Using machine-learning to optimize phase contrast in a low-cost cellphone microscope.
Using machine-learning to optimize phase contrast in a low-cost cellphone microscope.
复制标题
DOI：
10.1371/journal.pone.0192937
复制
发表时间：
2018
期刊：
影响因子：
3.7
通讯作者：
Heintzmann R
中科院分区：
文献类型：
--
作者：
Diederich B;Wartmann R;Schadwinkel H;Heintzmann R
配备高质量摄像头和强大CPU以及GPU的手机非常普遍。这为利用现有的计算和成像资源在发展中国家以非常低的成本进行医疗诊断开辟了新的前景。许多相关的样本，如生物细胞或水生寄生虫，几乎是完全透明的。因为它们不会表现出吸收，而只是改变光的相位，所以它们在明亮的显微镜下几乎是看不见的。用于显微镜对比或样本染色的昂贵设备和程序通常是不可用的。专门的照明方法，为研究中的样品量身定做，有助于提高对比度。这是通过可编程光源实现的，它还允许使用差分相位对比度(DPC)测量相位梯度，甚至使用导出的qDPC方法测量定量相位。通过应用机器学习技术，例如卷积神经网络(CNN)，可以学习要检查的样本与其最佳光源形状之间的关系，以便从给定数据集中增加例如相位对比度，从而实现实时应用。在实验装置中，我们开发了一款3D打印智能手机显微镜，价格不到100美元，只使用现成的组件，如低成本的视频投影仪。全自动系统使用LCD作为聚光器光圈，反转智能手机镜头作为显微镜物镜，确保了真正的克勒照明。我们发现，使用预先训练的CNN，改变光源形状的效果不仅改善了相位对比度，而且在不增加任何特殊光学元件的情况下，改善了光学分辨率的印象，正如测量所证明的那样。
Cellphones equipped with high-quality cameras and powerful CPUs as well as GPUs are widespread. This opens new prospects to use such existing computational and imaging resources to perform medical diagnosis in developing countries at a very low cost. Many relevant samples, like biological cells or waterborn parasites, are almost fully transparent. As they do not exhibit absorption, but alter the light’s phase only, they are almost invisible in brightfield microscopy. Expensive equipment and procedures for microscopic contrasting or sample staining often are not available. Dedicated illumination approaches, tailored to the sample under investigation help to boost the contrast. This is achieved by a programmable illumination source, which also allows to measure the phase gradient using the differential phase contrast (DPC) or even the quantitative phase using the derived qDPC approach. By applying machine-learning techniques, such as a convolutional neural network (CNN), it is possible to learn a relationship between samples to be examined and its optimal light source shapes, in order to increase e.g. phase contrast, from a given dataset to enable real-time applications. For the experimental setup, we developed a 3D-printed smartphone microscope for less than 100 $ using off-the-shelf components only such as a low-cost video projector. The fully automated system assures true Koehler illumination with an LCD as the condenser aperture and a reversed smartphone lens as the microscope objective. We show that the effect of a varied light source shape, using the pre-trained CNN, does not only improve the phase contrast, but also the impression of an improvement in optical resolution without adding any special optics, as demonstrated by measurements.
登录
查看更多内容
DOI：
10.1117/1.1794708
发表时间：
2004-10-01
期刊：
JOURNAL OF MICROLITHOGRAPHY MICROFABRICATION AND MICROSYSTEMS
影响因子：
--
作者：
Granik, Y
通讯作者：
Granik, Y
影响因子：
3.7
作者：
Greenbaum A;Akbari N;Feizi A;Luo W;Ozcan A
通讯作者：
Ozcan A
DOI：
10.1098/rspa.1953.0071
发表时间：
1953-01-01
影响因子：
--
作者：
HOPKINS, HH
通讯作者：
HOPKINS, HH
对计算生物学的深度学习。
影响因子：
9.9
作者：
Angermueller C;Pärnamaa T;Parts L;Stegle O
通讯作者：
Stegle O
基于手机的临床显微镜用于全球健康应用。
影响因子：
3.7
作者：
Breslauer, David N.;Maamari, Robi N.;Switz, Neil A.;Lam, Wilbur A.;Fletcher, Daniel A.
通讯作者：
Fletcher, Daniel A.