MorphSeek：面向可变形图像配准的细粒度潜表征级策略优化
MorphSeek: Fine-grained Latent Representation-Level Policy Optimization for Deformable Image Registration
把 DIR 的稠密位移场优化搬到潜特征空间，用高斯策略头 + GRPO 做由粗到细的探索，这种「表征级策略优化」思路可迁移到任何高维稠密预测任务（如光流、稠密对应、点云配准）的搜索式优化中。
原文依据 reformulates DIR as a spatially continuous optimization process in the latent feature space
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论可变形图像配准（DIR）仍是医学图像分析中一个基础而富有挑战性的问题，这在很大程度上源于稠密位移场的高维形变空间规模过大，以及体素级监督的稀缺。现有的强化学习框架往往将该空间投影为粗糙的低维表示，从而限制了其捕捉空间变化形变的能力。我们提出 MorphSeek，一种细粒度的表征级策略优化范式，将 DIR 重新表述为潜特征空间中的空间连续优化过程。MorphSeek 在编码器之上引入随机高斯策略头，对潜特征上的分布进行建模，从而促进高效探索与由粗到细的细化。该框架通过组相对策略优化将无监督预热与弱监督微调相结合，其中多轨迹采样可稳定训练并提升标签效率。在三个 3D 配准基准（OASIS 脑部 MRI、LiTS 肝脏 CT 与 Abdomen MR-CT）上，MorphSeek 相较有竞争力的基线取得了一致的 Dice 提升，同时以极小的参数代价和较低的步级延迟开销保持高标签效率。除优化器细节之外，MorphSeek 还推进了一种表征级策略学习范式，实现了空间连贯且数据高效的形变优化，为高维场景下的可扩展视觉对齐提供了一种有原则、与骨干网络无关且与优化器无关的解决方案。
英文原文摘要 1587 字符
Deformable image registration (DIR) remains a fundamental yet challenging problem in medical image analysis, largely due to the prohibitively high-dimensional deformation space of dense displacement fields and the scarcity of voxel-level supervision. Existing reinforcement learning frameworks often project this space into coarse, low-dimensional representations, limiting their ability to capture spatially variant deformations. We propose MorphSeek, a fine-grained representation-level policy optimization paradigm that reformulates DIR as a spatially continuous optimization process in the latent feature space. MorphSeek introduces a stochastic Gaussian policy head atop the encoder to model a distribution over latent features, facilitating efficient exploration and coarse-to-fine refinement. The framework integrates unsupervised warm-up with weakly supervised fine-tuning through Group Relative Policy Optimization, where multi-trajectory sampling stabilizes training and improves label efficiency. Across three 3D registration benchmarks (OASIS brain MRI, LiTS liver CT, and Abdomen MR-CT), MorphSeek achieves consistent Dice improvements over competitive baselines while maintaining high label efficiency with minimal parameter cost and low step-level latency overhead. Beyond optimizer specifics, MorphSeek advances a representation-level policy learning paradigm that achieves spatially coherent and data-efficient deformation optimization, offering a principled, backbone-agnostic, and optimizer-agnostic solution for scalable visual alignment in high-dimensional settings.