论文标题
用于超采样数据的渐进式采样 - 应用于定量MRI
Progressive Subsampling for Oversampled Data - Application to Quantitative MRI
论文作者
论文摘要
我们提出了Prosub：渐进式采样，这是一种基于深度学习的自动化方法，该方法是一个过采样的数据集（例如，多渠道的3D图像），信息损失最小。我们以最近的双NETWORK方法为基础，该方法赢得了MICCAI多扩散（MUDI）定量MRI测量测量取样重建挑战，但通过在艰难的决策边界进行下采样，遭受了深度学习训练的不稳定。 Prosub使用递归功能消除（RFE）的范式，并在深度学习训练期间逐步进行亚子样本测量，从而提高了优化稳定性。 Prosub还集成了神经体系结构搜索（NAS）范式，从而允许网络体系结构超参数响应子采样过程。我们表明，Prosub优于Mudi Miccai挑战的获胜者，在Mudi Challenge子任务中产生了> 18％的MSE，并且在下游过程中的定性改进对临床应用有用。我们还展示了合并NAS并分析Prosub组件的效果的好处。由于我们的方法概括了除MRI测量选择重建之外的其他问题，因此我们的代码是https://github.com/sbb-gh/prosub
We present PROSUB: PROgressive SUBsampling, a deep learning based, automated methodology that subsamples an oversampled data set (e.g. multi-channeled 3D images) with minimal loss of information. We build upon a recent dual-network approach that won the MICCAI MUlti-DIffusion (MUDI) quantitative MRI measurement sampling-reconstruction challenge, but suffers from deep learning training instability, by subsampling with a hard decision boundary. PROSUB uses the paradigm of recursive feature elimination (RFE) and progressively subsamples measurements during deep learning training, improving optimization stability. PROSUB also integrates a neural architecture search (NAS) paradigm, allowing the network architecture hyperparameters to respond to the subsampling process. We show PROSUB outperforms the winner of the MUDI MICCAI challenge, producing large improvements >18% MSE on the MUDI challenge sub-tasks and qualitative improvements on downstream processes useful for clinical applications. We also show the benefits of incorporating NAS and analyze the effect of PROSUB's components. As our method generalizes to other problems beyond MRI measurement selection-reconstruction, our code is https://github.com/sbb-gh/PROSUB
