数据采集方案对神经扩散模型影响的评估

周敏雄,张会婷,王一达,杨光,姚旭峰,高安康,程敬亮,白洁,严序

Evaluation of the Influence of Data Sampling Schemes on Neural Diffusion Models

Min-xiong ZHOU,Hui-ting ZHANG,Yi-da WANG,Guang YANG,Xu-feng YAO,An-kang GAO,Jing-liang CHENG,Jie BAI,Xu YAN

图1 基于ROI均值，评估不同采集方案对多种扩散模型定量参数计算结果的影响.采集方案包括QGrid、Free和MDDW，扩散模型包括DTI、DKI、MAP和NODDI，ROI均值比较分别在灰质和白质进行（由于参数值值域不同，参数值通过数量级调整同时显示）

Fig.1 Based on the mean values in ROIs, the influence of different sampling schemes on the quantitative parameters of various diffusion models was compared. The sampling schemes included QGrid, Free and MDDW. The diffusion models included DTI, DKI, NODDI and MAP. ROIs were selected in gray matter and white matter regions respectively (Each parameter is in different value range, thus a rescale is applied to display them together)