Loading...

4,068 posters, 219 videos, 101 topics, 69 sessions, 14,365 authors, 6,128 institutions

ePostersLive by SciGen Technologies S.A. All rights reserved.

Alzheimer's Association International Conference 2026

July 12-15, 2026 | London, United Kingdom, and Online

Alzheimer's Association International Conference 2026 banner

2618

Highly Accelerated Quantitative Mri For Discovery Of Novel Ad Biomarkers - Mpnrage Meets Inr Reconstruction

Poster Presenter

Natascha Niessen

Authors

Natascha Niessen, Ana Beatriz Solana, Carolin M. Pirkl, Tim Sprenger, Veronika Spieker, Hannah Eichhorn, Rolf F. Schulte, Marion I. Menzel, Julia A. Schnabel, PREDICTOM consortium

Affiliations

, School of Computation and Information Technology, Technical University of Munich, Munich, Germany; GE HealthCare, Munich, Germany;, GE HealthCare, Munich, Germany, GE HealthCare, Munich, Germany; Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden, School of Computation and Information Technology, Technical University of Munich, Munich, Germany; Institute of Machine Learning in Biomedical Imaging, Helmholtz Munich, Neuherberg, Germany, GE HealthCare, Munich, Germany; Technische Hochschule Ingolstadt, Ingolstadt, Germany; School of Natural Sciences, Technical University of Munich, Munich, Germany, School of Computation and Information Technology, Technical University of Munich, Munich, Germany; Institute of Machine Learning in Biomedical Imaging, Helmholtz Munich, Neuherberg, Germany; School of Biomedical Engineering and Imaging Sciences, King’s College London, London, United Kingdom

Part of Topic

Introduction

•Current Alzheimer’s disease diagnostics are either invasive or costly.
•Quantitative MRI offers a non-invasive and absolute route to detect early tissue microstructure changes.
•Long scan times currently limit quantitative MRI use in neuroimaging protocols for dementia patients.
•We develop a fast MPnRAGE1 acquisition and reconstruction framework for clinically feasible quantitative T1 mapping and multiple inversion time (TI) contrast images.
 
Methods

MRI Acquisition:

•MPnRAGE contrast images differ in contrast but share anatomical information.
•Complementary undersampling is applied across inversion-time contrasts to leverage this redundant anatomical information.
•Central k-space is densely sampled to preserve contrast information. Outer k-space is sampled using complementary Poisson disk patterns.

Reconstruction:

•Complementary data are jointly reconstructed using an implicit neural representation (INR) network which is self-supervised and scan-specific not needing any training data.
 
Results

Scan time was reduced from 29.22 min to 5.39 min for 10 TI images at 1.5 mm isotropic resolution.

Conclusion

MPnRAGE is included in the advanced PREDICTOM MRI protocol and can be leveraged for future MRI biomarker
discovery for early Alzheimer’s disease detection.

Comments

Email is required but is not shown publicly.

Loading comments...

aaic2026 banner
Copyright © 2015-2026, ePostersLive® SciGen is a registered trademark of SciGen Technologies S.A. Patent pending.

This website and third-party tools we use rely on cookies for the best user experience. By selecting "I agree", you agree to cookie usage as described in our Privacy Policy.