Amalie Shi
About Me
Amalie Shi is a software engineer specializing in healthcare informatics and automation systems. Her work focuses on modernizing healthcare imaging verification through the integration of Python-based automation frameworks, data pipelining, and human-centered design.
She holds a Master’s degree in Biomedical Engineering from Johns Hopkins University and a Bachelor’s degree in Biomedical Engineering from the Georgia Institute of Technology.
Amalie’s professional interests include software architecture, data engineering, and the application of automation to improve compliance, interoperability, and efficiency in clinical systems.
She is a certified Project Management Professional (PMP), Engineer in Training (EIT), ISTQB Certified Test Automation Engineer (CTAL-TAE), and ASQ Certified Six Sigma Yellow Belt (CSSYB).
Research Experience
Amalie’s research background bridges engineering and medicine through advanced imaging, computation, and system design. Her previous work includes:
- Implantable Device Design Improvement (animal model studies)
- Peripheral Nerve Injury Kinesiology using feline models
- Myocarditis and Immune Cell Clustering in cardiac tissues
- Wearable Sensing Systems for monitoring medication adherence
These projects reflect her passion for developing technologies that enhance clinical workflows, diagnostic accuracy, and patient safety.
Publications
Performance Assessment of Texture Reproduction in High-Resolution CT
Hui Shi, Grace J. Gang, Junyuan Li, Elena Liapi, Craig Abbey, J. Webster Stayman
PMID: 33162640 | PMCID: PMC7643885 | DOI: 10.1117/12.2550579
View on PubMed
The Use of 3D-Printed Phantoms for Evaluating CT Image Quality
Hui Shi
Master’s Research Thesis, Johns Hopkins University
Read Thesis
The Use of Implanted Intramuscular FES System for Ameliorating Foot Drop During Locomotion
Hui Shi
Undergraduate Research Thesis, Georgia Institute of Technology
Read Thesis
Technical Projects and Presentations
Automate the UI Software Using Python
Amalie Shi
Verifying performance and safety is critical but has long been a bottleneck in the medical software release process. UI software testing—being the most integrated and complex component—has traditionally been performed manually.
This project presents a unique, readable, and maintainable test automation method applied in medical imaging using Python. It leverages Python libraries to emulate user interactions with the UI, communicate with external web APIs, validate test data, record test evidence, and generate automated test reports.
The automation solution enhances testing efficiency, ensures consistency in regression testing, reduces human error, and strengthens the software development lifecycle.
Read on Zenodo
Watch Presentation on YouTube
UI Software Testing Framework
Amalie Shi
Developed an automated UI software testing framework designed for medical imaging applications. The framework was presented at RSLondon Southeast, held at Imperial College London, and was awarded Best Poster Award.
Academic Projects
Computational Models of Hippocampal Cells
Developed computational models to study neuron firing patterns and hippocampal dynamics.
PK/PD Models and Analysis of the Combination Treatment for Malaria
Designed pharmacokinetic/pharmacodynamic models to analyze drug synergy for malaria treatment.
R21 Grant Proposal: Leaky Wrist Motor Control
Drafted a mock NIH R21 grant proposal for a computational motor control project, emphasizing signal feedback and neural modeling.
Positive Feedback Control in Neural Systems
Hui Shi
Presented at the Society for Neuroscience (SfN) annual meeting.
View Abstract
In-vitro Effects of 1,2,3,4,6-penta-O-galloyl-beta-D-glucose on NF-κB Activation Levels in Human Glioblastoma Cells
Hui Shi
Research proposal and poster analyzing NF-κB pathway inhibition in glioblastoma cells.
View Poster
Induction of Autophagy upon Starvation
Analyzed cellular responses to nutrient deprivation and autophagy induction mechanisms.
Pioneer Articles Summary
Summarized key findings from pioneering research in biomedical imaging and computational physiology.
Contact
For inquiries, collaborations, or professional opportunities, please reach out via LinkedIn or GitHub.