Hung P. Do, PhD, MSEE

Senior Clinical Scientist (Senior MRI Physicist)

Email   Homepage   Google Scholar   LinkedIn   Github   Work   Tustin, CA


Jump to: Skills | Jobs | Education | Awards | Certificates | Publications | Talks | Teaching | Reviewer | Membership | Interests


Expertise and Skills

  • Magnetic Resonance Imaging (MRI) Physics, MRI Pulse Sequence Design, and Advanced Image Reconstruction
  • Signal and Image Processing
  • Design and execute scientific, FDA 510(k)-cleared, and hypothesis-driven research studies
  • Applications of Statistics, Data Science, Machine Learning, and Deep Learning to MRI, Medical Imaging, and Healthcare
  • Clinical evaluations and translations of innovative imaging solutions into clinical practice
  • End-to-end project management and multidisciplinary collaborations
  • Fundamental and translational MRI research related to quantitative imaging, novel pulse sequence design, and advanced image reconstruction
  • Programmable animation, data visualization, data analysis, and statistics using Python and R
  • Bayesian methods and probabilistic programming for quantitative imaging with uncertainty quantification
  • Mathematical modeling, numerical simulations, and optimization
  • Automatic and reproducible pipelines for data curation, cleaning, and visualization, statistical analysis, and report/presentation generation using Git version control, Bash, Python, R, and related packages
  • Operating Systems: Linux, macOS, and Microsoft Windows
  • Programming Languages: Python, R, Bash, EPIC (General Electric (GE) Healthcare's C-based MRI pulse sequence programming language)
  • Packages and Libraries: Pandas, NumPy, PyDicom, SciPy, Matplotlib, Tidyverse, ggplot2, Seaborn, fastai, TensorFlow-Keras, PyTorch, nbdev
  • Version Control: Git and GitHub
  • Package and Environments Management: Anaconda and PyPI's pip
  • Tools: Microsoft Office, Command Line (Terminal), Markdown, HTML, CSS, \( \LaTeX \), OsiriX, Visual Studio Code


Experience


Education


Honors and Awards


Certificates

  • Data Science: Statistics and Machine Learning, a 5-Course Specialization, Profs. Jeff Leek, Roger Peng, Brian Caffo, Department of Biostatistics, Johns Hopkins Bloomberg School of Public Health, Johns Hopkins University
    • Course 1: Statistical Inference
    • Course 2: Regression Model
    • Course 3: Practical Machine Learning
    • Course 4: Developing Data Products
    • Course 5: Data Science Capstone Project
  • Data Science: Foundations using R, a 5-Course Specialization, Profs. Jeff Leek, Roger Peng, Brian Caffo, Department of Biostatistics, Johns Hopkins Bloomberg School of Public Health, Johns Hopkins University
    • Course 1: The Data Scientist’s Toolbox
    • Course 2: R Programming
    • Course 3: Getting and Cleaning Data
    • Course 4: Exploratory Data Analysis
    • Course 5: Reproducible Research
  • AI for Healthcare, a 5-Course Specialization, Profs. Nigam Shah, Laurence Baker, David Magnus, Serena Yeung, Mildred Cho, Steven Bagley, Matthew Lungren, Tina Hernandez-Boussard, Stanford University
    • Course 1: Introduction to Healthcare
    • Course 2: Introduction to Clinical Data
    • Course 3: Fundamentals of Machine Learning for Healthcare
    • Course 4: Evaluations of AI applications in Healthcare
    • Course 5: AI in Healthcare Capstone Projects
  • Statistics with Python, a 3-Course Specialization, Brenda Gunderson PhD, Brady T. West PhD, Kerby Shedden PhD, University of Michigan
    • Course 1: Understanding and Visualizing Data with Python
    • Course 2: Inferential Statistical Analysis with Python
    • Course 3: Fitting Statistical Models to Data with Python
  • AI for Medicine, a 3-Course Specialization, Pranav Rajpurkar PhD candidate, Stanford University and deeplerning.ai
    • Course 1: AI for Medical Diagnosis
    • Course 2: AI for Medical Prognosis
    • Course 3: AI for Medical Treatment
  • Improving your statistical inferences, Daniel Lakens PhD, Eindhoven University of Technology
  • Improving Your Statistical Questions, by Daniel Lakens PhD, Eindhoven University of Technology
  • Neural Networks for Machine Learning, Prof. Geoffrey E. Hinton, University of Toronto
  • Deep Learning, a 5-Course Specialization, Prof. Andrew Ng, deeplearning.ai and Stanford University
    • Course 1: Neural Networks and Deep Learning
    • Course 2: Improving Deep Neural Networks: Hyper-parameter tuning, Regularization and Optimization
    • Course 3: Structuring Machine Learning Projects
    • Course 4: Convolutional Neural Networks
    • Course 5: Sequence Models
  • Machine Learning, Prof. Andrew Ng, Stanford University


Selected Publications

Full list of publications can be seen at Publications

  • HP Do, Y Guo, AJ Yoon, and KS Nayak. “Accuracy, Uncertainty, and Adaptability of Automatic Myocardial ASL Segmentation using Deep CNN.” Magnetic Resonance in Medicine 2020; 83:1863–1874. PDF JRNL
  • HP Do, V Ramanan, X Qui, J Barry, GA Wright, NR Ghugre, KS Nayak. “Non-Contrast Assessment of Microvascular Integrity using Arterial Spin Labeled CMR in a Porcine Model of Acute Myocardial Infarction.” Journal of Cardiovascular Magnetic Resonance 20:45, July 2018. PDF JRNL
  • HP Do, AJ Yoon, MW Fong, F Saremi, ML Barr, KS Nayak. “Double-gated Myocardial Arterial Spin Labeled Perfusion Imaging is Robust to Heart Rate Variation.” Magnetic Resonance in Medicine 77(5):1975-1980, 2017. PDF JRNL


Selected Talks

Full list of talks can be seen at Talks

  • HP Do, et al. "Accelerated 2-3-Minute Multi-echo Ultra-short Echo Time (mecho UTE) using Conjugate Gradient SENSE (CG-SENSE) Reconstruction.” The Radiological Society of North America (RSNA) Scientific Session, Chicago, Nov 2023.
  • HP Do, et al. "Eleven-minute Comprehensive MSK Imaging Using Deep Learning Reconstruction (DLR) and Multi-echo Ultrashort Echo-Time (UTE)." The Radiological Society of North America (RSNA) Scientific Session, Chicago, Nov 2022. SLIDES-PDF
  • HP Do, et al. "dnoiseNET: Deep Convolutional Neural Network for Image Denoising." The ISMRM & SCMR Co-Provided Workshop on the Emerging Role of Machine Learning in Cardiovascular Magnetic Resonance Imaging, Seattle, Feb 2019. SLIDES-PDF
  • HP Do, et al. "Deep Convolutional Neural Network for Segmentation of Myocardial ASL Short-Axis Data: Accuracy, Uncertainty, and Adaptability." The ISMRM Workshop on Machine Learning, Part II, Washington D.C., Oct 2018. SLIDES-PDF


Teaching and Training Experience


Peer Reviewer


Membership


Interests

  • Jogging, Hiking, Nature Walk
  • Programming, Science, Technology