01
![]()
Holographic deep learning for rapid
optical screening of anthrax spore
基于深度学习用于快速光学筛选炭疽孢子的全息技术
( YoungJu Jo, Sangjin Park, JaeHwang Jung, Jonghee Yoon,
Hosung Joo, Min-hyeok Kim, Suk-Jo Kang, Myung Chul Choi, Sang Yup Lee, and YongKeun Park )
http://advances.sciencemag.org/content/3/8/e1700606?from=singlemessage&isappinstalled=0
（ 导读 杨璐 ）
建立炭疽攻击预警系统对生物防御至关重要。尽管数十年来对此进行了大量研究，传统的生物化学方法的灵敏度仍然不够并且需要一系列的预处理步骤，因此要在在实际生化战争装备中使用依然有很多限制。我们提出了一种光学方法，通过全息显微镜和深度学习的结合，对炭疽芽孢杆菌孢子进行快速无标记筛选。我们设计了一种深度卷积神经网络，用来对未标记的活细胞的全息图像进行分类。经过训练后，网络在所有准确性测试中均优于以前的技术，区分精度达到了单孢子水平和亚属性特征。深度学习独特的“表现学习”能力使我们可以直接利用原始图像进行训练，不必再手动提取特征。该方法能够自动识别隐藏在图像中关键生物学特征并将其当作指纹。这种显著的学习能力使得本文提出的方法能够容易实现除炭疽芽孢杆菌之外的各种单细胞的分类，同时不对细胞做任何处理，就像对单核细胞增生李斯特单核细胞增生的诊断过程一样。我们相信，我们的方法将使数字全息显微镜在生物医学科学家中更加普及，从而轻松，快速，准确地对病原体进行诊断。
Abstract
Establishing
early warning systems for anthrax attacks is crucial in biodefense. Despite
numerous studies for decades, the limited sensitivity of conventional
biochemical methods essentially requires preprocessing steps and thus has
limitations to be used in realistic settings of biological warfare. We present
an optical method for rapid and label-free screening of Bacillus anthracis
spores through the synergistic application of holographic microscopy and deep learning.
A deep convolutional neural network is designed to classify holographic images
of unlabeled living cells. After training, the network outperforms previous
techniques in all accuracy measures, achieving single-spore sensitivity and
subgenus specificity. The unique “representation learning” capability of deep
learning enables direct training from raw images instead of manually extracted
features. The method automatically recognizes key biological traits encoded in
the images and exploits them as fingerprints. This remarkable learning ability
makes the proposed method readily applicable to classifying various single
cells in addition to B. anthracis, as demonstrated for the diagnosis of
Listeria monocytogenes, without any modification. We believe that our strategy
will make holographic microscopy more accessible to medical doctors and
biomedical scientists for easy, rapid, and accurate point-of-care diagnosis of
pathogens.
![]()
（图片来源：http://advances.sciencemag.org/）
![]()
（图片来源：http://advances.sciencemag.org/）
02
< Biomedical Optics Express >
![]()
Speckle
variance OCT for depth resolved assessment of the viability of bovine embryos
基于动态散斑光学相干层析的空间分辨的牛胚胎发育状况评估方法
( S. Caujolle, R. Cernat, G.
Silvestri, et al )
https://www.osapublishing.org/boe/abstract.cfm?uri=boe-8-11-5139
（ 导读 车蕾平 ）
试管内受精产生的胚胎的发育状况能够通过它的形态进行判断。然而，通过标准显微镜的成像是主观的，并且标准显微镜在胚胎被成长后无法从细胞尺度上评价胚胎的发育状况。光学相干层析成像技术能够得到被测样本空间分辨的轮廓，与动态散斑方法结合可以探测微米量级的运动。在本文的研究中，以在试管中培养7天的牛胚胎作为活体生物样本，开展两组试验，一组实验观察时间是10分钟，另外一组实验观察时间超过18小时，通过光学相干层析获得空间分辨的样本轮廓，再结合动态散斑测量和样品活性相关的微米量级的运动。计算任一给定时间的纵向剖面图像的百分比，能够显示运动状态，作为探测胚胎发育状态的方法。这个方法能够快速无损地测量胚胎损伤程度，例如，在低温贮藏后胚胎的损伤程度。
Abstract
The morphology of
embryos produced by in vitro fertilization (IVF) is commonly used
to estimate their viability. However, imaging by standard microscopy is
subjective and unable to assess the embryo on a cellular scale after compaction.
Optical coherence tomography is an imaging technique that can produce a
depth-resolved profile of a sample and can be coupled with speckle variance
(SV) to detect motion on a micron scale. In this study, day 7 post-IVF bovine
embryos were observed either short-term (10 minutes) or long-term (over 18
hours) and analyzed by swept source OCT and SV to resolve their depth profile and
characterize micron-scale movements potentially associated with viability. The percentage
of en face images showing
movement at any given time was calculated as a method to detect the vital
status of the embryo. This method could be used to measure the levels of damage
sustained by an embryo, for example after cryopreservation, in a rapid and non-invasive
way.
![]()
（图片来源：https://www.osapublishing.org/）
03
![]()
Single-shotdual-mode water-immersion microscopy platform for biological applications
用于生物领域的单次曝光双模式水浸式全息显微成像系统
( JOSÉ ÁNGEL PICAZO-BUENO, DAN COJOC, FEDERICO ISEPPON, VINCENT TORRE, VICENTE MICÓ )
（ 导读 汪其香 ）
本文介绍了一种采用宽带（白光）照明的单次曝光水浸数字全息显微镜。这种双成像平台通过对样品进行相位全息成像可实现传统的非相干观测，。全息结构是在图像空间（即通过显微镜透镜）之后实现的，与常规干涉仪相比，减小了系统对振动和/或热变化的敏感性。由于离轴全息记录的原则，在没有任何可移动结构的条件下进行整个视场单次成像获取活的生物样品定量相位图。水浸式成像透镜的使用最大限度地提高了分辨率。这种双模式显微镜平台第一次用微球进行标定，然后应用到固定细胞的特性（神经母细胞瘤、乳腺癌和海马神经元细胞），最后用于观测动态活细胞（神经元）。
Abstract
A single-shot water-immersion digital holographic microscope combined with
broadband (white light) illumination mode is presented. This double imaging
platform allows conventional incoherent visualization with phase holographic
imaging of inspected samples. The holographic architecture is implementedat the image space (that is, after passing the microscope lens) thus reducing
the sensitivity of the system to vibrations and/or thermal changes in
comparison to regular interferometers. Because of the off-axis holographic
recording principle, quantitative phase images of live biosamples can be
recorded in a single camera snapshot at full-field geometry without any moving
parts. And the use of water immersion imaging lenses maximizes the achievable
resolution limit. This dual mode microscope platform is first calibrated using
microbeads, then applied to the characterization of fixed cells (neuroblastoma,
breast cancer and hippocampal neuronal cells) and finally validated for
visualization of dynamic living cells (hippocampal neurons).
![]()
![]()
（图片来源：https://www.osapublishing.org/）
04
< Biomedical Optics Express >
![]()
Improving lateral resolution and image qualityof optical coherence tomography by the multi-frame superresolution techniquefor 3D tissue imaging
针对三维组织成像，利用多帧超分辨率技术提高光学相干层析的横向分辨率和图像质量
( Kai Shen, Hui Lu, Sarfaraz Baig, and Michael R. Wang)
https://www.osapublishing.org/boe/abstract.cfm?uri=boe-8-11-4887
（ 导读 李颖 ）
本文引入多帧超分辨率技术，显著提高了频谱域光学相干层析技术（SD-OCT）的横向分辨率和图像质量。利用多组低分辨率C扫描三维图像，不同组具有横向的子点间距偏移，对图像的每个深度层进行多帧超分辨率处理，重构出具有更高分辨率的、高质量的横向图像。该方法进行逐层处理，得到总体具有高横向分辨率的高质量的三维图像。反卷积超分辨率处理可以同时解决衍射极限，横向扫描密度和背景噪声问题。本文通过对已知分辨率的测试目标进行成像，已经证实：通过使用0.015和0.05数值孔径的样本臂光学器件，横向分辨率提高了约3倍，分别达到了7.81μm和2.19μm，图像质量提高约两倍。而且该方法也可改进体外皮肤C扫描图像的横向分辨率。对于人体皮肤，指纹和视网膜层的体内三维SD-OCT成像，使用多模态体积配准方法来有效地估计由随机的轻微运动而导致的不同C扫描之间的横向图像偏移。这些图像的进一步处理得到高横向分辨率三维图像以及这些体内组织的高质量B扫描图像。
Abstract
The multi-frame
superresolution technique is introduced to significantly improve the lateral
resolution and image quality of spectral domain optical coherence tomography
(SD-OCT). Using several sets of low resolution C-scan 3D images with lateral
sub-spot-spacing shifts on different sets, the multi-frame superresolution
processing of these sets at each depth layer reconstructs a higher resolution
and quality lateral image. Layer by layer processing yields an overall high
lateral resolution and quality 3D image. In theory, the superresolution
processing including deconvolution can solve the diffraction limit, lateral
scan density and background noise problems together. In experiment, the
improved lateral resolution by ~3 times reaching 7.81 µm and 2.19 µm using sample arm optics of 0.015 and 0.05 numerical aperture
respectively as well as doubling the image quality has been confirmed by
imaging a known resolution test target. Improved lateral resolution on in vivo skin C-scan images has been
demonstrated. For in vivo 3D
SD-OCT imaging of human skin, fingerprint and retina layer, we used the multi-modal volume
registration method to effectively estimate the lateral image shifts among different C-scans due to random minor
unintended live body motion. Further processing of these images generated high
lateral resolution 3D images as well as high quality B-scan images of these in vivo tissues.
![]()
（图片来源：https://www.osapublishing.org/）
（编辑 曹闰禹）
