PRISM通过可微分析-合成方法，提升扩散MRI中纤维束的精准恢复。
PRISM: Differentiable Analysis-by-Synthesis for Fixel Recovery in Diffusion MRI
- 基于可微分框架端到端拟合多组分模型，结合方向与稀疏性先验。
- 在信噪比30的模拟数据中，角度误差低至2.3度，交叉角最小可分辨20度。
- 适合需要高精度纤维追踪的脑连接研究，尤其适用于复杂交叉区域。
扩散MRI微观结构拟合是非凸问题，通常逐体素进行，限制了狭窄交叉处的纤维峰恢复。本文提出PRISM，一种可微分的分析-合成框架，在空间块上端到端拟合显式多组分前向模型。该模型包含脑脊液（CSF）、灰质、最多K个白质纤维组分（stick-and-zeppelin）及受限组分，显式建模纤维方向，并通过排斥与稀疏性先验实现软模型选择。PRISM支持快速均方误差（MSE）目标和瑞利负对数似然（NLL），可联合学习噪声标准差σ而无需先验信息。引入轻量级干扰校准模块（平滑偏置场及每测量尺度/偏移），增强鲁棒性并在干净数据测试中正则化为恒等变换。在合成交叉纤维数据（SNR=30；五种方法，16种交叉角）中，PRISM达到3.5度最佳匹配角度误差，召回率95%，优于最佳基线MSMT-CSD（6.8度，83%召回率）1.9倍；在NLL模式下σ由模型学习时，误差降至2.3度，召回率达99%，可分辨低至20度的交叉。在DiSCo1幻影数据中（NLL模式），所有四类追踪角度下连接相关性均优于CSD基线（最佳r=0.934，25度时，优于MSMT-CSD的0.920）。全脑HCP拟合（约741k体素，MSE模式）在单张GPU上仅需约12分钟，且不同随机种子结果几乎一致。
原文摘要 · Abstract (English)
Diffusion MRI microstructure fitting is nonconvex and often performed voxelwise, which limits fiber peak recovery in narrow crossings. This work introduces PRISM, a differentiable analysis-by-synthesis framework that fits an explicit multi-compartment forward model end-to-end over spatial patches. The model combines cerebrospinal fluid (CSF), gray matter, up to K white-matter fiber compartments (stick-and-zeppelin), and a restricted compartment, with explicit fiber directions and soft model selection via repulsion and sparsity priors. PRISM supports a fast MSE objective and a Rician negative log-likelihood (NLL) that jointly learns sigma without oracle information. A lightweight nuisance calibration module (smooth bias field and per-measurement scale/offset) is included for robustness and regularized to identity in clean-data tests. On synthetic crossing-fiber data (SNR=30; five methods, 16 crossing angles), PRISM achieves 3.5 degrees best-match angular error with 95% recall, which is 1.9x lower than the best baseline (MSMT-CSD, 6.8 degrees, 83% recall); in NLL mode with learned sigma, error drops to 2.3 degrees with 99% recall, resolving crossings down to 20 degrees. On the DiSCo1 phantom (NLL mode), PRISM improves connectivity correlation over CSD baselines at all four tracking angles (best r=.934 at 25 degrees vs. .920 for MSMT-CSD). Whole-brain HCP fitting (~741k voxels, MSE mode) completes in ~12 min on a single GPU with near-identical results across random seeds.
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。