01
Deep learning
Foundation models, efficient inference, and multimodal methods for biomedical data.
COMPUTER SCIENCE × BIOMEDICAL IMAGING
Rokunuzjahan Rudro
Building intelligent imaging systems for biomedical discovery and clinical pathology.
Explore work01 / WORK
Research at the intersection of algorithms, instruments, and medicine.
02
Hyperspectral imaging
Spectral-spatial systems that reveal tissue information beyond conventional RGB imaging.
03
Computational pathology
Machine learning pipelines designed to support reproducible, clinically meaningful tissue analysis.
04
Microscope automation
SDK-level control, autofocus, and acquisition optimization for faster digital pathology workflows.
02 / SELECTED PROJECTS
From acquisition hardware to deployable intelligence.
RESEARCH · 2026
TinyScope
Lightweight hyperspectral tissue classification with TinyML inference on a Raspberry Pi 5.
SYSTEMS · CURRENT
Automated HSI Microscopy
Python and SDK-level control for Olympus IX83 and IMEC SnapScan acquisition, including focus-map optimization.
AI · PATHOLOGY
Foundation Models for Tissue
Adapting pathology foundation features and deep learning methods to hyperspectral histopathology data.
03 / EXPERIENCE
Computer science foundations, applied to biomedical engineering.
2025 — Present
Graduate Research Assistant
University of Texas at Dallas · QBIL
Automated hyperspectral microscopy, efficient tissue classification, and computational pathology research funded through an NIH research grant.
2023 — 2025
Graduate Research Assistant · Machine Learning
University of Kansas
Machine learning for driver behavior and clinical language-model evaluation on MIMIC-III.
2024
Machine Learning Intern
AssetWorks Inc.
Conversational AI testing and an agentic data-analytics application built with Azure OpenAI and Streamlit.
04 / EDUCATION
PhD · Biomedical Engineering
University of Texas at Dallas · 2025–2029
MS · Computer Science
University of Kansas · 2023–2025
BS · Computer Science
University of Kansas · 2019–2023