Adrian Dalca
Assistant Professor at Harvard Medical School
Cambridge, Massachusetts, United States
Summary
🤩
Rockstar🎓
Top SchoolAdrian Dalca is an Assistant Professor at Harvard Medical School and Research Scientist at CSAIL, MIT, with 13 years of experience applying probabilistic machine learning and computer vision to medical image analysis. Trained at MIT (PhD) and University of Toronto, he builds practical deep learning tools—such as contributions to the widely used VoxelMorph image-registration library—that translate cutting-edge research into clinical workflows. His work spans unsupervised and generative models for linking genotypes and records to medical images, and novel population-based methods that “borrow” tiny shared anatomy to improve clinical imaging. Comfortable moving between theory, software engineering, and deployment, he is driven by curiosity about atypical directions that open new analyses and real-world clinical impact.
13 years of coding experience
10 years of employment as a software developer
S.M., Computer Science (Machine Learning, Computer Vision, Medical Image Analysis), S.M., Computer Science (Machine Learning, Computer Vision, Medical Image Analysis) at Massachusetts Institute of TechnologyB.Sc, Computer Science, B.Sc, Computer Science at University of Toronto
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (7)
keras10
machine-learning10
unsupervised-learning10
deep-learning10
tensorflow10
python10
image-registration10
Programming languages (8)
Github contributions (5)
voxelmorph/voxelmorph
May 2018 - Jan 2023
Unsupervised Learning for Image Registration
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:2 reviews, 239 commits, 57 PRs in 4 years 8 months
Contributions summary:Adrian primarily contributed by moving code from the "balakg" repository, indicating knowledge transfer and potential refactoring. They implemented and modified a 3D spatial transformer using Keras layers and TensorFlow, essential for image registration. Furthermore, the user added and modified training and testing files related to MICCAI network, which suggests involvement in machine learning model development and deployment. The user demonstrated the ability to develop and utilize deep learning tools and understand concepts like diffeomorphisms for registration.
pytorchunsupervised-learningdeep-learningunsupervisedoptical-flow
adalca/medical-datasets
Feb 2019 - Oct 2022
tracking medical datasets, with a focus on medical imaging
Contributions:1 review, 91 commits, 13 PRs in 3 years 7 months
medical-datasetsmedical-image-processingdatasetmriimaging
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.