SPoD-Net: Fast Recovery of Microscopic Images Using Learned ISTA
SPoD-Net: Fast Recovery of Microscopic Images Using Learned ISTA
复制标题
DOI：
--
复制
发表时间：
2019-10
期刊：
影响因子：
--
通讯作者：
Satoshi Hara;Weichih Chen;Takashi Washio;T. Wazawa;T. Nagai
中科院分区：
文献类型：
--
作者：
Satoshi Hara;Weichih Chen;Takashi Washio;T. Wazawa;T. Nagai
从显微观察中恢复高质量图像是生物成像中的一项重要技术。现有的恢复方法需要使用迭代算法来解决优化问题，这在计算上是昂贵且耗时的。本研究的重点是通过使用深度神经网络（DNN）加速图像恢复。在我们的方法中，我们首先使用显微镜的一些观察结果来训练某种类型的 DNN，以便它能够很好地近似图像恢复过程。然后，通过训练的 DNN 中的单个前向传播来计算新观测值的恢复。在本研究中，我们特别关注通过最近开发的显微技术 SPoD（偏振解调超分辨率）获得的观测结果，并使用 DNN 加速 SPoD 的图像恢复。为此，我们提出了 SPoD-Net，这是一种专门定制的 DNN，用于快速恢复 SPoD 图像。与一般的 DNN 不同，SPoD-Net 可以使用少量参数进行参数化，这有两个好处：（i）它可以存储在较小的内存中，（ii）它可以被有效地训练。我们还提出了一种稳定 SPoD-Net 训练的方法。在真实 SPoD 观测的实验中，我们证实了 SPoD-Net 相对于现有恢复方法的有效性。具体来说，我们观察到 SPoD-Net 恢复图像的速度比现有方法快一百倍以上。
Recovering high quality images from microscopic observations is an essential technology in biological imaging. Existing recovery methods require solving an optimization problem by using iterative algorithms, which are computationally expensive and time consuming. The focus of this study is to accelerate the image recovery by using deep neural networks (DNNs). In our approach, we first train a certain type of DNN by using some observations from microscopes, so that it can well approximate the image recovery process. The recovery of a new observation is then computed thorough a single forward propagation in the trained DNN. In this study, we specifically focus on observations obtained by SPoD (Super-resolution by Polarization Demodulation), a recently developed microscopic technique, and accelerate the image recovery for SPoD by using DNNs. To this end, we propose SPoD-Net, a specifically tailored DNN for fast recovery of SPoD images. Unlike general DNNs, SPoD-Net can be parameterized using a small number of parameters, which is helpful in two ways: (i) it can be stored in a small memory, and (ii) it can be trained efficiently. We also propose a method to stabilize the training of SPoD-Net. In the experiments with the real SPoD observations, we confirmed the effectiveness of SPoD-Net over existing recovery methods. Specifically, we observed that SPoD-Net could recover images with more than a hundred times faster than the existing method.