Lifan Chen, Ph.D.

Lifan Chen, Ph.D.

Cupertino, California, United States
2K followers 500+ connections

Join to view profile

About

An out-of-the-box thinker. A cross functional team leader and collaborator. Highly…

Articles by Lifan

Activity

2K followers

See all activities

Experience

  • Apple Graphic

    Apple

    Cupertino, California, United States

  • -

    Redmond, Washington, United States

  • -

    San Jose, CA

  • -

    Los Angeles

  • -

    Los Angeles, California, United States

  • -

    Electrical Engineering Department

Education

  • UCLA Graphic

    University of California, Los Angeles

    -

    -

    Activities and Societies: OSE/SPIE Student Chapter, Technical Entrepreneurial Community, CSSA-UCLA

    Field:
    Computational imaging, Microscopy, Fiber Optics, Coherent Detection, Flow Cytometry,
    Image processing, Machine learning

  • -

    -

  • -

    -

Volunteer Experience

  • The Optical Society (OSA) Graphic

    President of student chapter at UCLA

    The Optical Society (OSA)

    - 1 month

    Education

    Educational outreach, academic seminars, social network for optics and photonics community

  • SPIE Graphic

    President of student chapter at UCLA

    SPIE

    - 1 month

    Science and Technology

    Educational outreach, academic seminars, social network for optics and photonics community

Publications

  • Deep Cytometry: Deep Learning with Real-Time Inference in Cell Sorting and Flow Cytometry

    Nature Scientific Reports

    We demonstrated a new deep learning pipeline, which entirely avoids the slow and computationally costly signal processing and feature extraction steps by a convolutional neural network that directly operates on the measured phase contrast microscope images.

    Other authors
    See publication

  • Deep Learning Smart Microscope

    OSA publishing

    We describe a microscope featuring artificial intelligence (AI), time stretch, quantitative phase imaging and optofluidics. Capturing images at 50 GigaPixels per seconds, the system has shown record performance in classification of cancer in blood.

    Other authors
    See publication

  • Artificial Intelligence in Label-Free Microscopy

    Springer

    This book demonstrates how machine learning is used in high-speed microscopy imaging to facilitate medical diagnosis; provides a systematic and comprehensive illustration of time stretch technology; and enables multidisciplinary application, including industrial, biomedical, and artificial intelligence.

    Other authors
    See publication

  • Deep Learning in Label-free Cell Classification

    Nature Scientific Reports

    We integrate feature extraction and deep learning with high-throughput quantitative imaging enabled by photonic time stretch, achieving record high accuracy in label-free cell classification. Our system captures quantitative optical phase and intensity images and extracts multiple biophysical features of individual cells. These biophysical measurements form a hyperdimensional feature space in which supervised learning is performed for cell classification. We compare various learning algorithms…

    We integrate feature extraction and deep learning with high-throughput quantitative imaging enabled by photonic time stretch, achieving record high accuracy in label-free cell classification. Our system captures quantitative optical phase and intensity images and extracts multiple biophysical features of individual cells. These biophysical measurements form a hyperdimensional feature space in which supervised learning is performed for cell classification. We compare various learning algorithms including aritificial neural network, support vector machine, logistic regression, and a novel deep learning pipeline, which adopts global optimization of receiver operating characteristics. As a validation of the enhanced sensitivity and specificity of our system, classification of white blood T-cells against colon cancer cells is shown, as well as lipid accumulating algal strains for biofuel production. This system opens up a new path to data-driven phenotypic diagnosis and better understanding of the heterogeneous gene expressions in cells.

    Other authors
    See publication

  • Design of Warped Stretch Transform

    Scientific Reports

    Here, for the first time, we show how to design the kernel of the transform and specifically, the nonlinear group delay profile dictated by the signal sparsity. Such a kernel leads to smart stretching with nonuniform spectral resolution, having direct utility in improvement of data acquisition rate, real-time data compression, and enhancement of ultrafast data capture accuracy.

    Other authors
    See publication

  • Optical Data Compression in Time Stretch Imaging

    PLoS One

    By exploiting the sparsity of the image, we reduce the number of samples and the amount of data generated by the time stretch camera in our proof-of-concept experiments by about three times. Optical data compression addresses the big data predicament in such systems.

    Other authors
    See publication

  • Optical Data Compression in Time Stretch Imaging

    PLOS ONE

    We report the first experimental demonstration of real-time optical image compression applied to time stretch imaging. By exploiting the sparsity of the image, we reduce the number of samples and the amount of data generated by the time stretch camera in our proof-of-concept experiments by about three times. Optical data compression addresses the big data predicament in such systems.

    Other authors
    See publication

  • High-throughput Biological Cell Classification Featuring Real-time Optical Data Compression

    Conference on Information Sciences and Systems, CISS 2015, Baltimore, MD, USA

    Other authors

  • Label-free high-throughput cell screening in flow

    Biomedical Optics Express

    Other authors
    See publication

  • Silicon PIN quasi-continuous wave Terahertz emitter

    IEEE

    Enhanced external efficiency, improved coherence and tunability are demonstrated for silicon PIN THz emitters by utilizing the internal reflection and multi optical pulse excitation.

    Other authors
    See publication

Patents

  • Deep learning in label-free cell classification and machine vision extraction of particles

    Issued US WO/2017/053592

    A method and apparatus for using deep learning in label-free cell classification and machine vision extraction of particles. A time stretch quantitative phase imaging (TS-QPI) system is described which provides high-throughput quantitative imaging, and utilizing photonic time stretching. In at least one embodiment, TS-QPI is integrated with deep learning to achieve record high accuracies in label-free cell classification. The system captures quantitative optical phase and intensity images and…

    A method and apparatus for using deep learning in label-free cell classification and machine vision extraction of particles. A time stretch quantitative phase imaging (TS-QPI) system is described which provides high-throughput quantitative imaging, and utilizing photonic time stretching. In at least one embodiment, TS-QPI is integrated with deep learning to achieve record high accuracies in label-free cell classification. The system captures quantitative optical phase and intensity images and extracts multiple biophysical features of individual cells. These biophysical measurements form a hyperdimensional feature space in which supervised learning is performed for cell classification. The system is particularly well suited for data-driven phenotypic diagnosis and improved understanding of heterogeneous gene expression in cells.

    See patent

  • A method of data reduction in deep learning

    Filed US pending

    with application to improve most of current machine learning techniques heavily used in information technology and internet industry.

    Other inventors

  • A Method of Filter Design for Signal Analysis

    Filed US 62/166,064

    In application for signal processing and analysis, efficient sampling, sparse coding and feature representation of data, improvement in signal to noise ratio and feature detection, compression, and classification.

    Other inventors

Honors & Awards

  • UCLA Graduate Division Fellowship

    -

  • CYTO best student award finalist

    -

  • UCLA Graduate Division Fellowship

    -

  • UCLA Biomedical Engineering Fellowship

    -

  • SPIE student chapter officer travel grant

    -

  • The First Prize of People’s Scholarship by Ministry of Education, China

    -

Languages

  • Chinese

    -

  • English

    -

View Lifan’s full profile

  • See who you know in common
  • Get introduced
  • Contact Lifan directly
Join to view full profile

Other similar profiles

Explore more posts

Explore top content on LinkedIn

Find curated posts and insights for relevant topics all in one place.

View top content

Add new skills with these courses

See all courses