发表机构
Southern University of Science and Technology; Shenzhen University of Advanced Technology; Shenzhen University Medical School; Shenzhen University; Research Institute of Trustworthy Autonomous Systems（南方科技大学; 深圳先进技术研究院; 深圳大学医学院; 深圳大学; 可信自主系统研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出低秩速度场作为结构先验，结合多尺度方案实现无监督4D医学图像插值，在ACDC和4D-Lung数据集上达到最优性能，生成的中间体积结构一致性与轮廓稳定性更优。
AI 中文摘要
仅端点式无监督四维医学图像插值从稀疏采样序列合成中间体积，训练时仅使用起始和结束体积；然而这种弱约束设置常生成边界不稳定、非生理运动的中间体积，限制了可解释性和下游分析。我们提出低秩速度场作为结构先验，将运动约束在结构化Tucker低秩速度场空间中，该空间将运动分解为全局共享空间基和紧凑的样本特定核心，从而鼓励空间相关、解剖结构一致的变形，同时抑制体素级高频伪影。为捕捉全局协调和局部非刚性细节，我们采用由粗到精的多尺度方案对运动建模，并在推理时组合各尺度变形以合成任意时刻的体积。我们进一步提供理论分析，表明在Tucker参数化下，低秩参数控制速度场的平滑度能量，解释了低秩建模为何能促进更平滑的运动。在ACDC和4D-Lung数据集上的实验表明，该方法达到了最先进的性能，与使用中间帧监督训练的方法相比仍具竞争力，且生成的中间体积具有更好的结构一致性和更稳定的解剖轮廓。
英文摘要
Endpoint-only unsupervised 4D medical image interpolation synthesizes intermediate volumes from sparsely sampled sequences with only the start and end volumes available for training; however, this weakly constrained setting often yields intermediates with unstable boundaries and non-physiological motion, limiting interpretability and downstream analysis. We propose low-rank velocity fields as a structural prior, constraining motion to a structured Tucker low-rank velocity field space that decomposes motion into globally shared spatial bases and a compact sample-specific core, thereby encouraging spatially correlated, anatomy-consistent deformation while suppressing voxel-wise high-frequency artifacts. To capture global coordination and local non-rigid details, we model motion in a coarse-to-fine multi-scale scheme and compose scale-wise deformations at inference to synthesize volumes at arbitrary times. We further provide a theoretical analysis showing that, under Tucker parameterization, low-rank parameters control the smoothness energy of the velocity field, explaining why low-rank modeling promotes smoother motion. Experiments on ACDC and 4D-Lung demonstrate state-of-the-art performance, remaining competitive with methods trained with intermediate-frame supervision, and producing intermediates with improved structural coherence and more stable anatomical contours.
CommentsMICCAI 2026
