Andriy Myronenko
Sr. Research Scientist at NVIDIA
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolAndriy Myronenko is a senior research scientist in San Francisco with eight years of focused experience building state-of-the-art deep learning solutions for medical imaging, currently at NVIDIA after a long tenure developing clinical and treatment-guidance algorithms at Accuray. He specializes in 3D tumor and organ segmentation from MRI/CT/PET, 2D pathology classification, and performance-optimized models intended for clinical deployment. Andriy combines rigorous academic training (PhD in computer vision and medical imaging) with hands-on engineering—contributing performance improvements and robust Dice-based metrics to the widely used MONAI toolkit. He is driven by both accuracy and speed, routinely tackling MICCAI segmentation challenges to push boundaries, and brings practical experience turning research into tools that assist radiologists and researchers in practice.
8 years of coding experience
8 years of employment as a software developer
PhD, Computer Vision, Medical Imaging, AI, PhD, Computer Vision, Medical Imaging, AI at Oregon Health & Science University
Github Skills (8)
pytorch10
machine-learning10
deep-learning10
python10
medical-image-processing10
faster-rcnn8
mask-rcnn8
data-analysis7
Programming languages (5)
Github contributions (5)
Project-MONAI/MONAI
Jun 2020 - Dec 2022
AI Toolkit for Healthcare Imaging
Role in this project:
ML Engineer
ML EngineerContributions:204 reviews, 35 commits, 66 PRs in 2 years 6 months
Contributions summary:Andriy primarily focused on improving the `monai` library's machine learning capabilities. Their contributions involved significant code refactoring, specifically optimizing the `one_hot()` function for GPU performance using `scatter_`, and adding and cleaning up the Dice loss function, along with incorporating a MaskedDiceLoss. The user added a new DiceMetric class based on the compute_meandice function, accounting for NaN values, to improve the library's metrics for segmentation tasks, including the addition of a deep supervision loss wrapper class and updating the Gaussian map calculation for sliding window inference.
pytorchpythondeep-learningmedical-image-processingcomputer-vision
myron/tutorials
Nov 2021 - Feb 2024
MONAI Tutorials
Contributions:43 pushes, 11 branches in 2 years 3 months
deep-learningmonaimonai-tutorials
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.