基于检测Transformer的多壳扩散MRI纤维分辨微结构量化
Fiber-Resolved Microstructure Quantification from Multi-Shell Diffusion MRI using Detection Transformers
浏览论文内容
中文总结 AI 辅助
提出用检测Transformer从标准多壳扩散MRI中联合预测纤维方向与微结构参数，在合成数据上实现高精度，解决了传统方法需复杂编码和昂贵计算的问题。
中文摘要 AI 辅助
纤维方向和区室微结构是扩散MRI中白质组织表征的核心，然而现有方法要么在量化微结构的同时解析纤维方向，要么在假设固定数量的区室和单一纤维方向的前提下量化微结构。同时恢复两者的非参数方法需要张量值扩散编码和计算昂贵的蒙特卡洛反演，以求解病态逆拉普拉斯变换。我们提出将这一问题重新构建为类似目标检测的任务，采用检测Transformer（DETR）架构，从标准多壳扩散MRI线性编码中联合预测每个体素可变数量区室的平均扩散率（MD）、分数各向异性（FA）、主纤维方向和信号分数。训练期间的匈牙利匹配解决了区室间的排列不变性。我们引入平均精度均值作为可复现的基准指标。在每体素最多五个区室的合成测试数据上评估，我们的模型在MD上达到$R^2=0.95$，在FA上达到$R^2=0.88$，中位角度误差为4.2°，性能随区室信号分数自然扩展。
英文摘要
Fiber orientation and compartmental microstructure are central to the characterization of white matter tissue in diffusion MRI, yet existing methods either resolve fiber orientations without quantifying microstructure, or quantify microstructure while assuming a fixed number of compartments and a single fiber direction. Nonparametric approaches that recover both require tensor-valued diffusion encoding and computationally expensive Monte-Carlo inversion of an ill-posed inverse Laplace transform. We propose to reframe this problem as an object detection-like task, adopting the Detection Transformer (DETR) architecture to jointly predict mean diffusivity (MD), fractional anisotropy (FA), main fiber direction, and signal fraction for a variable number of compartments per voxel from standard multi-shell diffusion MRI with linear encoding. Hungarian matching during training resolves permutation invariance across compartments. We introduce mean Average Precision as a reproducible benchmark metric. Evaluated on synthetic test data with up to five compartments per voxel, our model achieves $R^2=0.95$ for MD, $R^2=0.88$ for FA, and a median angular error of 4.2°, with performance scaling naturally with compartmental signal fraction.
发表机构
- AImotion Bavaria, Technische Hochschule Ingolstadt（AImotion Bavaria，英戈尔施塔特应用技术大学）
- TUM School of Computation, Information and Technology, Technical University of Munich（慕尼黑工业大学计算、信息与技术学院）
- TUM School of Natural Sciences, Technical University of Munich（慕尼黑工业大学自然科学学院）
机构由 AI 辅助整理，请以论文原文为准。
