Experience
Postdoctoral Researcher
- Developing sovereign AI and digital twin technologies for trustworthy, locally governed neurological and surgical applications.
- Developing cross-modality generative AI to synthesize amyloid PET from structural MRI, enabling amyloid-burden estimation without PET while safeguarding against false-positive signals in healthy populations.
- Developing a self-supervised foundation model for resting-state fMRI to learn healthy brain dynamics as a baseline for clinical perturbation analysis and digital twin modeling.
- Building real-time computer vision for DaVinci robotic-assisted gynecologic surgery, integrating object detection, promptable segmentation, visibility-aware tracking, and safety mechanisms under occlusion.
Graduate Research Assistant
- Developed image-processing and deep-learning methods for amyloid PET quantification in Alzheimer's disease.
- Built MRI-assisted and MRI-less deep-learning segmentation pipelines, demonstrating quantitative equivalence to FreeSurfer across multi-site cohorts.
- Developed tracer characteristic-based co-registration for simultaneous PET/MR motion correction and a PET biomarker for MCI-to-AD progression prediction.
- Performed Centiloid calibration, equivalence testing, ROC analysis, and bootstrap validation while collaborating across nuclear medicine, radiology, neurology, and computer science.
Education
Ph.D. in Biomedical Engineering
GPA: 3.85/4.0
Dissertation: "Optimizing Quantification in Alzheimer's Disease with PET Imaging through Advanced Imaging and Deep Learning Techniques"
B.S. in Biomedical Engineering
GPA: 3.76/4.30 (Upper Division: 3.86/4.30)
Technical Skills
Click a chip to jump to evidence
Deep Learning
Medical Imaging Processing
Medical Imaging Tools
Research & Publications
"Classification of tau status with machine learning models in amyloid-positive cohorts"
Machine-learning surrogate for tau-PET status using MRI and amyloid PET across ADNI, OASIS-3, and SCAN cohorts (AUC 0.92).
"Amyloid PET quantification with deep learning segmentation models without MRI"
MRI-less amyloid PET quantification using synthetic CT, with quantitative equivalence and external PET/CT validation.
"Motion correction of simultaneous brain PET/MR images based on tracer uptake characteristics"
Tracer characteristic-based co-registration that reduces PET/MR misalignment and improves quantification and lesion detectability.
"Prediction of MCI-to-AD progression with atrophy-weighted standard uptake value ratios of ¹⁸F-Florbetapir PET"
Atrophy-weighted SUVR combining amyloid uptake and hippocampal volume to predict MCI-to-AD progression.
Under Review
"Deep learning MR-based segmentation approach for amyloid PET quantification"
MR-based deep-learning brain segmentation for amyloid PET quantification.
In Preparation
"Accelerated tau deposition is associated with COVID infection in the ADNI cohort"
"Evaluating the association between cerebral atrophy and tau deposition in amyloid-positive individuals across the Alzheimer's disease continuum"
"A simplified scoring system for MCI-to-AD conversion prediction based on Centiloid and cognitive tests"
Poster Presentations
"Evaluation of Deep Learning Models for Brain Parcellation in Neuroimaging of Alzheimer's Disease"
Conference poster on DL parcellation for AD neuroimaging.
"Volumetric Brain Tumor Segmentation in High-Grade Glioma Using a Semi-Automated Workflow"
Semi-automated volumetric brain-tumor segmentation workflow for high-grade glioma.
"Correction for Involuntary Motion of Simultaneous PET/MR Brain Scans Based on Regional Tracer Characteristics"
Early TCBC presentation at SNMMI.
"Development of an Extension Framework to Enable Deep Learning-Based Image Processing and Analysis with Cloud Computing for Open-Source Imaging Software"
Cloud DL tooling for open-source imaging workflows.