The Trustworthy AI for MRI (TAIMRI) Lab centers its research around two core themes: AI for MRI in diagnosis of neurological and musculoskeletal (MSK) diseases and health.
To drive these advancements, the lab leverages key technical AI components, focusing primarily on:
With a commitment to explainable AI systems.
The Trustworthy AI for MRI (TAIMRI) Lab is dedicated to improving the accuracy and reduce the costs of MRI-based diagnosis using AI methods, with a focus on neurological and musculoskeletal diseases.
The lab’s mission and vision are to improve the quality of MRI-based diagnosis with trustworthy AI methods. For this, they aim to optimize the full chain from image acquisition prescription, to image analysis and introduction of AI-supported acquisition and diagnosis in clinical practice.
The impact of the Lab lies in forming the basis for clinical MR scanning in the future. In the AI-assisted diagnostic approaches for brain tumors and bone/soft-tissue lesions, image-based disease biomarkers will be created, which can be a subsequent target for the protocol adaptation. By focusing on two clinical domains, they aim to enhance the generalizability of the developed methods and ensure broad applicability across disease domains.
Trustworthy AI for adaptive and precision MR protocols – Aims to develop predictor of acquisition settings optimal for imaging pathological tissue.
End-to-end deep learning quantitative MR reconstruction – Aims to develop efficient methods for Quantitative MRI reconstruction.
Trustworthy AI for integrated diagnostics of brain tumours – Aims to improve diagnostic accuracy of non-invasive tumor characterization by MR imaging.
Trustworthy AI for improved diagnosis of bone and soft-tissue lesions on MRI – Aims to develop AI models for differential diagnosis of musculoskeletal lesions.
Acceptance of radiological AI technology in a clinical setting – Aims to develop a framework to understand different factors influencing acceptance.
Quantitative MRI Mapping using Diffusion Models with Data Consistency on 3D Fast Zero Echo Time Acquisition Proceedings Article
In: Proceedings of the 34th Annual Meeting of the International Society for Magnetic Resonance in Medicine (ISMRM), Cape Town, South Africa, 2026.
Partial Diffusion for Accelerated 3D Silent Multi-Parametric Zero Echo Time Acquisition (MuPa-ZTE) Proceedings Article
In: Proceedings of the 34th Annual Meeting of the International Society for Magnetic Resonance in Medicine (ISMRM), Cape Town, South Africa, 2026.
RGB4FLAIR: Eliminating Partial Volume Artifacts in Synthetic FLAIR Using Deep Learning Trained on Natural Images Proceedings Article
In: Annual Meeting of the International Society for Magnetic Resonance in Medicine (ISMRM), Cape Town, South Africa, 2026.
Towards One-Minute 3D Multi-Parametric Quantitative Brain MRI using Partial Diffusion Models Bachelor Thesis
2025.
Evaluation of Monte Carlo Dropout for Uncertainty Quantification in Multi-task Deep Learning-Based Glioma Subtyping Proceedings Article
In: International Workshop on Uncertainty for Safe Utilization of Machine Learning in Medical Imaging, pp. 180–190, Springer, 2025.
P04. 18. A GLIOSEG: AN INTEGRATED FRAMEWORK FOR ROBUST AI-BASED GLIOMA SEGMENTATION THROUGH MODEL ENSEMBLING Journal Article
In: vol. 27, iss. Supplement_3, pp. iii63, 2025.
AI in radiological imaging of soft-tissue and bone tumours: a systematic review evaluating against CLAIM and FUTURE-AI guidelines Journal Article
In: vol. 114, 2025.
Factors influencing AI acceptance in radiology: a systematic review across the radiology workflow Journal Article
In: pp. 1–10, 2025.
Self-Supervised Weighted Image Guided Quantitative MRI Super-Resolution Miscellaneous
2025.
Generalizable, Cross-sequence Physics-Informed Quantitative MRI Super-resolution Proceedings Article
In: Proceedings of the Annual Scientific Meeting of the European Society for Magnetic Resonance in Medicine and Biology (ESMRMB), Marseille, France, 2025.
RGB2qMRI: Can Deep Learning Models for Quantitative MRI be Trained with RGB Pictures? Proceedings Article
In: Proceedings of the 33rd Annual Meeting of the International Society for Magnetic Resonance in Medicine (ISMRM), Honolulu, HI, USA, 2025.
PT25 Systems-Level Modeling Approaches for Complex Health Technologies: A Systematic Review Journal Article
In: vol. 28, no. 12, pp. S541, 2025.
qMRI Diffuser: Quantitative T1 Mapping of the Brain using a Denoising Diffusion Probabilistic Model Proceedings Article
In: arXiv, 2024, (arXiv:2407.16477 [cs]).
Erasmus MC – University Medical Center Rotterdam based in Rotterdam, Netherlands, affiliated with Erasmus University and home to its faculty of medicine, is the largest and one of the most authoritative scientific University Medical Centers in Europe.
GE HealthCare provides digital infrastructure, data analytics & decision support tools helps in diagnosis, treatment and monitoring of patients.
Erasmus University Rotterdam (EUR) is a public research university located in Rotterdam, Netherlands.
