Patents & Translational Work
Four U.S. patents translating the research into deployable clinical ML systems.
My research is built to ship. Four U.S. patents cover the core methods:
- US12154354B2: System and Method for Labeling Ultrasound Data (granted 2024).
- US20240177000A1: System and Method for Training Machine-Learning Models with Probabilistic Confidence Labels.
- US20240177445A1: System and Method for Direct Diagnostic and Prognostic Semantic Segmentation of Images.
- US20240249498A1: System, Method, and Computer Program Product for Extracting Features from Imaging Biomarkers with ML Models.
Supporting translational grants and fellowships:
- Liang Zhao Endowed Fellowship, CMU (2025)
- CMLH Translational Fellowship in Digital Health, CMU (2022)
- NSF XSEDE Compute Grant, 130,500 GPU hours (2020)
- Neocortex EUP Compute Award, NSF PSC (2020)
Earlier industry work: 3 years as Senior Data Scientist & Software Engineer at Sling Media (Dish Networks), building the analytics pipeline for user-churn modeling and shipping a 20% startup-time improvement to the AirTV Player Android app; computer vision research internship at DawnLight Inc. (2021) on efficient multimodal (RGB + IR) action recognition for clinical monitoring.