Inverse regression in MR Fingerprinting: reducing dictionary size while increasing parameters accuracy - INRIA - Institut National de Recherche en Informatique et en Automatique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2019

Inverse regression in MR Fingerprinting: reducing dictionary size while increasing parameters accuracy

Résumé

Purpose: To reduce dictionary size and increase parameter estimate accuracy in MR Fingerprinting (MRF). Methods: A dictionary-based learning (DBL) method is investigated to bypass inherent MRF limitations in high dimension: reconstruction time and memory requirement. The DBL method is a 3-step procedure: (1) a quasi-random sampling strategy to produce the dictionary, (2) a statistical inverse regression model to learn from the dictionary a probabilistic mapping between MR fingerprints and parameters, and (3) this mapping to provide both parameter estimates and their confidence levels. Results: On synthetic data, experiments show that the quasi-random sampling outperforms the grid when designing the dictionary for inverse regression. Dictionaries up to 100 times smaller than usually employed in MRF yield more accurate parameter estimates with a 500 time gain. Estimates are supplied with a confidence index, well correlated with the estimation bias (r~$\ge$~0.89). On microvascular MRI data, results show that dictionary-based methods (MRF and DBL) yield more accurate estimates than the conventional, closed-form equation, method.On MRI signals from tumor bearing rats, the DBL method shows very little sensitivity to the dictionary size in contrast to the MRF method. Conclusion: The proposed method efficiently reduces the number of required simulations to produce the dictionary, speeds up parameter estimation, and improve estimates accuracy. The DBL method also introduces a confidence index for each parameter estimate.
Fichier principal
Vignette du fichier
Main4HAL.pdf (2.17 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02314026 , version 1 (11-10-2019)
hal-02314026 , version 2 (12-05-2020)
hal-02314026 , version 3 (17-03-2021)

Identifiants

  • HAL Id : hal-02314026 , version 1

Citer

Fabien Boux, Florence Forbes, Julyan Arbel, Emmanuel L. Barbier. Inverse regression in MR Fingerprinting: reducing dictionary size while increasing parameters accuracy. 2019. ⟨hal-02314026v1⟩

Collections

LJK_PS_MISTIS
442 Consultations
519 Téléchargements

Partager

Gmail Facebook X LinkedIn More