Navigation überspringen
Universitätsbibliothek Heidelberg
Status: Bibliographieeintrag

Verfügbarkeit
Standort: ---
Exemplare: ---
heiBIB
 Online-Ressource
Verfasst von:Rotkopf, Lukas Thomas [VerfasserIn]   i
 Ziener, Christian H. [VerfasserIn]   i
 von Knebel-Doeberitz, Nikolaus [VerfasserIn]   i
 Wolf, Sabine D. [VerfasserIn]   i
 Hohmann, Anja [VerfasserIn]   i
 Wick, Wolfgang [VerfasserIn]   i
 Bendszus, Martin [VerfasserIn]   i
 Schlemmer, Heinz-Peter [VerfasserIn]   i
 Paech, Daniel [VerfasserIn]   i
 Kurz, Felix T. [VerfasserIn]   i
Titel:A physics-informed deep learning framework for dynamic susceptibility contrast perfusion MRI
Verf.angabe:Lukas T. Rotkopf, Christian H. Ziener, Nikolaus von Knebel-Doeberitz, Sabine D. Wolf, Anja Hohmann, Wolfgang Wick, Martin Bendszus, Heinz-Peter Schlemmer, Daniel Paech, Felix T. Kurz
E-Jahr:2024
Jahr:[20 September 2024]
Umfang:10 S.
Fussnoten:Gesehen am 27.03.2025
Titel Quelle:Enthalten in: Medical physics
Ort Quelle:Hoboken, NJ : Wiley, 1974
Jahr Quelle:2024
Band/Heft Quelle:51(2024), 12, Seite 9031-9040
ISSN Quelle:2473-4209
 1522-8541
Abstract:Background Perfusion magnetic resonance imaging (MRI)s plays a central role in the diagnosis and monitoring of neurovascular or neurooncological disease. However, conventional processing techniques are limited in their ability to capture relevant characteristics of the perfusion dynamics and suffer from a lack of standardization. Purpose We propose a physics-informed deep learning framework which is capable of analyzing dynamic susceptibility contrast perfusion MRI data and recovering the dynamic tissue response with high accuracy. Methods The framework uses physics-informed neural networks (PINNs) to learn the voxel-wise TRF, which represents the dynamic response of the local vascular network to the contrast agent bolus. The network output is stabilized by total variation and elastic net regularization. Parameter maps of normalized cerebral blood flow (nCBF) and volume (nCBV) are then calculated from the predicted residue functions. The results are validated using extensive comparisons to values derived by conventional Tikhonov-regularized singular value decomposition (TiSVD), in silico simulations and an in vivo dataset of perfusion MRI exams of patients with high-grade gliomas. Results The simulation results demonstrate that PINN-derived residue functions show a high concordance with the true functions and that the calculated values of nCBF and nCBV converge towards the true values for higher contrast-to-noise ratios. In the in vivo dataset, we find high correlations between conventionally derived and PINN-predicted perfusion parameters (Pearson's rho for nCBF: 0.84±0.03\0.84 \pm 0.03\ and nCBV: 0.92±0.03\0.92 \pm 0.03\) and very high indices of image similarity (structural similarity index for nCBF: 0.91±0.03\0.91 \pm 0.03\ and for nCBV: 0.98±0.00\0.98 \pm 0.00\). Conclusions PINNs can be used to analyze perfusion MRI data and stably recover the response functions of the local vasculature with high accuracy.
DOI:doi:10.1002/mp.17415
URL:Bitte beachten Sie: Dies ist ein Bibliographieeintrag. Ein Volltextzugriff für Mitglieder der Universität besteht hier nur, falls für die entsprechende Zeitschrift/den entsprechenden Sammelband ein Abonnement besteht oder es sich um einen OpenAccess-Titel handelt.

Volltext: https://doi.org/10.1002/mp.17415
 Volltext: https://onlinelibrary.wiley.com/doi/abs/10.1002/mp.17415
 DOI: https://doi.org/10.1002/mp.17415
Datenträger:Online-Ressource
Sprache:eng
Sach-SW:deep learning
 MRI
 perfusion imaging
 physics-informed neural networks
K10plus-PPN:1920734694
Verknüpfungen:→ Zeitschrift

Permanenter Link auf diesen Titel (bookmarkfähig):  https://katalog.ub.uni-heidelberg.de/titel/69322848   QR-Code
zum Seitenanfang