cv

Research Technician II

Mallinckrodt Institute of Radiology

I built Deep Neural Nets to classify pathology using a type of diffusion MRI called Diffusion Basis Spectrum Imaging under the supervision of Prof Sheng-kwei Song

• Diffusion Basis Spectrum Imaging
• MRI
• Machine Learning
• Multiple Sclerosis
• glioblastoma
• prostate cancer

Teachers Assistant

Washington University in St. Louis|McKelvey School of Engineering

TAed for multiple courses including Engineering Ethics and Sustainability, Data Structures, Introduction to Artificial Intelligence, Quantitative Physiology, Introduction to Biomedical Engineering. Lectured Engineering Ethics and Sustainability.

• Engineering ethics
• Artificial intelligence
• Data Structures
• Quantitative Physiology
• Small group discussion
• Lecturing

Medical Student Assistant Teacher

University of California, Irvine School of Medicine

I run teaching sessions for first year medical students

• Teaching
• Medical School
• Physiology
• Histology
• Biostatistics

Graduate Researcher, Teaching Assistant

University of California, Irvine Department of Computer Science

I perform research in medical image analysis and currently am TAing CS 284A: AI in Biology and Medicine

• Medical Image Analysis
• Teaching

Patient Care Technician

Barnes-Jewish Hospital|Cardiothoracic Stepdown Unit

Performed phlebotomies, EKGs, foley care, chlorohexidine treatments, CPR, LVAD and chest tube care and transport of patients. Obtained vital signs (including manual and doppler blood pressures), blood glucose, and cardiac telemetry data from patients.

• Patient care

PLACEHOLDER

PLACEHOLDER

PLACEHOLDER

• PLACEHOLDER
• PLACEHOLDER

Peer Reviewer for Journal of Digital Imaging

Society for Imaging Informatics in Medicine

I review articles related to machine learning and artificial intelligence as applied to medical imaging

• reviewer
• imaging

PhD

University of California, Irvine

Computer Science

MD

University of California, Irvine School of Medicine

Medicine

BS, BS

Washington University in St. Louis

Major in Biomedical Engineering, Major in Computer Science

Graduation Honors: Honors Thesis in Computer Science and Engineering

Washington University in St. Louis

Modular Neural Network and clustering using Diffusion Basis Spectrum Imaging (DBSI) improves Prostate Cancer Grading

Latin Honors: Summa Cum Laude in Biomedical Engineering

Washington University in St. Louis

Top 10% of class

Honors Society: Alpha Eta Mu Beta Inductee

Alpha Eta Mu Beta

National Biomedical Engineering Honors Society

Honors Society: Tau Beta Pi Inductee

Tau Beta Pi (Gamma Chapter)

Tau Beta Pi is the oldest pan-engineering honor society and the second oldest collegiate honor society in the United States.

Scholarship: Christie Foundation Health Education

Christie Foundation

Each year, the Christie Foundation awards over $100,000 to students pursuing degrees in the medical field through their Health Education Scholarship program.

Scholarship: Stanley C. Pace Endowed Scholarship

Stanley C. Pace, Washington University in St. Louis

Named Scholars in Engineering Program. I thank Mr. Pace for his service to our country, for believing in my future and for helping me fund my education at WashU. I will always remember his generosity and continue to work hard for him and everyone else who believes in me. May he rest in peace.

Placeholder

Placeholder

Placeholder

Deep learning with diffusion basis spectrum imaging for classification of multiple sclerosis lesions

Annals of Clinical and Translational Neurology

Multiple sclerosis (MS) lesions are heterogeneous with regard to inflammation, demyelination, axonal injury, and neuronal loss. We previously developed a diffusion basis spectrum imaging (DBSI) technique to better address MS lesion heterogeneity. We hypothesized that the profiles of multiple DBSI metrics can identify lesion-defining patterns. Here we test this hypothesis by combining a deep learning algorithm using deep neural network (DNN) with DBSI and other imaging methods.

Diffusion Histology Imaging Combining Diffusion Basis Spectrum Imaging (DBSI) and Machine Learning Improves Detection and Classification of Glioblastoma Pathology

Clinical Cancer Research

Glioblastoma (GBM) is one of the deadliest cancers with no cure. While conventional MRI has been widely adopted to examine GBM clinically, accurate neuroimaging assessment of tumor histopathology for improved diagnosis, surgical planning, and treatment evaluation remains an unmet need in the clinical management of GBMs. We employ a novel diffusion histology imaging (DHI) approach, combining diffusion basis spectrum imaging (DBSI) and machine learning, to detect, differentiate, and quantify areas of high cellularity, tumor necrosis, and tumor infiltration in GBM

Diffusion histology imaging differentiates distinct pediatric brain tumor histology

Scientific Reports

High-grade pediatric brain tumors have the highest mortality rates among children. Conventional MRI is commonly used for clinical examination, but accurately detecting and distinguishing tumor types remains a challenge. We introduced a novel approach called Diffusion Histology Imaging (DHI) using diffusion basis spectrum imaging (DBSI) metrics to train a deep neural network. DHI aims to identify and quantify different tumor components such as normal white matter, dense and less dense tumor regions, infiltrating edges, necrosis, and hemorrhage. By combining DBSI metrics and deep learning, we achieved an 85.8% accuracy in classifying pediatric tumor histology.