目的 当前动态对比增强 (DCE)-MRI 分析的最佳实践是采用从嵌套模型层次结构中逐体素选择模型。这种嵌套模型选择（NMS）假设体素内观察到的造影剂（CA）浓度的时间轨迹对应于单一的生理学嵌套模型。然而，不同模型的混合可能存在于体素的 CA 时间轨迹中。本研究引入了一种无监督特征工程技术（Kohonen-Self-Organizing-Map (K-SOM)）来估计每个嵌套模型的体素概率。方法 66只免疫受损RNU大鼠体内植入人U-251N癌细胞，并获取所有大鼠脑部的DCE-MRI数据。计算所有动物脑体素的纵向弛豫率（ΔR 1 ）变化的时间轨迹。使用 NMS 进行 DCE-MRI 药代动力学 (PK) 分析，以估计三个模型区域：模型 1：无渗漏的正常脉管系统；模型 2：有渗漏且无回流至脉管系统的肿瘤组织；模型 3：有渗漏的肿瘤组织。泄漏和回流。大约二十三万 (229,314) 个动物大脑体素的归一化 ΔR 1 轮廓及其 NMS 结果用于构建 K-SOM（拓扑大小：8x8，具有竞争学习算法）和每个模型的概率图。 K 折嵌套交叉验证（NCV，k = 10）用于评估 K-SOM 概率 NMS (PNMS) 技术相对于 NMS 技术的性能。结果 K-SOM PNMS 对渗漏肿瘤区域的估计非常相似（模型 2 和模型 3 的骰子相似系数，DSC = 0.774 [CI: 0.731-0.823] 和 0.866 [CI: 0.828-0.912]）到各自的 NMS 区域。两种技术估计的渗透率参数的平均百分比差异（MPD、NCV、k = 10）分别为：对于 v p 、K trans 和 ve ，分别为：-28%、 18% 和  24%。 KSOM-PNMS 技术产生的微脉管系统参数和 NMS 区域受动脉输入功能分散效应的影响较小。结论本研究引入了无监督模型平均技术 (K-SOM) 来估计不同嵌套模型在 PK 分析中的贡献，并提供了渗透率参数的更快估计。

Purpose Best current practice in the analysis of dynamic contrast enhanced (DCE)-MRI is to employ a voxel-by-voxel model selection from a hierarchy of nested models. This nested model selection (NMS) assumes that the observed time-trace of contrast-agent (CA) concentration within a voxel, corresponds to a singular physiologically nested model. However, admixtures of different models may exist within a voxel's CA time-trace. This study introduces an unsupervised feature engineering technique (Kohonen-Self-Organizing-Map (K-SOM)) to estimate the voxel-wise probability of each nested model. Methods Sixty-six immune-compromised-RNU rats were implanted with human U-251N cancer cells, and DCE-MRI data were acquired from all the rat brains. The time-trace of change in the longitudinal-relaxivity (ΔR 1 ) for all animals' brain voxels was calculated. DCE-MRI pharmacokinetic (PK) analysis was performed using NMS to estimate three model regions: Model-1: normal vasculature without leakage, Model-2: tumor tissues with leakage without back-flux to the vasculature, Model-3: tumor vessels with leakage and back-flux. Approximately two hundred thirty thousand (229,314) normalized ΔR 1 profiles of animals' brain voxels along with their NMS results were used to build a K-SOM (topology-size: 8x8, with competitive-learning algorithm) and probability map of each model. K -fold nested-cross-validation (NCV, k = 10) was used to evaluate the performance of the K-SOM probabilistic-NMS (PNMS) technique against the NMS technique. Results The K-SOM PNMS's estimation for the leaky tumor regions were strongly similar (Dice-Similarity-Coefficient, DSC = 0.774 [CI: 0.731-0.823], and 0.866 [CI: 0.828-0.912] for Models 2 and 3, respectively) to their respective NMS regions. The mean-percent-differences (MPDs, NCV, k = 10) for the estimated permeability parameters by the two techniques were: -28%, + 18%, and + 24%, for v p , K trans , and v e , respectively. The KSOM-PNMS technique produced microvasculature parameters and NMS regions less impacted by the arterial-input-function dispersion effect. Conclusion This study introduces an unsupervised model-averaging technique (K-SOM) to estimate the contribution of different nested-models in PK analysis and provides a faster estimate of permeability parameters.