A5090108597- Cell Image Analysis Techniques
- Image Processing Techniques and Applications
- Advanced Fluorescence Microscopy Techniques
- Digital Holography and Microscopy
- Anomaly Detection Techniques and Applications
- Single-cell and spatial transcriptomics
- Risk and Safety Analysis
- Advanced Statistical Methods and Models
- Bacterial Identification and Susceptibility Testing
- Advanced Biosensing Techniques and Applications
- Microfluidic and Capillary Electrophoresis Applications
- Speech Recognition and Synthesis
- Neural dynamics and brain function
- AI in cancer detection
- Voice and Speech Disorders
- Machine Learning in Materials Science
- Biosensors and Analytical Detection
- Advanced Proteomics Techniques and Applications
- Photoacoustic and Ultrasonic Imaging
- Advanced Optical Imaging Technologies
- Speech and Audio Processing
- Advanced Image Processing Techniques
- Photoreceptor and optogenetics research
- Circadian rhythm and melatonin
- Phonetics and Phonology Research
Stanford University
2013-2025
Google (United States)
2018-2023
California Institute of Technology
2010-2011
Light field microscopy is a new technique for high-speed volumetric imaging of weakly scattering or fluorescent specimens.It employs an array microlenses to trade off spatial resolution against angular resolution, thereby allowing 4-D light be captured using single photographic exposure without the need scanning.The recorded can then used computationally reconstruct full volume.In this paper, we present optical model based on wave optics, instead previously reported ray optics models.We also...
The successful planning and execution of adaptive behaviors in mammals may require long-range coordination neural networks throughout cerebral cortex. neuronal implementation signals that could orchestrate cortex-wide activity remains unclear. Here, we develop apply methods for Ca2+ imaging mice performing decision-making behavior identify a global cortical representation task engagement encoded the dynamics both single cells superficial neuropil distributed across majority dorsal multiple...
Light field microscopy has been proposed as a new high-speed volumetric computational imaging method that enables reconstruction of 3-D volumes from captured projections the 4-D light field. Recently, detailed physical optics model microscope derived, which led to development deconvolution algorithm reconstructs with high spatial resolution. However, resolution reconstructions shown be non-uniform across depth, some z planes showing and others, particularly at center imaged volume, very low...
Large image datasets acquired on automated microscopes typically have some fraction of low quality, out-of-focus images, despite the use hardware autofocus systems. Identification these images using analysis with high accuracy is important for obtaining a clean, unbiased dataset. Complicating this task fact that focus quality only well-defined in foreground regions and as result, most previous approaches enable computation relative difference between two or more rather than an absolute...
We report the implementation of a fully on-chip, lensless, sub-pixel resolving optofluidic microscope (SROFM). The device utilizes microfluidic flow to deliver specimens directly across complementary metal oxide semiconductor (CMOS) sensor generate sequence low-resolution (LR) projection images, where resolution is limited by sensor's pixel size. This image then processed with super-resolution algorithm reconstruct single high (HR) image, features beyond Nyquist rate LR images are resolved....
Drug discovery for diseases such as Parkinson's disease are impeded by the lack of screenable cellular phenotypes. We present an unbiased phenotypic profiling platform that combines automated cell culture, high-content imaging, Cell Painting, and deep learning. applied this to primary fibroblasts from 91 patients matched healthy controls, creating largest publicly available Painting image dataset date at 48 terabytes. use fixed weights a convolutional neural network trained on ImageNet...
Miniaturization of imaging systems can significantly benefit clinical diagnosis in challenging environments, where access to physicians and good equipment be limited. Sub-pixel resolving optofluidic microscope (SROFM) offers high-resolution the form an on-chip device, with combination microfluidics inexpensive CMOS image sensors. In this work, we report on implementation color SROFM prototypes a demonstrated optical resolution 0.66 µm at their highest acuity. We applied perform red blood...
The quest to identify materials with tailored properties is increasingly expanding into high-order composition spaces, a corresponding combinatorial explosion in the number of candidate materials. A key challenge discover regions space where have novel properties. Traditional predictive models for material are not accurate enough guide search. Herein, we use high-throughput measurements optical three-cation metal oxide spaces by identifying compositions whose trends cannot be explained...
Post-Acute Sequelae of SARS-CoV-2 infection (PASC or “Long COVID”), includes numerous chronic conditions associated with widespread morbidity and rising healthcare costs. PASC has highly variable clinical presentations, likely multiple molecular subtypes, but it remains poorly understood from a mechanistic standpoint. This hampers the development rationally targeted therapeutic strategies. The NIH-sponsored “Researching COVID to Enhance Recovery” (RECOVER) initiative several...
We highlight the interindividual heterogeneity in pathogen killing kinetics by physiological concentrations of antibiotics urine and develop a microfluidic device capable tracking single-cell trajectories while allowing for reagent exchange.
Speech-to-text capabilities on mobile devices have proven helpful for hearing and speech accessibility, language translation, note-taking, meeting transcripts. However, our foundational large-scale survey (n=263) shows that the inability to distinguish indicate speaker direction makes them challenging in group conversations. SpeechCompass addresses this limitation through real-time, multi-microphone localization, where of allows visual separation guidance (e.g., arrows) user interface. We...
The etiological underpinnings of many CNS disorders are not well understood. This is likely due to the fact that individual diseases aggregate numerous pathological subtypes, each associated with a complex landscape genetic risk factors. To overcome these challenges, researchers integrating novel data types from patients, including imaging studies capturing broadly applicable features patient-derived materials. These datasets, when combined machine learning, potentially hold power elucidate...
Fundamental display characteristics are constantly being improved, especially resolution, dynamic range, and color reproduction. However, whereas high resolution high-dynamic range displays have matured as a technology, it remains largely unclear how to extend the gamut of without either sacrificing light throughput or making other tradeoffs. In this paper, we advocate for adaptive display; with hardware implementations that allow primaries be dynamically chosen, an optimal corresponding...
Tracking the coordinated activity of cellular events through volumes intact tissue is a major challenge in biology that has inspired significant technological innovation. Yet scanless measurement high-speed individual neurons across three dimensions scattering mammalian remains an open problem. Here we develop and validate computational imaging approach (SWIFT) integrates high-dimensional, structured statistics with light field microscopy to allow synchronous acquisition single-neuron...
We developed dysarthric speech intelligibility classifiers on 551,176 disordered samples contributed by a diverse set of 468 speakers, with range self-reported speaking disorders and rated for their overall five-point scale. trained three models following different deep learning approaches evaluated them ~ 94K utterances from 100 speakers. further found the to generalize well (without training) TORGO database[1] (100% accuracy), UASpeech[2] (0.93 correlation), ALS-TDI PMP[3] (0.81 AUC)...
Machine learning is transforming materials discovery by providing rapid predictions of material properties, which enables large-scale screening for target materials. However, such models require training data. While automated data extraction from scientific literature has potential, current auto-generated datasets often lack sufficient accuracy and critical structural processing details that influence the properties. Using band gap as an example, we demonstrate Large language model...
This paper introduces a new method of data-driven microscope design for virtual fluorescence microscopy. We use deep neural network (DNN) to effectively optical patterns specimen illumination that substantially improve upon the ability infer image information from unstained images. To achieve this design, we include an model within DNN's first layers is jointly optimized during training. validated our on two different experimental setups, with magnifications and sample types, show consistent...
Introduction Multidrug-resistant Enterobacteriaceae are among the most urgent global public health threats associated with various life-threatening infections. In absence of a rapid method to identify antimicrobial susceptibility, empirical use broad-spectrum antimicrobials such as carbapenem monotherapy has led spread resistant organisms. Rapid determination resistance is urgently needed overcome this issue. Methods By capturing dynamic single-cell morphological features, including...
Profiling cellular phenotypes from microscopic imaging can provide meaningful biological information resulting various factors affecting the cells. One motivating application is drug development: morphological cell features be captured images, which similarities between different compounds applied at doses quantified. The general approach to find a function mapping images an embedding space of manageable dimensionality whose geometry captures relevant input images. An important known issue...