Brian Anderson
Assistant Professor at UC San Diego
San Diego, California, United States
Summary
👤
Senior🎓
Top SchoolBrian Anderson is an assistant professor and medical physicist with eight years of experience bridging clinical care, academic research, and machine learning for radiation oncology. Trained at MD Anderson and UC San Diego, he progressed from graduate and residency roles to faculty appointments, developing autocontouring and segmentation tools that translate imaging research into treatment-planning workflows. He contributes ML engineering expertise to open-source projects—notably refining a Keras implementation of DeepLab v3+ for semantic segmentation—demonstrating a knack for making advanced models robust and Keras-compatible. Based in San Diego, he blends nuclear engineering fundamentals with practical clinical commissioning experience, and his GitHub reflects a focus on reproducible, deployable code that supports clinical translation.
9 years of coding experience
9 years of employment as a software developer
University of California, San DiegoBachelor of Science, Nuclear Engineering, 3.61, Bachelor of Science, Nuclear Engineering, 3.61 at Georgia Institute of TechnologyDoctor of Philosophy - PhD, Medical Physics, Doctor of Philosophy - PhD, Medical Physics at The University of Texas MD Anderson Cancer Center UTHealth Graduate School of Biomedical Sciences
Stackoverflow
466reputation
119kreached
13answers
0questions
Github Skills (13)
semantic-segmentation10
keras10
computer-vision10
machine-learning10
deep-learning10
tensorflow10
python9
faster-rcnn8
mask-rcnn8
python-poetry6
macos-big-sur6
pyenv6
scikit-learn6
Programming languages (4)
Github contributions (5)
bonlime/keras-deeplab-v3-plus
Mar 2020 - Apr 2020
Keras implementation of Deeplab v3+ with pretrained weights
Role in this project:
ML Engineer
ML EngineerContributions:30 commits, 7 PRs, 5 comments in 1 month
Contributions summary:Brian primarily focused on updating and refining a Keras implementation of Deeplab v3+ for semantic image segmentation. Their contributions involved refactoring the model to be fully compatible with Keras, addressing issues related to resizing and activations. The user's commits reflect an effort to improve model performance and stability within the Keras framework.
deeplabkeras
brianmanderson/RegisteringImages
Nov 2020 - Aug 2022
Tools for registering images with Dicom Registration files
Contributions:16 commits, 16 pushes, 1 branch in 1 year 9 months
dicomucsd-catalog
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.