arXiv 2510.031892025-12-16cs.CV

动态提示生成用于交互式3D医学图像分割训练

Dynamic Prompt Generation for Interactive 3D Medical Image Segmentation Training

Medical Physics, Department of Diagnostic and Interventional Radiology, Medical Center—University of Freiburg, Faculty of Medicine, University of Freiburg（医学物理，诊断与介入放射科，弗赖堡大学医学中心，医学院，弗赖堡大学）；University of Freiburg（弗赖堡大学）；ELLIS Institute Tübingen（图宾根ELLIS研究所）

Tidiane Camaret Ndir, Alexander Pfefferle, Robin Tibor Schirrmeister

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出一种动态提示生成方法，结合内容感知自适应裁剪优化图像编码器，提升交互式3D医学图像分割的性能。

摘要：

交互式3D生物医学图像分割需要高效的模型，能够根据用户提示迭代地细化预测。当前的基础模型要么缺乏体积意识，要么交互能力有限。我们提出了一种训练策略，结合动态体积分段提示生成和内容感知的自适应裁剪，以优化图像编码器的使用。我们的方法在训练过程中模拟真实的用户交互模式，同时解决在单个GPU上学习从连续细化反馈中学习的计算挑战。为了高效训练，我们使用公开可用的nnInteractive分割模型权重初始化网络。在Foundation Models for Interactive 3D Biomedical Image Segmentation竞赛上的评估显示，平均最终Dice得分为0.6385，归一化表面距离为0.6614，面积-曲线指标分别为2.4799（Dice）和2.5671（NSD）。

英文摘要：

Interactive 3D biomedical image segmentation requires efficient models that can iteratively refine predictions based on user prompts. Current foundation models either lack volumetric awareness or suffer from limited interactive capabilities. We propose a training strategy that combines dynamic volumetric prompt generation with content-aware adaptive cropping to optimize the use of the image encoder. Our method simulates realistic user interaction patterns during training while addressing the computational challenges of learning from sequential refinement feedback on a single GPU. For efficient training, we initialize our network using the publicly available weights from the nnInteractive segmentation model. Evaluation on the \textbf{Foundation Models for Interactive 3D Biomedical Image Segmentation} competition demonstrates strong performance with an average final Dice score of 0.6385, normalized surface distance of 0.6614, and area-under-the-curve metrics of 2.4799 (Dice) and 2.5671 (NSD).

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。