Deep learning-enabled point-of-care sensing using multiplexed paper-based sensors

Ballard, Zachary S.; Joung, Hyou-Arm; Goncharov, Artem; Liang, Jesse; Nugroho, Karina; Carlo, Dino Di; Garner, Omai B.; Özcan, Aydogan

doi:10.1038/s41746-020-0274-y

Cited by 83 publications

(58 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Inspired by neural interactions in human brain 1 , artificial neural networks and deep learning have been transformative in many fields, providing solutions to a variety of data processing problems, including for example image recognition 2 , natural language processing 3 and medical image analysis 4 . Data-driven training of deep neural networks has set the state-of-the-art performance for various applications in e.g., optical microscopy 4 – 10 , holography 11 – 16 , and sensing 17 – 20 , among others. Beyond these applications, deep learning has also been utilized to solve inverse physical design problems arising in e.g., nanophotonics and plasmonics 21 – 24 .…”

Section: Introductionmentioning

confidence: 99%

Terahertz pulse shaping using diffractive surfaces

et al. 2021

Self Cite

View full text Add to dashboard Cite

Recent advances in deep learning have been providing non-intuitive solutions to various inverse problems in optics. At the intersection of machine learning and optics, diffractive networks merge wave-optics with deep learning to design task-specific elements to all-optically perform various tasks such as object classification and machine vision. Here, we present a diffractive network, which is used to shape an arbitrary broadband pulse into a desired optical waveform, forming a compact and passive pulse engineering system. We demonstrate the synthesis of various different pulses by designing diffractive layers that collectively engineer the temporal waveform of an input terahertz pulse. Our results demonstrate direct pulse shaping in terahertz spectrum, where the amplitude and phase of the input wavelengths are independently controlled through a passive diffractive device, without the need for an external pump. Furthermore, a physical transfer learning approach is presented to illustrate pulse-width tunability by replacing part of an existing network with newly trained diffractive layers, demonstrating its modularity. This learning-based diffractive pulse engineering framework can find broad applications in e.g., communications, ultra-fast imaging and spectroscopy.

show abstract

Section: Introductionmentioning

confidence: 99%

Terahertz pulse shaping using diffractive surfaces

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recent years have witnessed the emergence of deep learning 1 , which has facilitated powerful solutions to an array of intricate problems in artificial intelligence, including image classification 2 , 3 , object detection 4 , natural language processing 5 , speech processing 6 , bioinformatics 7 , optical microscopy 8 , 9 , holography 10 – 12 , sensing 13 , and many more 14 . Deep learning has become particularly popular because of the recent advances in the development of advanced computing hardware and the availability of large amounts of data for training deep neural networks.…”

Section: Introductionmentioning

confidence: 99%

Ensemble learning of diffractive optical networks

et al. 2021

Self Cite

View full text Add to dashboard Cite

A plethora of research advances have emerged in the fields of optics and photonics that benefit from harnessing the power of machine learning. Specifically, there has been a revival of interest in optical computing hardware due to its potential advantages for machine learning tasks in terms of parallelization, power efficiency and computation speed. Diffractive deep neural networks (D2NNs) form such an optical computing framework that benefits from deep learning-based design of successive diffractive layers to all-optically process information as the input light diffracts through these passive layers. D2NNs have demonstrated success in various tasks, including object classification, the spectral encoding of information, optical pulse shaping and imaging. Here, we substantially improve the inference performance of diffractive optical networks using feature engineering and ensemble learning. After independently training 1252 D2NNs that were diversely engineered with a variety of passive input filters, we applied a pruning algorithm to select an optimized ensemble of D2NNs that collectively improved the image classification accuracy. Through this pruning, we numerically demonstrated that ensembles of N = 14 and N = 30 D2NNs achieve blind testing accuracies of 61.14 ± 0.23% and 62.13 ± 0.05%, respectively, on the classification of CIFAR-10 test images, providing an inference improvement of >16% compared to the average performance of the individual D2NNs within each ensemble. These results constitute the highest inference accuracies achieved to date by any diffractive optical neural network design on the same dataset and might provide a significant leap to extend the application space of diffractive optical image classification and machine vision systems.

show abstract

“…To potentially provide frequent and rapid in-field screening of large populations, a miniaturized benchtop fluorescence analyzer that can obtain snapshots of reacted bead lines and measure their final values can be integrated. An effective pixel extraction method will be embedded in the analyzer, thus enabling automatic, timely, and standardized diagnoses ( Ballard et al 2020 ). Importantly, the MOnITOR chip enables periodic and massive diagnosis, irrespective of patient symptoms.…”

Section: Discussionmentioning

confidence: 99%

A single snapshot multiplex immunoassay platform utilizing dense test lines based on engineered beads

Lee

Kim

Bae³

et al. 2021

Biosensors and Bioelectronics

View full text Add to dashboard Cite

Co-circulation of coronavirus disease 2019 (COVID-19) and dengue fever has been reported. Accurate and timely multiplex diagnosis is required to prevent future pandemics. Here, we developed an innovative microfluidic chip that enables a snapshot multiplex immunoassay for timely on-site response and offers unprecedented multiplexing capability with an operating procedure similar to that of lateral flow assays. An open microchannel assembly of individually engineered microbeads was developed to construct nine high-density test lines, which can be imaged in a 1 mm 2 field-of-view. Thus, simultaneous detection of multiple antibodies would be achievable in a single high-resolution snapshot. Next, we developed a novel pixel intensity-based imaging process to distinguish effective and non-specific fluorescence signals, thereby improving the reliability of this fluorescence-based immunoassay. Finally, the chip specifically identified and classified random combinations of arbovirus (Zika, dengue, and chikungunya viruses) and severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) antibodies within 30 minutes. Therefore, we believe that this snapshot multiplex immunoassay chip is a powerful diagnostic tool to control current and future pandemics.

show abstract

Deep learning-enabled point-of-care sensing using multiplexed paper-based sensors

Cited by 83 publications

References 46 publications

Terahertz pulse shaping using diffractive surfaces

Terahertz pulse shaping using diffractive surfaces

Ensemble learning of diffractive optical networks

A single snapshot multiplex immunoassay platform utilizing dense test lines based on engineered beads

Contact Info

Product

Resources

About