使基于模型的深度学习适应多种采集条件:Ada-MoDL
Adapting model-based deep learning to multiple acquisition conditions: Ada-MoDL
AI总结:
本文提出Ada-MoDL单一展开网络,通过条件向量生成缩放权重和正则化参数以适应多种并行MRI采集条件,在保持重建质量的同时减少模型数量与各设置所需训练数据。
摘要:
目的:本工作旨在引入一个单一的基于模型的深度网络,该网络能够从在多种序列、采集设置和场强下获取的欠采样并行MRI数据中提供高质量重建。方法:引入了一种单一的展开架构,可为多种采集设置提供良好的重建。所提方案通过用适当的权重缩放CNN特征和正则化参数,使模型适应每种设置。缩放权重和正则化参数由多层感知器模型从条件向量推导得出,条件向量表示特定的采集设置。感知器参数和CNN权重使用来自多种采集设置(包括场强、加速和对比度差异)的数据联合训练。该条件网络使用在不同采集设置下获取的数据集进行验证。结果:对该自适应框架(使用来自所有设置的数据训练单一模型)的比较表明,它能够为每种采集条件提供持续改进的性能。将所提方案与针对每种采集设置独立训练的网络进行比较表明,它在每种采集设置下需要更少的训练数据即可提供良好性能。结论:Ada-MoDL框架使得能够将单一的基于模型的展开网络用于多种采集设置。除了消除针对不同采集设置训练和存储多个网络的需要外,该方法还减少了每种采集设置所需的训练数据。
英文摘要:
Purpose: The aim of this work is to introduce a single model-based deep network that can provide high-quality reconstructions from undersampled parallel MRI data acquired with multiple sequences, acquisition settings and field strengths. Methods: A single unrolled architecture, which offers good reconstructions for multiple acquisition settings, is introduced. The proposed scheme adapts the model to each setting by scaling the CNN features and the regularization parameter with appropriate weights. The scaling weights and regularization parameter are derived using a multi-layer perceptron model from conditional vectors, which represents the specific acquisition setting. The perceptron parameters and the CNN weights are jointly trained using data from multiple acquisition settings, including differences in field strengths, acceleration, and contrasts. The conditional network is validated using datasets acquired with different acquisition settings. Results: The comparison of the adaptive framework, which trains a single model using the data from all the settings, shows that it can offer consistently improved performance for each acquisition condition. The comparison of the proposed scheme with networks that are trained independently for each acquisition setting shows that it requires less training data per acquisition setting to offer good performance. Conclusion: The Ada-MoDL framework enables the use of a single model-based unrolled network for multiple acquisition settings. In addition to eliminating the need to train and store multiple networks for different acquisition settings, this approach reduces the training data needed for each acquisition setting.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。