We introduce an all-optical Diffractive Deep Neural Network (D2NN) architecture that can learn to implement various functions after deep learning-based design of passive diffractive layers work collectively. experimentally demonstrated the success this framework by creating 3D-printed D2NNs learned handwritten digit classification and function imaging lens at terahertz spectrum. With existing plethora 3D-printing other lithographic fabrication methods as well spatial-light-modulators,...

Since their inception in the 1930-1960s, research disciplines of computational imaging and machine learning have followed parallel tracks and, during last two decades, experienced explosive growth drawing on similar progress mathematical optimization computing hardware.While these developments always been to benefit image interpretation vision, only recently has it become evident that architectures, deep neural networks particular, can be effective for formation, aside from...

Phase recovery from intensity-only measurements forms the heart of coherent imaging techniques and holography. In this study, we demonstrate that a neural network can learn to perform phase holographic image reconstruction after appropriate training. This deep learning-based approach provides an entirely new framework conduct by rapidly eliminating twin-image self-interference-related spatial artifacts. network-based method is fast compute reconstructs amplitude images objects using only one...

We demonstrate lensfree digital microscopy on a cellphone. This compact and light-weight holographic microscope installed cellphone does not utilize any lenses, lasers or other bulky optical components it may offer cost-effective tool for telemedicine applications to address various global health challenges. Weighing ∼38 grams (<1.4 ounces), this imaging platform can be mechanically attached the camera unit of where samples are loaded from side, vertically illuminated by simple...

Despite the rapid progress in optical imaging, most of advanced microscopy modalities still require complex and costly set-ups that unfortunately limit their use beyond well equipped laboratories. In meantime, resource-limited settings has requirements significantly different from those encountered laboratories, such imaging devices should be cost-effective, compact, light-weight appropriately accurate simple to usable by minimally trained personnel. Furthermore, these portable microscopes...

Optical imaging of nanoscale objects, whether it is based on scattering or fluorescence, a challenging task due to reduced detection signal-to-noise ratio and contrast at subwavelength dimensions. Here, we report field-portable fluorescence microscopy platform installed smart phone for individual nanoparticles as well viruses using lightweight compact opto-mechanical attachment the existing camera module cell phone. This hand-held fluorescent device utilizes (i) 450 nm laser diode that...

We demonstrate lensfree holographic microscopy on a chip to achieve approximately 0.6 microm spatial resolution corresponding numerical aperture of 0.5 over large field-of-view 24 mm2. By using partially coherent illumination from (approximately 50 microm), we acquire lower in-line holograms the objects with unit fringe magnification. For each hologram, pixel size at sensor limits reconstructed image. To circumvent this limitation, implement sub-pixel shifting based super-resolution...

We demonstrate a cellphone-based rapid-diagnostic-test (RDT) reader platform that can work with various lateral flow immuno-chromatographic assays and similar tests to sense the presence of target analyte in sample. This compact cost-effective digital RDT reader, weighing only ∼65 g, mechanically attaches existing camera unit cellphone, where types RDTs be inserted imaged reflection or transmission modes under light-emitting diode (LED)-based illumination. Captured raw images these are then...

Detection of environmental contamination such as trace-level toxic heavy metal ions mostly relies on bulky and costly analytical instruments. However, a considerable global need exists for portable, rapid, specific, sensitive, cost-effective detection techniques that can be used in resource-limited field settings. Here we introduce smart-phone-based hand-held platform allows the quantification mercury(II) water samples with parts per billion (ppb) level sensitivity. For this task, created an...

Fluorescent microscopy and flow cytometry are widely used tools in biomedical sciences. Cost-effective translation of these technologies to remote resource-limited environments could create new opportunities especially for telemedicine applications. Toward this direction, here we demonstrate the integration imaging fluorescent on a cell phone using compact, lightweight, cost-effective optofluidic attachment. In cell-phone-based platform, fluorescently labeled particles or cells interest...

We demonstrate that a deep neural network can significantly improve optical microscopy, enhancing its spatial resolution over large field-of-view and depth-of-field. After training, the only input to this is an image acquired using regular microscope, without any changes design. blindly tested learning approach various tissue samples are imaged with low-resolution wide-field systems, where rapidly outputs remarkably better resolution, matching performance of higher numerical aperture lenses,...

Some of the emerging applications and future opportunities challenges created by use mobile phones their embedded components for development next-generation imaging, sensing, diagnostics measurement tools are discussed.

Standard microplate based enzyme-linked immunosorbent assays (ELISA) are widely utilized for various nanomedicine, molecular sensing, and disease screening applications, this multiwell plate batched analysis dramatically reduces diagnosis costs per patient compared to nonbatched or nonstandard tests. However, their use in resource-limited field-settings is inhibited by the necessity relatively large expensive readout instruments. To mitigate problem, we created a hand-held cost-effective...

We demonstrate a handheld on-chip biosensing technology that employs plasmonic microarrays coupled with lens-free computational imaging system towards multiplexed and high-throughput screening of biomolecular interactions for point-of-care applications resource-limited settings. This lightweight field-portable device, weighing 60 g 7.5 cm tall, utilizes compact optoelectronic sensor array to record the diffraction patterns nanostructures under uniform illumination by single-light emitting...

Abstract Using a deep neural network, we demonstrate digital staining technique, which term PhaseStain, to transform the quantitative phase images (QPI) of label-free tissue sections into that are equivalent brightfield microscopy same samples histologically stained. Through pairs image data (QPI and corresponding images, acquired after staining), train generative adversarial network effectiveness this virtual-staining approach using human skin, kidney, liver tissue, matching stained with...

We demonstrate wide-field fluorescent and darkfield imaging on a cell-phone with compact, light-weight cost-effective optical components that are mechanically attached to the existing camera unit of cell-phone. For this purpose, we used battery powered light-emitting diodes (LEDs) pump sample interest from side using butt-coupling, where light was guided within cuvette uniformly excite specimen. The emission then imaged an additional lens positioned right in front camera. Because excitation...

Dynamic tracking of human sperms across a large volume is challenging task. To provide high-throughput solution to this important need, here we describe lensfree on-chip imaging technique that can track the three-dimensional (3D) trajectories &gt; 1,500 individual within an observation approximately 8–17 mm 3 . This computational platform relies on holographic shadows are simultaneously acquired at two different wavelengths, emanating from partially-coherent sources placed 45° with respect...

Holography encodes the three dimensional (3D) information of a sample in form an intensity-only recording. However, to decode original image from its hologram(s), auto-focusing and phase-recovery are needed, which general cumbersome time-consuming digitally perform. Here we demonstrate convolutional neural network (CNN) based approach that simultaneously performs significantly extend depth-of-field (DOF) holographic reconstruction. For this, CNN is trained by using pairs randomly de-focused...