Brian Avants
Visiting Associate Professor
Portsmouth, New Hampshire, United States
Summary
🤩
Rockstar🎓
Top SchoolBrian Avants is a Visiting Associate Professor and seasoned computational imaging scientist with 24 years of experience bridging academic research and industry-driven machine learning for clinical trials. He led integrative imaging analytics across large cohorts (ADNI, UK Biobank) and directed ML at Invicro to deliver cross-disease, multi-species clinical trial software, while contributing foundational registration methods (SyN) and extending ANTs/ITK toolchains. His deep systems-level expertise in C++ and Python is evident in substantial open-source work refactoring ANTsPy and enhancing ITK—modernizing image transforms, I/O, and high-dimensional optimizers. Based in Portsmouth, NH, he combines rigorous mathematical foundations developed at ICERM and Penn with practical trial-stage impact (Biogen Aducanumab programs), making him fluent in both algorithmic innovation and production-grade imaging pipelines.
24 years of coding experience
18 years of employment as a software developer
Doctor of Philosophy - PhD, Doctor of Philosophy - PhD at University of PennsylvaniaNew College of Florida
Github Skills (16)
itk10
image-analysis10
medical-imaging10
open-source10
c-language10
cpp10
cprogramming-language10
image-processing10
scientific-computing10
neuroimaging9
data-structure9
datastructures-algorithms9
algorithm9
data-structures9
algorithms9
Programming languages (12)
Github contributions (5)
ANTsX/ANTsPy
Aug 2017 - Jan 2023
A fast medical imaging analysis library in Python with algorithms for registration, segmentation, and more.
Role in this project:
Back-end Developer & Data Scientist
Back-end Developer & Data ScientistContributions:5 releases, 3 reviews, 389 commits in 5 years 5 months
Contributions summary:Brian primarily focused on refactoring and updating the medical imaging analysis library, antsPy, to align with ITK v5 style, removing dependencies on VTK. Their contributions involved modifying C++ code, particularly within the ants/lib directory, to incorporate the new style and manage transformation parameters and image manipulations. Furthermore, the user made changes related to image header information and pixel type handling. This work involved deep knowledge of medical imaging data formats and image transformations.
imagingpythonsegmentationmedical-imagingneuroimaging
InsightSoftwareConsortium/ITK
Apr 2002 - Jun 2018
Insight Toolkit (ITK) -- Official Repository. ITK builds on a proven, spatially-oriented architecture for processing, segmentation, and registration of scientific images in two, three, or more dimensions.
Role in this project:Back-end Developer
Back-end DeveloperContributions:349 commits, 2 PRs, 5 comments in 16 years 4 months
Contributions summary:Brian's contributions primarily involve enhancing the ITK (Insight Toolkit) codebase through the addition of new metrics for high-dimensional optimizers, and modifications to existing classes. Their work includes refactoring and renaming existing classes like `DeformationFieldTransform` and related components. The user also addresses and resolves bugs, adds new I/O types (nrrd), and makes minor changes to existing code, such as fixing Jacobian calculations with respect to parameters.
itksegmentationinsight-toolkitimage-analysismedical-imaging
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.