Diffusion-weighted magnetic resonance imaging (D-MRI) is an in-vivo and non-invasive imaging technology to probe anatomical architectures of biological samples. The anatomy of white matter fiber tracts in the brain can be revealed to help understanding of the connectivity patterns among different brain regions. In this paper, we propose a novel Nearest-neighbor Adaptive Regression Model (NARM) for adaptive estimation of the fiber orientation distribution (FOD) function based on D-MRI data, where spatial homogeneity is used to improve FOD estimation by incorporating neighborhood information. Specifically, we formulate the FOD estimation problem as a weighted linear regression problem, where the weights are chosen to account for spatial proximity and potential heterogeneity due to different fiber configurations. The weights are adaptively updated and a stopping rule based on nearest neighbor distance is designed to prevent over-smoothing. NARM is further extended to accommodate D-MRI data with multiple bvalues. Comprehensive simulation results demonstrate that NARM leads to satisfactory FOD reconstructions and performs better than voxel-wise estimation as well as competing smoothing methods. By applying NARM to real 3T D-MRI datasets, we demonstrate the effectiveness of NARM in recovering more realistic crossing fiber patterns and producing more coherent fiber tracking results, establishing the practical value of NARM for analyzing D-MRI data and providing reliable information on brain structural connectivity. * Jilei Yang and Seungyong Hwang are co-first authors

翻译：扩散加权磁共振成像（D-MRI）是一种用于探测生物样本解剖结构的活体无创成像技术。它可以揭示大脑白质纤维束的解剖结构，有助于理解不同脑区之间的连接模式。本文提出一种新颖的近邻自适应回归模型（NARM），用于基于D-MRI数据自适应估计纤维取向分布（FOD）函数，其中利用空间同质性通过纳入邻域信息来改进FOD估计。具体而言，我们将FOD估计问题建模为加权线性回归问题，其中权重选择用于考虑空间邻近性以及因不同纤维构型导致的潜在异质性。自适应更新权重，并基于近邻距离设计停止规则以防止过度平滑。NARM进一步扩展以支持具有多个b值的D-MRI数据。综合仿真结果表明，NARM能够实现令人满意的FOD重构，且性能优于体素级估计及其他竞争性平滑方法。通过将NARM应用于真实3T D-MRI数据集，我们证明了NARM在恢复更真实的交叉纤维模式及生成更连贯的纤维追踪结果方面的有效性，确立了NARM在分析D-MRI数据、提供脑结构连接可靠信息方面的实用价值。* Jilei Yang与Seungyong Hwang为共同第一作者