Can Zhao
Research Scientist at Nvidia
Summary
🤩
RockstarCan Zhao is a research scientist with nine years of experience specializing in computer vision and medical imaging, currently contributing at NVIDIA. He has deep practical expertise in building and refining ML tooling for healthcare, notably enhancing the widely used MONAI toolkit with annotation models for brain and spleen, anti-aliasing resize filters, and robust box utilities. His work on MONAI tutorials added object detection examples, evaluation metrics, DICOM support, and quality automation via pre-commit hooks, showing a focus on reproducible, production-ready research code. Comfortable spanning research and engineering, he implements model integration and data-format adaptations that bridge academic methods and clinical data constraints. Colleagues rely on him to turn complex imaging tasks into maintainable pipelines and teachable examples. Less obvious: he combines low-level image-processing care (e.g., anti-aliasing) with higher-level evaluation plumbing, which improves both model accuracy and developer ergonomics.
9 years of coding experience
Github Skills (16)
object-detection10
computer-vision10
machine-learning10
medical-imaging10
pytorch10
deep-learning10
python10
ai10
imaging10
modeling9
model-driven9
model-driven-development9
jupyter-notebook9
model-building9
dicom8
Programming languages (3)
Github contributions (5)
Project-MONAI/tutorials
Jun 2022 - Dec 2022
MONAI Tutorials
Role in this project:
ML Engineer
ML EngineerContributions:144 reviews, 13 commits, 54 PRs in 5 months
Contributions summary:Can contributed significantly to the development of object detection examples within the MONAI tutorials repository. Their work included adding and refining detection examples, integrating evaluation metrics, and incorporating pre-commit hooks for automated code formatting. They also focused on adapting the examples for different data formats, specifically adding support for DICOM images. This suggests a focus on implementing and improving object detection models using the MONAI framework.
pytorchmonai-tutorialsdeep-learningjupyter-notebookmonai
Project-MONAI/MONAI
Jun 2021 - Dec 2022
AI Toolkit for Healthcare Imaging
Role in this project:ML Engineer
ML EngineerContributions:169 reviews, 38 commits, 75 PRs in 1 year 5 months
Contributions summary:Can's contributions primarily focused on enhancing the capabilities of the MONAI toolkit for healthcare imaging. They added new functionalities related to annotation and model integration, specifically including support for brain and spleen annotation models and the addition of an anti-aliasing filter within the Resize transform. Furthermore, the user implemented a suite of box utility functions. These utility functions include operations such as converting box modes, calculating center points and distances, clipping boxes to image boundaries, and non-maximum suppression.
pytorchpythondeep-learningmedical-image-processingcomputer-vision
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.