Research Scientist. Ultrasound AI group.

Cambridge, MA

• AI Based Medical Ultrasound Imaging Analysis

• Develop detection and classification models for AI based lung ultrasound diagnosis.

Research intern. Advised by Dr. Reza Negahdar, Early Clinical Development Informatics (ECDi) group.

South San Francisco, CA

• Imaging and non-imaging feature fusion

• Developed a feature fusion model for improving COVID-19 classification from CTA images.
  • Fusion of imaging and non-imaging features improves COVID classification by 6.6%.
  • Grad-CAM to interpret image region importance.

Research Intern. Co-adviced by Dr. Shanhui Sun and Terrence Chen, Medical AI group

Boston, MA

• Landmark tracking for stent enhancement

• • Developed a marker detector with 95% recall / 50% precision / 44 frames per second.
  • Robust marker tracking using graph search with 0.36mm mean distance with manual labels.

Research Assistant. Co-adviced by Prof. Chun Yuan and Prof. Jenq-Neng Hwang

Seattle, WA

• Quantitative intracranial artery modeling and vascular feature extraction

• • Developed iCafe (C++ software, 60k C++ lines) for intracranial artery tracing and labeling.
  • A novel artery refinement algorithm through optimization on Curved Planar Reformation view.
  • A novel artery naming algorithm using Graph Neural Network and hierarchical refinement.
  • Created a database of 1000+ scans of cerebral vasculature models.
  • iCafe used by 12+ sites on dozens of medical research studies (aging, dementia, artery revascularization, etc.).
  • Three first-author journal papers (1,2,3) and seven conference publications ranging from technical development, validation and medical applications.
  • Editor's pick by Magnetic Resonance in Medicine.

• Fully automated vessel wall segmentation and quantification

• • 3D region of interest identification using object tracking (Yolo V2 detector and tracklet refinement).
  • A novel vessel wall segmentation algorithm in polar coordinate system using deep learning (paper)
  • Transfer learning and active learning techniques for adaptation to multiple vascular beds.
  • Validated on 48k popliteal arteries (paper). Workload of 70 years for expert human reader.
  • Winner for American Heart Association/Amazon Web Services Prize Competition.

• Carotid atherosclerotic lesion screening for high risk population

• • A 5-minute MR screening workflow using deep learning for cardiovascular risk assessments.
  • Modules include fast imaging, image quality assessment, artery detection, and lesion classification.
  • Assist radiologists by warning potential locations of advance lesions visualized in 3D view.
  • High agreements with expert radiologist (0.9+ sensitivity/specificity).
  • Effective in reducing manual review time for both experts and novice radiologists in clinical reading.

Undergraduate Researcher, Project leader, Adviced by Dr. Huiliang Shang and Dr. Yi Guo

Shanghai, China

• Modernizing Traditional Chinese Medicine diagnosis methods

• • Created or improved algorithms in tongue image analysis and data-mining of prescriptions.
  • 4 related publications (1,2,3,4) as leading authors.

• Capstone research: Vascular image registration by circuit simulation

• • A novel algorithm to represent vasculatures as circuits for robust matching. (paper)
  • Best undergraduate thesis in Fudan University.

2018

Outstanding Research Award, OCSMRM

2015

Mathematical Contest in Modeling 2015 (Meritorious Winner, top 10%)

2009-2015

Six consecutive years of Shu Ping Scholarship(top 3%)

2013-2014

Two consecutive years of Fudan university scholarship(top 15%)