发表机构
Peking University; Weihai Institute of Oceanology, Peking University; Beijing MagnVue Medix Co., Ltd.（北京大学; 北京大学威海海洋研究院; 北京迈格威医疗科技有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出AGW-PBR方法，通过组织混合熵加权优化脑部MRI超分辨率，提升了IXI数据集的重建效果，无PVE监督的骨干网络在fastMRI上也表现出色。
AI 中文摘要
脑部磁共振成像（MRI）超分辨率（SR）的全图像目标函数会低估受部分容积效应（PVE）影响的组织过渡区域的权重，因为这些区域仅占图像的一小部分，且二元边界也无法捕捉体素内脑脊液、灰质和白质的连续混合状态。我们提出了解剖学引导的高斯参数变形与PVE平衡重建（AGW-PBR），它将仅含低分辨率（LR）的重建骨干网络与训练时强调组织过渡的目标函数相结合。该骨干网络整合了源自低分辨率的Sobel引导、软潜基分配以及有界网格锚定残差变形。从配准后的T1/T2/PD IXI图像中获取的固定、质量受控的组织分数被转换为组织混合熵，该熵在经验证的PVE支持范围内定义了均值归一化的重建权重。这些辅助数据仅在训练期间使用，推理仅需低分辨率图像。AGW-PBR在IXI数据集的T2加权图像上以2倍、4倍和6倍放大率进行评估，采用三个随机种子和受试者级配对分析；在4倍放大时，仅测试的SynthSeg掩码独立评估组织界面和非界面区域的重建效果，针对性消融实验则检验了有效支持监督、空间对齐的熵加权以及软潜基分配的效果。AGW骨干网络还在fastMRI数据集上以4倍放大率从头训练，未使用PVE监督。AGW-PBR在测试的IXI尺度上提升了全图像重建效果，并在4倍放大时提升了区域保真度，而无PVE监督的骨干网络在fastMRI上仍保持出色性能，这些发现支持将组织混合熵加权用于部分容积感知的脑部MRI超分辨率。
英文摘要
Background and Objectives: Full-image objectives in brain magnetic resonance imaging (MRI) super-resolution (SR) can underweight tissue-transition regions affected by the partial-volume effect (PVE), as these regions occupy a small fraction of the image. Binary boundaries further provide only a discrete approximation of continuous tissue mixtures within a voxel. Methods: We propose Anatomy-Guided Gaussian-Parameter Warping with PVE-Balanced Reconstruction (AGW-PBR), combining a low-resolution (LR)-only reconstruction backbone with a PVE-aware training objective. The backbone uses LR-derived anatomical guidance, soft latent assignment, and bounded residual warping. Quality-controlled tissue fractions are converted into tissue-mixture entropy to spatially weight reconstruction within validated PVE support. PVE sidecars are used only during training, while inference requires only the LR image. Downstream utility is further evaluated through zero-shot transfer to whole-tumor segmentation on BraTS2023. Results: AGW-PBR improves reconstruction across 2x and 4x SR on IXI and achieves the lowest normalized gradient-vector reconstruction error at both CSF--GM and GM--WM interfaces at 4x. Ablation studies verify the contributions of PVE-aware weighting and soft latent assignment. The PVE-free AGW backbone also maintains strong performance on fastMRI. On BraTS2023, AGW-PBR achieves competitive whole-tumor Dice and the lowest HD95 under direct zero-shot transfer. Conclusions:AGW-PBR improves brain MRI SR while preserving tissue-transition information relevant to downstream analysis. The results support tissue-mixture entropy as an effective supervision signal for partial-volume-aware MRI reconstruction.
Comments17 pages, 6 figures, 8 tables
