Search

We present a field-portable and high-throughput imaging flow-cytometer, which performs phenotypic analysis of microalgae using image processing and deep learning. This computational cytometer weighs ~1.6kg, and captures holographic images of water samples containing microalgae, flowing in a microfluidic channel at a rate of 100mL/h. Automated analysis is performed by extracting the spatial and spectral features of the reconstructed images to automatically identify/count the target algae within the sample, using image processing and convolutional neural networks. Changes within the measured features and the composition of the microalgae can be rapidly analyzed to reveal even minute deviations from the normal state of the population.

We present a deep learning-based high-throughput cytometer to detect rare cells in whole blood using a cost-effective and light-weight design. This system uses magnetic-particles to label and enrich the target cells. Then, a periodically-alternating magnetic-field creates time-modulated diffraction patterns of the target cells that are recorded using a lensless microscope. Finally, a custom-designed convolutional network is used to detect and classify the target cells based on their modulated spatio-temporal patterns. This cytometer was tested with cancer cells spiked in whole blood to achieve a limit-of-detection of 10 cells/mL. This compact, cost-effective and high-throughput cytometer might serve diagnostics needs in resource-limited-settings.

We report a deep learning-based framework which can be used to screen thin blood smears for sickle-cell-disease using images captured by a smartphone-based microscope. This framework first uses a deep neural network to enhance and standardize the smartphone images to the quality of a diagnostic level benchtop microscope, and a second deep neural network performs cell segmentation. We experimentally demonstrated that this technique can achieve 98% accuracy with an area-under-the-curve (AUC) of 0.998 on a blindly tested dataset made up of thin blood smears coming from 96 patients, of which 32 had been diagnosed with sickle cell disease.

We present a high-throughput and cost-effective computational cytometer for rare cell detection, where the target cells are specifically labeled with magnetic particles and exhibit an oscillatory motion under a periodically-changing magnetic field. The time-varying diffraction patterns of the oscillating cells are then captured with a holographic imaging system and are further classified by a customized pseudo-3D convolutional network. To evaluate the performance of our technique, we detected serially-diluted MCF7 cancer cells that were spiked in whole blood, achieving a limit of detection (LoD) of 10 cells per 1 mL of whole blood.

Schistosomiasis affects over 170 million people in Africa. Here we compare a novel, low-cost mobile phone microscope to a conventional light microscope for the label-free diagnosis of Schistosoma haematobium infections in a rural Ghanaian school setting. We tested the performance of our handheld microscope using 60 slides that were randomly chosen from an ongoing epidemiologic study in school-aged children. The mobile phone microscope had a sensitivity of 72.1% (95% confidence interval [CI]: 56.1-84.2), specificity of 100% (95% CI: 75.9-100), positive predictive value of 100% (95% CI: 86.3-100), and a negative predictive value of 57.1% (95% CI: 37.4-75.0). With its modest sensitivity and high specificity, this handheld and cost-effective mobile phone-based microscope is a stepping-stone toward developing a powerful tool in clinical and public health settings where there is limited access to conventional laboratory diagnostic support.

Detecting rare cells within blood has numerous applications in disease diagnostics. Existing rare cell detection techniques are typically hindered by their high cost and low throughput. Here, we present a computational cytometer based on magnetically modulated lensless speckle imaging, which introduces oscillatory motion to the magnetic-bead-conjugated rare cells of interest through a periodic magnetic force and uses lensless time-resolved holographic speckle imaging to rapidly detect the target cells in three dimensions (3D). In addition to using cell-specific antibodies to magnetically label target cells, detection specificity is further enhanced through a deep-learning-based classifier that is based on a densely connected pseudo-3D convolutional neural network (P3D CNN), which automatically detects rare cells of interest based on their spatio-temporal features under a controlled magnetic force. To demonstrate the performance of this technique, we built a high-throughput, compact and cost-effective prototype for detecting MCF7 cancer cells spiked in whole blood samples. Through serial dilution experiments, we quantified the limit of detection (LoD) as 10 cells per millilitre of whole blood, which could be further improved through multiplexing parallel imaging channels within the same instrument. This compact, cost-effective and high-throughput computational cytometer can potentially be used for rare cell detection and quantification in bodily fluids for a variety of biomedical applications., Deep Learning Cytometry: Magnetically modulating rare cells for high-throughput detection Rare cells of medical significance can be detected in blood by a high-throughput imaging technique that analyzes movements of magnetically-labelled target cells using deep-learning. Analysis of magnetically-modulated light interference using an artificial neural network enhances the ability of the system to specifically and sensitively detect the tagged cells as they respond to a periodically changing magnetic field. Researchers in the USA, led by Aydogan Ozcan at the University of California, Los Angeles, demonstrated the technique using rare cancer cells added to blood. They achieved a detection limit as low as ten cells per milliliter. The optical system uses a holographic process called speckle imaging, which is much more compact and achieves higher throughput than traditional methods. It holds significant potential for the rapid analysis of blood and other bodily fluids to diagnose and monitor disease.

Lack of access to clean water is a major global issue that affects millions of people worldwide. Drinking contaminated water can be extremely hazardous, so it is imperative that it is tested sufficiently. One method commonly used to determine the quality of water is testing for both E. coli and total coliform. Here, we present a cost-effective and automated device which can concurrently test drinking water samples for both E. coli and total coliform using an EPA-approved reagent. Equipped with a Raspberry Pi microcontroller and camera, we perform automated periodic measurements of both the absorption and fluorescence of the water under test over 24 hours. In each test, 100 mL of the water sample is split into a custom designed 40-well plate, where the transmitted blue light and the fluorescent light (under UV excitation) are collected by 520 individual optical fibers. Images of these fiber outputs are then acquired periodically, and digitally processed to determine the presence of the bacteria in each well of the 40-well plate. We demonstrate that this cost-effective device, weighing 1.66 kg, can automatically detect the presence of both E. coli and total coliform in drinking water within ∼16 hours, down to a level of one colony-forming unit (CFU) per 100 mL. Furthermore, due to its automated analysis, this approach is also more sensitive than a manual count performed by an expert, reducing the time needed to determine whether the water under test is safe to drink or not.

We introduce a field-portable and cost-effective holographic imaging flow cytometer, which provides phase contrast microscopic images of the contents of water samples at a throughput of 100 ml/h. This imaging cytometer uses a high power multi-colored LED and a custom designed circuit to illuminate continuously flowing water samples with short-pulses of red, green, and blue light that are simultaneously on, thereby eliminating motion blur and making the system vibration resistant. The recorded color holograms are segmented and reconstructed in real time and are phase recovered using a deep learning-based algorithm. Weighing 1kg with the dimensions of 15.5 cm × 15 cm × 12.5 cm, our label-free imaging flow-cytometer is controlled by a laptop computer equipped with a graphical processing unit. We tested the capabilities of our field-portable device by imaging micro- and nano-plankton inside ocean water samples collected at six beaches along the California coastline. We also determined Pseudo-Nitzschia algae concentration of these samples, providing a good agreement with the measurements made by the California Department of Public Health. Our device represents 1-2 orders of magnitude reduction in the cost and size of an imaging flow cytometer compared to state-of-the-art designs, while providing a similar or better performance in terms of volumetric throughput, detection limit and imaging resolution.

There is an increasing but unmet need for accurate, label-free and automated bio-aerosol sensing. To address this need, we developed a high-throughput, cost-effective and portable bio-aerosol sensor based on computational microscopy and deep-learning. Our device is composed of an impactor and a lens-less digital holographic on-chip microscope. It screens air at 13 liters per minute, and captures bio-aerosols on the impactor substrate. An image sensor then records the in-line holograms of these captured bio-aerosols in real time. Using these recorded in-line holograms, the captured bio-aerosols are analyzed within a minute, facilitated by two deep convolutional neural networks (CNNs): the first CNN simultaneously performs auto-focusing and phase-recovery to reconstruct both the amplitude and phase images of each bio-aerosol with sub-micron resolution; and the second CNN performs automatic classification of the reconstructed bio-aerosols into pre-trained classes and counting their densities in air. As a proof-of-concept, we demonstrated reconstruction and label-free sensing of five different types of bio-aerosols: Bermuda grass pollen, oak tree pollen, ragweed pollen, Aspergillus spore, and Alternaria spore. These bio-aerosols form some of the most common allergens in air. Using our mobile bio-aerosol sensor, we achieved ~94% precision and recall in differentiating these bio-aerosols without the use of any labeling. We also demonstrated successful sensing of oak tree pollens in the field using our mobile device. To the best of our knowledge, this is the first demonstration of automated label-free sensing of bio-aerosols using a portable device, which is enabled by computational microscopy and deep-learning. It has broad applications in label-free bio-aerosol sensing and air-quality monitoring.

We report a deep learning-enabled field-portable and cost-effective imaging flow cytometer that automatically captures phase-contrast color images of the contents of a continuously flowing water sample at a throughput of 100 mL/h. The device is based on partially coherent lens-free holographic microscopy and acquires the diffraction patterns of flowing micro-objects inside a microfluidic channel. These holographic diffraction patterns are reconstructed in real time using a deep learning-based phase-recovery and image-reconstruction method to produce a color image of each micro-object without the use of external labeling. Motion blur is eliminated by simultaneously illuminating the sample with red, green, and blue light-emitting diodes that are pulsed. Operated by a laptop computer, this portable device measures 15.5 cm × 15 cm × 12.5 cm, weighs 1 kg, and compared to standard imaging flow cytometers, it provides extreme reductions of cost, size and weight while also providing a high volumetric throughput over a large object size range. We demonstrated the capabilities of this device by measuring ocean samples at the Los Angeles coastline and obtaining images of its micro- and nanoplankton composition. Furthermore, we measured the concentration of a potentially toxic alga (Pseudo-nitzschia) in six public beaches in Los Angeles and achieved good agreement with measurements conducted by the California Department of Public Health. The cost-effectiveness, compactness, and simplicity of this computational platform might lead to the creation of a network of imaging flow cytometers for large-scale and continuous monitoring of the ocean microbiome, including its plankton composition.

Diagnostics based on fluorescence imaging of biomolecules is typically performed in well-equipped laboratories and is in general not suitable for remote and resource limited settings. Here we demonstrate the development of a compact, lightweight and cost-effective smartphone-based fluorescence microscope, capable of detecting signals from fluorescently labeled bacteria. By optimizing a peptide nucleic acid (PNA) based fluorescence in situ hybridization (FISH) assay, we demonstrate the use of the smartphone-based microscope for rapid identification of pathogenic bacteria. We evaluated the use of both a general nucleic acid stain as well as species-specific PNA probes and demonstrated that the mobile platform can detect bacteria with a sensitivity comparable to that of a conventional fluorescence microscope. The PNA-based FISH assay, in combination with the smartphone-based fluorescence microscope, allowed us to qualitatively analyze pathogenic bacteria in contaminated powdered infant formula (PIF) at initial concentrations prior to cultivation as low as 10 CFU per 30 g of PIF. Importantly, the detection can be done directly on the smartphone screen, without the need for additional image analysis. The assay should be straightforward to adapt for bacterial identification also in clinical samples. The cost-effectiveness, field-portability and simplicity of this platform will create various opportunities for its use in resource limited settings and point-of-care offices, opening up a myriad of additional applications based on other fluorescence-based diagnostic assays.

We introduce a deep learning based approach that uses a neural network to enhance the image resolution and color accuracy of a smartphone microscope, mitigating the gap between low cost mobile imaging devices and high end benchtop microscopes.

We created a mobile fluorescence microscope weighing

not available. © (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.

Schistosomiasis is a parasitic and neglected tropical disease, and affects

Quantification of plant health is crucial for agriculture and can even be used to monitor environmental factors and climate related changes. Plant health is known to be directly related to the chlorophyll content of leaves, which correlates with the capacity of the leaves to transmit or absorb light. The gold-standard method for measuring the chlorophyll concentration of a leaf is based on chemical extraction, which is complex, destructive and time-consuming. As an alternative, here we present a field-portable, cost-effective, and colorimetric method to quantify the chlorophyll content of leaves using Google Glass. For this purpose, we created a custom designed handheld device which is battery-powered and 3D-printed to separately provide uniform illumination of a selected region of interest on the leaf surface using red and white light-emitting-diodes (LEDs). The design of this device minimizes the interference of ambient light conditions to our chlorophyll measurements performed through the Glass camera. We tested this platform by using fifteen randomly selected plant species from UCLA Botanical Garden and imaging fully-grown leaves of these species using Glass. An image-processing algorithm was developed to process the acquired images and obtain the chlorophyll concentration information using the red channel intensities in our region-of-interest for both the white and red LED illumination conditions. The results obtained by this algorithm are in good agreement with the SPAD indices measured for each plant, demonstrating that Google Glass, in combination with our custom-designed illumination platform, can expand its functionality to be used as a chlorophyll meter in field-settings.

Giardia lamblia is a waterborne parasite that causes an intestinal infection, known as giardiasis, and it is found not only in countries with inadequate sanitation and unsafe water but also streams and lakes of developed countries. Simple, sensitive, and rapid detection of this pathogen is important for monitoring of drinking water. Here we present a cost-effective and field portable mobile-phone based fluorescence microscopy platform designed for automated detection of Giardia lamblia cysts in large volume water samples (i.e., 10 ml) to be used in low-resource field settings. This fluorescence microscope is integrated with a disposable water-sampling cassette, which is based on a flow-through porous polycarbonate membrane and provides a wide surface area for fluorescence imaging and enumeration of the captured Giardia cysts on the membrane. Water sample of interest, containing fluorescently labeled Giardia cysts, is introduced into the absorbent pads that are in contact with the membrane in the cassette by capillary action, which eliminates the need for electrically driven flow for sample processing. Our fluorescence microscope weighs ~170 grams in total and has all the components of a regular microscope, capable of detecting individual fluorescently labeled cysts under light-emitting-diode (LED) based excitation. Including all the sample preparation, labeling and imaging steps, the entire measurement takes less than one hour for a sample volume of 10 ml. This mobile phone based compact and cost-effective fluorescent imaging platform together with its machine learning based cyst counting interface is easy to use and can even work in resource limited and field settings for spatio-temporal monitoring of water quality.

Mobile-phones have facilitated the creation of field-portable, cost-effective imaging and sensing technologies that approach laboratory-grade instrument performance. However, the optical imaging interfaces of mobile-phones are not designed for microscopy and produce spatial and spectral distortions in imaging microscopic specimens. Here, we report on the use of deep learning to correct such distortions introduced by mobile-phone-based microscopes, facilitating the production of high-resolution, denoised and colour-corrected images, matching the performance of benchtop microscopes with high-end objective lenses, also extending their limited depth-of-field. After training a convolutional neural network, we successfully imaged various samples, including blood smears, histopathology tissue sections, and parasites, where the recorded images were highly compressed to ease storage and transmission for telemedicine applications. This method is applicable to other low-cost, aberrated imaging systems, and could offer alternatives for costly and bulky microscopes, while also providing a framework for standardization of optical images for clinical and biomedical applications.

Sickle cell disease (SCD) is a major public health priority throughout much of the world, affecting millions of people. In many regions, particularly those in resource-limited settings, SCD is not consistently diagnosed. In Africa, where the majority of SCD patients reside, more than 50% of the 0.2-0.3 million children born with SCD each year will die from it; many of these deaths are in fact preventable with correct diagnosis and treatment. Here we present a deep learning framework which can perform automatic screening of sickle cells in blood smears using a smartphone microscope. This framework uses two distinct, complementary deep neural networks. The first neural network enhances and standardizes the blood smear images captured by the smartphone microscope, spatially and spectrally matching the image quality of a laboratory-grade benchtop microscope. The second network acts on the output of the first image enhancement neural network and is used to perform the semantic segmentation between healthy and sickle cells within a blood smear. These segmented images are then used to rapidly determine the SCD diagnosis per patient. We blindly tested this mobile sickle cell detection method using blood smears from 96 unique patients (including 32 SCD patients) that were imaged by our smartphone microscope, and achieved ~98% accuracy, with an area-under-the-curve (AUC) of 0.998. With its high accuracy, this mobile and cost-effective method has the potential to be used as a screening tool for SCD and other blood cell disorders in resource-limited settings., Comment: 30 pages, 5 figures