Calibrating
000
Portfolio / v4 · Rev 26.04 Dartmouth · Hanover NH

Roya
Parsa.

Computational scientist building machine learning for medicine — currently at Dartmouth's Hassanpour Lab, where I work on medical imaging, diagnostic systems, and the quieter question of what ethical AI in healthcare is actually supposed to look like.
StatusOpen to 2026 roles · research, bio info & swe
StudyingMS Computer Science · Dartmouth
PriorBS CS + Stats · Adelphi · Honors
FocusML · medical imaging · ethics
DrinksMatcha, mostly ceremonial
§ 01  ·  Profile

Somewhere between a research lab and a code editor.

I'm a graduate researcher at Dartmouth, advised inside the Hassanpour Lab — a group that builds machine learning tools for digital pathology, medical imaging, and clinical text. My days drift between PyTorch notebooks, ethics discussions, and long conversations with clinicians about what a model is actually being asked to see.

Before Dartmouth, I finished a CS degree with a Statistics minor at Adelphi, where my senior thesis — done with the New York Proton Center — looked at improving proton stopping power estimation for pediatric cancer therapy using dual-energy CT. That project is the reason I care about the weird little seams between numbers, bodies, and the clinicians reading them.

I like clean pipelines, well-commented code, and software that refuses to be dishonest about its uncertainty. I also like matcha, russian literature, and escaping into the woods whenever possible.

§ 02  ·  Research & Work

A short ledger of places that let me touch the data.

2025 — Now

Graduate Researcher, Hassanpour Lab

Dartmouth College · Geisel School of Medicine
Developing ML methods at the intersection of medical imaging and computational pathology — with the Center for Precision Health & AI. Focused on multi-modal models that are interpretable by the people actually reading charts.
2026 — Now

Teaching Assistant, Computer Science

Dartmouth College · Department of Computer Science
Guiding students through coursework and office hours. Helping them debug Graphical ML.
2024 — 2025

Student Researcher, Proton Therapy

New York Proton Center
Improved accuracy of proton stopping power estimation using dual-energy CT models for pediatric cancer treatment planning. Advised by Dr. Sixia Chen; awarded the Honors College Summer Research Fellowship to pursue the work full-time.
2023 — 2024

Teaching Assistant · CS/Stats

Adelphi University
Led labs and office hours for too many courses across CS and Stats.
2022 — 2024

Undergraduate Researcher · CT & Imaging

Adelphi CS · with Dr. Sixia Chen
First tasted ML-for-medicine as an undergrad doing my senior thesis — building preprocessing and evaluation pipelines for CT data, which is where the appetite for this whole field came from.
§ 03  ·  Selected Specimens

Things I've built, mostly for science, occasionally for fun.

№ 001 / LIVE
Medical Imaging · Research

NYPC — DCT Analysis

Frontend and analysis layer for a dual-energy CT pipeline built with the New York Proton Center. The tool lets medical physicists inspect reconstructions, compare stopping-power estimates, and feed the results back into treatment planning — without leaving the browser.

React · Python · CT reconstruction repository →
№ 002
AI Agent · CLI

simpleCoder

A ReAct-style AI coding assistant that lives in the terminal. Built with semantic RAG for codebase navigation, automated task planning, and strict file-permission guardrails—because AI tools should write code, not quietly overwrite your directories. Basically, a pocket-sized software engineer.

№ 003
Medical AI · Fairness

Fairness in Skin Models

An audit of skin lesion classifiers to determine if they learn genuine pathology or merely exploit dataset artifacts like clinical markings and demographic features. By systematically removing confounders and applying GradCAM, this project exposes what models are actually looking at—ensuring they diagnose the condition, not the photo.

PyTorch · GradCAM in progress...
Currently ·  LIVE

Reading

Notes from the Underground

Working on

A multi-modal imaging paper

Listening

T-Swift, endlessly

Matcha count · ytd

limt → ∞ Matcha(t) = ∞
§ 04  ·  Contact

Collaborations, questions, and book recs.

Let's build
something honest.