Jakob Wasserthal
Research Scientist at Universitätsspital Basel (USB)
Basel, Basel-City, Switzerland
Summary
🤩
Rockstar🎓
Top SchoolJakob Wasserthal is a research scientist in Basel with 11 years of experience building deep learning solutions for medical image analysis, currently developing production-ready models and pipelines at Universitätsspital Basel. He combines a strong research background from a PhD at DKFZ with practical engineering—contributions to widely used open-source projects like TotalSegmentator and MITK show he bridges model development, MLOps, and backend systems. His work spans algorithmic innovation (diffusion imaging, nnUNet integration) to robust engineering practices (multithreaded I/O, package setup, and comprehensive testing for batch generators). Colleagues rely on him for turning complex imaging requirements into reproducible, deployable tools that support clinical workflows.
10 years of coding experience
4 years of employment as a software developer
Master of Science, Computer Science, Master of Science, Computer Science at Universität Passau
Github Skills (21)
unit-testing10
c-language10
python10
machine-learning10
resampling10
numpy10
image-segmentation10
segmentation10
nifti10
medical-imaging10
cprogramming-language10
cpp-library9
multithreading9
data-augmentation8
github-ci7
Programming languages (4)
Github contributions (5)
wasserth/TotalSegmentator
Jan 2022 - Jan 2023
Tool for robust segmentation of >100 important anatomical structures in CT and MR images
Role in this project:
Back-end & MLOps Engineer
Back-end & MLOps EngineerContributions:8 releases, 195 commits, 31 PRs in 1 year
Contributions summary:Jakob primarily contributed to setting up the foundational structure of the project, including package setup and initial code for the nnUNet integration. They implemented code for predicting segmentations using nnUNet, and added supporting code for alignment and pre-processing. The user incorporated the capability to download and install pre-trained weights and added functionality for preview image generation. The user also added code to calculate statistics, include radiomics features, and made multithreaded saving possible.
ct-imagesimportantsegmentation
MIC-DKFZ/batchgenerators
Mar 2017 - Jan 2021
A framework for data augmentation for 2D and 3D image classification and segmentation
Role in this project:QA Engineer / Test Automation Engineer
QA Engineer / Test Automation EngineerContributions:44 commits, 4 comments in 3 years 10 months
Contributions summary:Jakob primarily contributed to the testing framework of the project. The commits focused on implementing unit tests for batch generator functionalities, specifically verifying the correct number of batches and the reproducibility of multithreaded generators. The user also added and refined test cases, demonstrating a focus on ensuring the reliability and correctness of the data augmentation framework.
classificationdata-augmentationdeep-learningcomputer-vision3d-image
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.