AI in motion: the impact of data augmentation strategies on mitigating MRI motion artifacts
Question Motion artifacts negatively impact the performance of diagnostic AI models for MRI, but mitigation methods remain largely unexplored. Findings Domain-specific augmentation during training can improve the robustness and performance of a model for quantifying lower limb alignment in the presence of severe artifacts. Clinical relevance Excellent robustness and accuracy are crucial for deploying diagnostic AI models in clinical practice. Including domain knowledge in model training can benefit clinical adoption.
Authors
- Teresa Lemainque (ORCID: https://orcid.org/0000-0003-3167-7121)
- Daniel Truhn (ORCID: https://orcid.org/0000-0002-9605-0728)
- Robert Siepmann (ORCID: https://orcid.org/0000-0002-4608-5180)
- Alexandra Barabasch (ORCID: https://orcid.org/0000-0002-1744-6987)
- Christiane Katharina Kuhl (ORCID: https://orcid.org/0000-0001-8696-2363)
- Simon Westfechtel (ORCID: https://orcid.org/0000-0002-7050-9924)
- Marc Huppertz (ORCID: https://orcid.org/0009-0004-2801-3679)
- Christian Aßmann (ORCID: https://orcid.org/0000-0002-4827-3150)
- Sven Nebelung (ORCID: https://orcid.org/0000-0002-5267-9962)
- Kristoffer Kußmann
- Vera R Winter
Institutions
- Universitätsklinikum Aachen (DE)
Publication Details
- Journal
- European Radiology
- Published
- 2025-05-17
- DOI
- https://doi.org/10.1007/s00330-025-11670-6
- Citations
- 3
- Primary Topic
- Advanced MRI Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 4.08
Funders
- Deutsche Forschungsgemeinschaft
- Bundesministerium für Bildung und Forschung
- Ministerium für Kultur und Wissenschaft des Landes Nordrhein-Westfalen
- HORIZON EUROPE Framework Programme
- Medizinische Fakultät, RWTH Aachen University