Carlos Parra

Translational Imaging Data Scientist and PhD Biomedical Engineer with 15+ years of experience developing imaging biomarkers, AI/ML-enabled analytics, and reproducible clinical data infrastructure across oncology, ophthalmology, neurodegeneration, and pediatric disease. Expertise spans MRI, CT, PET, OCT, fMRI, DTI/DKI, ASL, MRS, DCE-MRI, visual function, longitudinal clinical outcomes, and tumor imaging, including pediatric oncology at St. Jude, thyroid cancer imaging at MSK, and neurodegeneration imaging biomarkers at NYU Langone.

Experienced translating complex imaging and clinical datasets into biomarker strategies, disease models, patient-stratification concepts, and endpoint-oriented workflows for translational R&D. Strong record building SOP-driven pipelines, automated QA/QC, cross-study harmonization, analysis-ready datasets, and regulatory-aware workflows. Positioned to support pharma and MedTech R&D teams developing scalable imaging data products, biomarker strategies, clinical endpoint workflows, and therapeutic-area decision support.

Independent Consulting — Translational Imaging & Digital Biomarkers

Self-employed | New York, NY | 2023–Present

Advise on translational imaging, digital biomarker concepts, and multimodal clinical data strategies, aligning biomarker hypotheses, endpoint concepts, QC methods, and validation.

Apply signal processing, feature extraction, and signal-quality reasoning to imaging, clinical outcomes, and multimodal biomedical data projects.

Develop reproducible workflows and evidence-generation approaches supporting clinical measurement, analytical validation, and translational R&D decisions.

Research Scientist & Postdoctoral Fellow — Translational Neuroimaging

New York University Grossman School of Medicine | New York, NY | 2016–2023

Led glaucoma-neurodegeneration programs integrating MRI, OCT, perimetry, and clinical data to identify disease mechanisms, biomarkers, and progression markers.

Developed endpoint-oriented workflows linking retinal structure, visual function, cortical activity, brain microstructure, metabolism, perfusion, and CSF/glymphatic dynamics.

Built SOP-driven imaging pipelines, QC methods, and reproducible analysis infrastructure enabling scalable operations, data integrity, and cross-study consistency.

Research Scholar — Quantitative Imaging

Memorial Sloan Kettering Cancer Center | New York, NY | 2015–2016

Re-engineered MATLAB-based DCE-MRI/IVIM biomarker platform for thyroid tumor imaging, improving convergence, robustness, reproducibility, and speed.

Improved quantitative imaging workflow speed and precision by ~70%, accelerating translational tumor biomarker analysis and clinical research interpretation.

Collaborated with clinical teams to standardize imaging analytics workflows; co-authored MRI Clinics of North America review on head and neck quantitative imaging biomarkers.

Doctoral Researcher & Diagnostic Imaging Fellow — Pediatric Oncology

St. Jude Children’s Research Hospital | Memphis, TN | 2009–2015

Pioneered retinoblastoma visual-outcome research integrating retinal tumor localization, functional neuroimaging, epidemiology, and clinical outcome prediction.

Developed predictive models linking retinal tumor burden/location to visual cortex response, visual potential, and clinically meaningful functional outcomes.

Led pediatric oncology imaging collaborations across retinoblastoma, medulloblastoma, and glioma studies, integrating MRI markers, clinical data, and outcomes analytics.

Developed AI-driven organ segmentation and image-quality metrics for pediatric CT, supporting dose-reduction protocols while preserving diagnostic utility.

Introduced spatiotemporal and epidemiologic tumor-pattern modeling to distinguish disease biology from developmental and care-access factors, leveraging data-driven disease modeling.

PhD Biomedical Engineering | U. of Memphis & St. Jude Children’s Research Hospital | 2015
MSc Electrical Engineering | U. of Memphis & St. Jude Children’s Research Hospital | 2008