Deep Learning Approach for Dynamic Sparse Sampling for High-Throughput Mass Spectrometry Imaging.
Deep Learning Approach for Dynamic Sparse Sampling for High-Throughput Mass Spectrometry Imaging.
复制标题
DOI：
10.2352/issn.2470-1173.2021.15.coimg-290
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Ye DH
中科院分区：
文献类型：
--
作者：
Helminiak D;Hu H;Laskin J;Ye DH
动态采样监督学习方法 (SLADS) 通过将随机过程纳入压缩感知方法来解决传统问题。从样本重建中提取的统计特征，通过回归模型估计熵减少，以便动态确定最佳采样位置。这项工作引入了一种增强的 SLADS 方法，采用动态采样深度学习方法 (DLADS) 的形式，与传统直线扫描相比，高保真重建的样本采集时间减少了约 70-80%。这些改进通过使用纳米喷雾解吸电喷雾电离 (nano-DESI) 质谱成像 (MSI) 获得的小鼠子宫和肾脏组织的尺寸不对称、高分辨率分子图像得到了证明。训练集创建方法经过调整，以减轻使用先前 SLADS 方法时生成的拉伸伪影。过渡到 DLADS 消除了特征提取的需要，并通过使用卷积层来利用像素间的空间关系进一步推进。此外，尽管训练和测试数据不同，DLADS 仍表现出有效的泛化能力。总体而言，DLADS 可以最大限度地提高 nano-DESI MSI 的潜在实验通量。
A Supervised Learning Approach for Dynamic Sampling (SLADS) addresses traditional issues with the incorporation of stochastic processes into a compressed sensing method. Statistical features, extracted from a sample reconstruction, estimate entropy reduction with regression models, in order to dynamically determine optimal sampling locations. This work introduces an enhanced SLADS method, in the form of a Deep Learning Approach for Dynamic Sampling (DLADS), showing reductions in sample acquisition times for high-fidelity reconstructions between ~ 70–80% over traditional rectilinear scanning. These improvements are demonstrated for dimensionally asymmetric, high-resolution molecular images of mouse uterine and kidney tissues, as obtained using Nanospray Desorption ElectroSpray Ionization (nano-DESI) Mass Spectrometry Imaging (MSI). The methodology for training set creation is adjusted to mitigate stretching artifacts generated when using prior SLADS approaches. Transitioning to DLADS removes the need for feature extraction, further advanced with the employment of convolutional layers to leverage inter-pixel spatial relationships. Additionally, DLADS demonstrates effective generalization, despite dissimilar training and testing data. Overall, DLADS is shown to maximize potential experimental throughput for nano-DESI MSI.