Optical microscopy has become an indispensable tool for visualizing sub-cellular structures andbiological processes.However,scattering in biological tissues is a major obstacle that preventshigh-resolution images from...Optical microscopy has become an indispensable tool for visualizing sub-cellular structures andbiological processes.However,scattering in biological tissues is a major obstacle that preventshigh-resolution images from being obtained from deep regions of tissue.We review commontechniques,such as multiphoton microscopy(MPM)and optical coherence microscopy(OCM),for diffraction limited imaging beyond an imaging depth of 0.5 mm.Novel implementations havebeen emerging in recent years giving higher imaging speed,deeper penetration,and better imagequality.Focal modulation microscopy(FMM)is a novel method that combines confocal spatialfltering with focal modulation to reject out-of-focus background.FMM has demonstrated animaging depth comparable to those of MPM and OCM,near-real-time image acquisition,and thecapability for multiple contrast mechanisms.展开更多
In the wake of the rapid surge in the COVID-19-infected cases seen in Southern and West-Central USA in the period of June-July 2020,there is an urgent need to develop robust,data-driven models to quantify the effect w...In the wake of the rapid surge in the COVID-19-infected cases seen in Southern and West-Central USA in the period of June-July 2020,there is an urgent need to develop robust,data-driven models to quantify the effect which early reopening had on the infected case count increase.In particular,it is imperative to address the question:How many infected cases could have been prevented,had the worst affected states not reopened early?To address this question,we have developed a novel COVID-19 model by augmenting the classical SIR epidemiological model with a neural network module.The model decomposes the contribution of quarantine strength to the infection time series,allowing us to quantify the role of quarantine control and the associated reopening policies in the US states which showed a major surge in infections.We show that the upsurge in the infected cases seen in these states is strongly corelated with a drop in the quarantine/lockdown strength diagnosed by our model.Further,our results demonstrate that in the event of a stricter lockdown without early reopening,the number of active infected cases recorded on 14 July could have been reduced by more than 40%in all states considered,with the actual number of infections reduced being more than 100,000 for the states of Florida and Texas.As we continue our fight against COVID-19,our proposed model can be used as a valuable asset to simulate the effect of several reopening strategies on the infected count evolution,for any region under consideration.展开更多
Noninvasive X-ray imaging of nanoscale three-dimensional objects,such as integrated circuits(ICs),generally requires two types of scanning:ptychographic,which is translational and returns estimates of the complex elec...Noninvasive X-ray imaging of nanoscale three-dimensional objects,such as integrated circuits(ICs),generally requires two types of scanning:ptychographic,which is translational and returns estimates of the complex electromagnetic field through the IC;combined with a tomographic scan,which collects these complex field projections from multiple angles.Here,we present Attentional Ptycho-Tomography(APT),an approach to drastically reduce the amount of angular scanning,and thus the total acquisition time.APT is machine learning-based,utilizing axial self-Attention for Ptycho-Tomographic reconstruction.APT is trained to obtain accurate reconstructions of the ICs,despite the incompleteness of the measurements.The training process includes regularizing priors in the form of typical patterns found in IC interiors,and the physics of X-ray propagation through the IC.We show that APT with×12 reduced angles achieves fidelity comparable to the gold standard Simultaneous Algebraic Reconstruction Technique(SART)with the original set of angles.When using the same set of reduced angles,then APT also outperforms Filtered Back Projection(FBP),Simultaneous Iterative Reconstruction Technique(SIRT)and SART.The time needed to compute the reconstruction is also reduced,because the trained neural network is a forward operation,unlike the iterative nature of these alternatives.Our experiments show that,without loss in quality,for a 4.48×93.2×3.92µm^(3) IC(≃6×10^(8) voxels),APT reduces the total data acquisition and computation time from 67.96 h to 38 min.We expect our physics-assisted and attention-utilizing machine learning framework to be applicable to other branches of nanoscale imaging,including materials science and biological imaging.展开更多
The existing knowledge on the electrodynamics of invisibility cloaking based on transformation optics is reviewed from an integrated science and engineering perspective.Several significant electromagnetic problems tha...The existing knowledge on the electrodynamics of invisibility cloaking based on transformation optics is reviewed from an integrated science and engineering perspective.Several significant electromagnetic problems that have resulted in intense discussions in the past few years are summarized in terms of propagation,scattering,radiation and fabrication.Finally,the road ahead toward invisibility cloaking and transformation optics is discussed from the viewpoint of the author.展开更多
The quality of inverse problem solutions obtained through deep learning is limited by the nature of the priors learned from examples presented during the training phase.Particularly in the case of quantitative phase r...The quality of inverse problem solutions obtained through deep learning is limited by the nature of the priors learned from examples presented during the training phase.Particularly in the case of quantitative phase retrieval,spatial frequencies that are underrepresented in the training database,most often at the high band,tend to be suppressed in the reconstruction.Ad hoc solutions have been proposed,such as pre-amplifying the high spatial frequencies in the examples;however,while that strategy improves the resolution,it also leads to high-frequency artefacts,as well as low-frequency distortions in the reconstructions.Here,we present a new approach that learns separately how to handle the two frequency bands,low and high,and learns how to synthesize these two bands into full-band reconstructions.We show that this“learning to synthesize”(LS)method yields phase reconstructions of high spatial resolution and without artefacts and that it is resilient to high-noise conditions,e.g.,in the case of very low photon flux.In addition to the problem of quantitative phase retrieval,the LS method is applicable,in principle,to any inverse problem where the forward operator treats different frequency bands unevenly,i.e.,is ill-posed.展开更多
Limited-angle tomography of an interior volume is a challenging, highly ill-posed problem with practical implications in medical and biological imaging, manufacturing, automation, and environmental and food security. ...Limited-angle tomography of an interior volume is a challenging, highly ill-posed problem with practical implications in medical and biological imaging, manufacturing, automation, and environmental and food security. Regularizing priors are necessary to reduce artifacts by improving the condition of such problems. Recently, it was shown that one effective way to learn the priors for strongly scattering yet highly structured 3D objects, e.g. layered and Manhattan, is by a static neural network [Goy et al. Proc. Natl. Acad. Sci. 116, 19848–19856 (2019)]. Here, we present a radically different approach where the collection of raw images from multiple angles is viewed analogously to a dynamical system driven by the object-dependent forward scattering operator. The sequence index in the angle of illumination plays the role of discrete time in the dynamical system analogy. Thus, the imaging problem turns into a problem of nonlinear system identification, which also suggests dynamical learning as a better fit to regularize the reconstructions. We devised a Recurrent Neural Network (RNN) architecture with a novel Separable-Convolution Gated Recurrent Unit (SC-GRU) as the fundamental building block. Through a comprehensive comparison of several quantitative metrics, we show that the dynamic method is suitable for a generic interior-volumetric reconstruction under a limited-angle scheme. We show that this approach accurately reconstructs volume interiors under two conditions: weak scattering, when the Radon transform approximation is applicable and the forward operator well defined;and strong scattering, which is nonlinear with respect to the 3D refractive index distribution and includes uncertainty in the forward operator.展开更多
文摘Optical microscopy has become an indispensable tool for visualizing sub-cellular structures andbiological processes.However,scattering in biological tissues is a major obstacle that preventshigh-resolution images from being obtained from deep regions of tissue.We review commontechniques,such as multiphoton microscopy(MPM)and optical coherence microscopy(OCM),for diffraction limited imaging beyond an imaging depth of 0.5 mm.Novel implementations havebeen emerging in recent years giving higher imaging speed,deeper penetration,and better imagequality.Focal modulation microscopy(FMM)is a novel method that combines confocal spatialfltering with focal modulation to reject out-of-focus background.FMM has demonstrated animaging depth comparable to those of MPM and OCM,near-real-time image acquisition,and thecapability for multiple contrast mechanisms.
基金This effort was partially funded by the Intelligence Advanced Research Projects Activity(IARPA).We are grateful to Haluk Akay,Hyungseok Kim,and Wujie Wang for helpful discussions and suggestions.
文摘In the wake of the rapid surge in the COVID-19-infected cases seen in Southern and West-Central USA in the period of June-July 2020,there is an urgent need to develop robust,data-driven models to quantify the effect which early reopening had on the infected case count increase.In particular,it is imperative to address the question:How many infected cases could have been prevented,had the worst affected states not reopened early?To address this question,we have developed a novel COVID-19 model by augmenting the classical SIR epidemiological model with a neural network module.The model decomposes the contribution of quarantine strength to the infection time series,allowing us to quantify the role of quarantine control and the associated reopening policies in the US states which showed a major surge in infections.We show that the upsurge in the infected cases seen in these states is strongly corelated with a drop in the quarantine/lockdown strength diagnosed by our model.Further,our results demonstrate that in the event of a stricter lockdown without early reopening,the number of active infected cases recorded on 14 July could have been reduced by more than 40%in all states considered,with the actual number of infections reduced being more than 100,000 for the states of Florida and Texas.As we continue our fight against COVID-19,our proposed model can be used as a valuable asset to simulate the effect of several reopening strategies on the infected count evolution,for any region under consideration.
基金We are grateful to Jung Ki Song,Mo Deng,Baoliang Ge,William Harrod,Ed Cole,Zachary Levine,Bradley Alpert,Nina Weisse-Bernstein,Lee Oesterling,and Antonio Orozco for helpful discussions and comments.Funding from the Intelligence Advanced Research Projects Activity,Office of the Director of National Intelligence(IARPA-ODNI),contract FA8650-17-C-9113 is gratefully acknowledged.The MIT SuperCloud and Lincoln Laboratory Supercomputing Center provided resources(high performance computing,database,consultation)that have contributed to the research results reported within this paperI.Kang acknowledges support from Korea Foundation for Advanced Studies(KFAS).This research used resources of the Advanced Photon Source,a U.S.Department of Energy(DOE)Office of Science User Facility,operated for the DOE Office of Science by Argonne National Laboratory under Contract No.DE-AC02-06CH11357.The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements,either expressed or implied,of the ODNI,IARPA,or the US Government.
文摘Noninvasive X-ray imaging of nanoscale three-dimensional objects,such as integrated circuits(ICs),generally requires two types of scanning:ptychographic,which is translational and returns estimates of the complex electromagnetic field through the IC;combined with a tomographic scan,which collects these complex field projections from multiple angles.Here,we present Attentional Ptycho-Tomography(APT),an approach to drastically reduce the amount of angular scanning,and thus the total acquisition time.APT is machine learning-based,utilizing axial self-Attention for Ptycho-Tomographic reconstruction.APT is trained to obtain accurate reconstructions of the ICs,despite the incompleteness of the measurements.The training process includes regularizing priors in the form of typical patterns found in IC interiors,and the physics of X-ray propagation through the IC.We show that APT with×12 reduced angles achieves fidelity comparable to the gold standard Simultaneous Algebraic Reconstruction Technique(SART)with the original set of angles.When using the same set of reduced angles,then APT also outperforms Filtered Back Projection(FBP),Simultaneous Iterative Reconstruction Technique(SIRT)and SART.The time needed to compute the reconstruction is also reduced,because the trained neural network is a forward operation,unlike the iterative nature of these alternatives.Our experiments show that,without loss in quality,for a 4.48×93.2×3.92µm^(3) IC(≃6×10^(8) voxels),APT reduces the total data acquisition and computation time from 67.96 h to 38 min.We expect our physics-assisted and attention-utilizing machine learning framework to be applicable to other branches of nanoscale imaging,including materials science and biological imaging.
文摘The existing knowledge on the electrodynamics of invisibility cloaking based on transformation optics is reviewed from an integrated science and engineering perspective.Several significant electromagnetic problems that have resulted in intense discussions in the past few years are summarized in terms of propagation,scattering,radiation and fabrication.Finally,the road ahead toward invisibility cloaking and transformation optics is discussed from the viewpoint of the author.
基金supported by the Intelligence Advanced Research Projects Activity(IARPA)grant No.FA8650-17-C-9113supported in part by the KFAS(Korea Foundation for Advanced Studies)scholarship.
文摘The quality of inverse problem solutions obtained through deep learning is limited by the nature of the priors learned from examples presented during the training phase.Particularly in the case of quantitative phase retrieval,spatial frequencies that are underrepresented in the training database,most often at the high band,tend to be suppressed in the reconstruction.Ad hoc solutions have been proposed,such as pre-amplifying the high spatial frequencies in the examples;however,while that strategy improves the resolution,it also leads to high-frequency artefacts,as well as low-frequency distortions in the reconstructions.Here,we present a new approach that learns separately how to handle the two frequency bands,low and high,and learns how to synthesize these two bands into full-band reconstructions.We show that this“learning to synthesize”(LS)method yields phase reconstructions of high spatial resolution and without artefacts and that it is resilient to high-noise conditions,e.g.,in the case of very low photon flux.In addition to the problem of quantitative phase retrieval,the LS method is applicable,in principle,to any inverse problem where the forward operator treats different frequency bands unevenly,i.e.,is ill-posed.
基金The authors acknowledge funding from Intelligence Advanced Research Projects Activity(FA8650-17-C-9113).
文摘Limited-angle tomography of an interior volume is a challenging, highly ill-posed problem with practical implications in medical and biological imaging, manufacturing, automation, and environmental and food security. Regularizing priors are necessary to reduce artifacts by improving the condition of such problems. Recently, it was shown that one effective way to learn the priors for strongly scattering yet highly structured 3D objects, e.g. layered and Manhattan, is by a static neural network [Goy et al. Proc. Natl. Acad. Sci. 116, 19848–19856 (2019)]. Here, we present a radically different approach where the collection of raw images from multiple angles is viewed analogously to a dynamical system driven by the object-dependent forward scattering operator. The sequence index in the angle of illumination plays the role of discrete time in the dynamical system analogy. Thus, the imaging problem turns into a problem of nonlinear system identification, which also suggests dynamical learning as a better fit to regularize the reconstructions. We devised a Recurrent Neural Network (RNN) architecture with a novel Separable-Convolution Gated Recurrent Unit (SC-GRU) as the fundamental building block. Through a comprehensive comparison of several quantitative metrics, we show that the dynamic method is suitable for a generic interior-volumetric reconstruction under a limited-angle scheme. We show that this approach accurately reconstructs volume interiors under two conditions: weak scattering, when the Radon transform approximation is applicable and the forward operator well defined;and strong scattering, which is nonlinear with respect to the 3D refractive index distribution and includes uncertainty in the forward operator.