Open Source Software for Medical Imaging

Medical imaging requires an enormous amount of expert knowledge in signal processing, image reconstruction and image processing. At our institute we develop imaging algorithms using the open source scientific programming language Julia and make them available via the collaborative version control platform GitHub under the MIT license. This enables the documentation of scientific methodology and ensures the reproducibility of our own research contributions. Furthermore, even scientists with only rudimentary knowledge of medical imaging are enabled to use state-of-the-art image reconstruction methods. We are happy about any feedback / suggestions that can be send by email to us. Improvements and amendments can be also directly made on GitHub.

All MPI related projects are collected in the organization https://github.com/MagneticParticleImaging, while the institute's contributions to MRI are collected in the organization https://github.com/MagneticResonanceImaging. Projects, which cannot be assigned clearly to an imaging method, are maintained under the account of Tobias Knopp, where our main contributions are:

Magnetic Particle Imaging
Magnetic Resonance Imaging
Further Projects

Publications

[191962]
Title: TrainingPhantoms.jl: Simple and Versatile Image Phantom Generation.
Written by: P. Jürß, C. Droigk, M. Boberg, and T. Knopp
in: <em>International Journal on Magnetic Particle Imaging</em>. Mar (2025).
Volume: <strong>11</strong>. Number: (1 Suppl 1),
on pages: 1-2
Chapter:
Editor:
Publisher:
Series:
Address:
Edition:
ISBN:
how published:
Organization:
School:
Institution:
Type:
DOI: https://doi.org/10.18416/IJMPI.2025.2503031
URL: https://www.journal.iwmpi.org/index.php/iwmpi/article/view/802
ARXIVID:
PMID:

[www]

Note: inproceedings, opensoftware, generalsoftware

Abstract: Large collections of labeled data play a crucial role in supervised machine learning projects. Unfortunately, such datasets are quite rare in the medical domain. In this work, the Julia project TrainingPhantoms.jl is introduced, which provides a simple interface to generate large and diverse collections of randomly generated image phantoms. The proposed phantom generator has been successfully used to train an image quality enhancement network that managed to generalize to unseen experimental out-of-distribution data.