的分割能力，但当前最先进的方法通常依赖输入提示，如点或框，这使得其性能对提示的质量和位置敏感。因此，理解基于提示的基础模型的局限性和约束对于设计可靠的医学图像分割解决方案至关重要。本研究探讨提示质量如何影响基础模型在肺结节分割中的性能，还提出一种合成提示生成模型，以测试是否可通过生成合成提示来减少对人工提供提示的依赖，同时提升分割性能。扰动实验显示，边界框提示通常优于点提示，而最新的专用医学成像模型比通用模型表现更好。所提方法的戴斯系数（Dice coefficient）达0.85，表明合成提示生成是利用基础模型进行肺结节分割的一种有前景的策略。
英文摘要
Lung nodule segmentation in computed tomography is essential for extracting clinically relevant information for lung cancer assessment and treatment planning. Foundation models have shown notable segmentation capabilities, but state-of-the-art approaches often depend on input prompts, such as points or boxes, making their performance sensitive to prompt quality and placement. Understanding the limitations and constraints of prompt-based foundation models is therefore essential for designing reliable medical image segmentation solutions. In this work, we investigate how prompt quality affects foundation models performance for lung nodule segmentation. We further propose a synthetic prompt-generation model to test if the dependence on manually provided prompts can be mitigated by generating synthetic prompts that can also improve segmentation performance. Perturbation experiments show that bounding box prompts generally outperform point prompts, while latest specialized medical imaging models achieve better performance than general purpose ones. The proposed approach obtains a Dice coefficient of 0.85, suggesting that synthetic prompt generation as a promising strategy for lung nodule segmentation with foundation models.
