A5001462698- Cell Image Analysis Techniques
- Image Processing Techniques and Applications
- Digital Holography and Microscopy
- Digital Imaging for Blood Diseases
- COVID-19 diagnosis using AI
- Microfluidic and Bio-sensing Technologies
- AI in cancer detection
- Digital and Traditional Archives Management
- Marine and coastal ecosystems
- Mosquito-borne diseases and control
- Genetic factors in colorectal cancer
- Water Quality Monitoring Technologies
- Educator Training and Historical Pedagogy
- Hemoglobinopathies and Related Disorders
- Biosensors and Analytical Detection
- Bacterial Identification and Susceptibility Testing
- Gastrointestinal disorders and treatments
- Microbial Community Ecology and Physiology
- Colorectal Cancer Surgical Treatments
- Fish biology, ecology, and behavior
- Diverticular Disease and Complications
- American Political and Social Dynamics
- Microscopic Colitis
- Gastroesophageal reflux and treatments
University of California, Los Angeles
2019-2021
Sickle cell disease (SCD) is a major public health priority throughout much of the world, affecting millions people. In many regions, particularly those in resource-limited settings, SCD not consistently diagnosed. Africa, where majority patients reside, more than 50% 0.2-0.3 million children born with each year will die from it; these deaths are fact preventable correct diagnosis and treatment. Here, we present deep learning framework which can perform automatic screening sickle cells blood...
Early identification of pathogenic bacteria in food, water, and bodily fluids is very important yet challenging, owing to sample complexities large volumes that need be rapidly screened. Existing screening methods based on plate counting or molecular analysis present various tradeoffs with regard the detection time, accuracy/sensitivity, cost, preparation complexity. Here, we a computational live system periodically captures coherent microscopy images bacterial growth inside 60-mm-diameter...
Environmental factors such as temperature, nutrients, and pollutants affect the growth rates physical characteristics of microalgae populations. As algae play a vital role in marine ecosystems, monitoring is important to observe state an ecosystem. However, analyzing these populations using conventional light microscopy time-consuming requires experts both identify count algal cells, which turn considerably limits volume samples that can be measured each experiment. In this work we use...
Abstract Water quality is undergoing significant deterioration due to bacteria, pollutants and other harmful particles, damaging aquatic life lowering the of drinking water. It is, therefore, important be able rapidly accurately measure water in a cost-effective manner using e.g., turbidimeter. Turbidimeters typically use different illumination angles scattering transmittance light through sample translate these readings into measurement based on standard nephelometric turbidity unit (NTU)....
We present a deep learning-based framework for performing automatic screening of sickle cells using smartphone-based microscope. achieved 98% accuracy when blindly testing 96 human blood smear slides, including 32 with cell disease.
Using deep learning and lensfree holographic imaging, we report early detection classification of bacterial colonies in water samples. Our system detects 1 colony-forming unit (CFU) per Liter within 9 h total test time.
We report a highly-sensitive, high-throughput, and cost-effective bacteria identification system which continuously captures reconstructs holographic images of an agar-plate analyzes the time-lapsed with deep learning models for early detection colonies. The performance our was confirmed by classification Escherichia coli, Enterobacter aerogenes, Klebsiella pneumoniae in water samples. detected 90% bacterial colonies their growth within 7-10h (>95% 12h) ~100% precision, correctly identified...
We report a field-portable and high-throughput imaging flow-cytometer to perform label-free phenotypic analysis of microalgae populations by extracting processing the spatial spectral features their reconstructed holographic images using deep learning.
We report a deep learning-based framework which can be used to screen thin blood smears for sickle-cell-disease using images captured by smartphone-based microscope. This first uses neural network enhance and standardize the smartphone quality of diagnostic level benchtop microscope, second performs cell segmentation. experimentally demonstrated that this technique achieve 98% accuracy with an area-under-the-curve (AUC) 0.998 on blindly tested dataset made up coming from 96 patients, 32 had...
We present a deep-learning based device to perform automated screening of sickle cell disease (SCD) using images blood smears captured by smartphone-based microscope. experimentally validated the system 96 (including 32 positive samples for SCD), each coming from unique patient. Tested on these smears, our framework achieved 98% accuracy and had an area-under-the-curve (AUC) 0.998. Since this technique is both low-cost accurate, it has potential improve access cost-effective monitoring...
We present a field-portable and high-throughput imaging flow-cytometer, which performs phenotypic analysis of microalgae using image processing deep learning. This computational cytometer weighs ~1.6kg, captures holographic images water samples containing microalgae, flowing in microfluidic channel at rate 100mL/h. Automated is performed by extracting the spatial spectral features reconstructed to automatically identify/count target algae within sample, convolutional neural networks. Changes...
We present a deep learning-aided imaging system for early detection and classification of live bacterial colonies by capturing time-lapse holographic images an agar plate analyzing these using neural networks. blindly tested our identifying Escherichia coli total coliform bacteria in spiked water samples successfully detected 90% the within 7-10 h, while keeping 99.2~100% precision. further classified corresponding species 7.6-12 h incubation with 80% accuracy, which represents >12...