动态生成提示，提升3D医学图像交互分割效率
Dynamic Prompt Generation for Interactive 3D Medical Image Segmentation Training
- 训练时模拟用户交互，动态生成体积提示并自适应裁剪
- 在单张显卡上实现高效训练，最终Dice达0.6385
- 适合需要实时交互的医学影像分割研究者
交互式3D生物医学图像分割需要高效模型，能基于用户提示迭代优化分割结果。现有基础模型或缺乏体数据感知能力，或交互能力受限。本文提出一种训练策略，结合动态体素提示生成与内容感知自适应裁剪，优化图像编码器使用。训练中模拟真实用户交互模式，同时解决单卡学习序列精修反馈的计算挑战。采用公开的nnInteractive模型权重初始化网络。在「基础模型用于交互式3D生物医学图像分割」竞赛中表现优异，平均最终Dice得分为0.6385，归一化表面距离为0.6614，曲线下面积指标分别为2.4799（Dice）和2.5671（NSD）。
原文摘要 · Abstract (English)
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).
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。