Exploring the Acceleration Limits of Deep Learning Variational Network–based Two-dimensional Brain MRI
Rattachement africain : il, us, de. Niveau de preuve : code pays fourni par la source.
Le résumé fourni par la source
Purpose To explore the limits of deep learning–based brain MRI reconstruction and identify useful acceleration ranges for general-purpose imaging and potential screening. Materials and Methods In this retrospective study conducted from 2019 through 2021, a model was trained for reconstruction on 5847 brain MR images. Performance was evaluated across a wide range of accelerations (up to 100-fold along a single phase-encoded direction for two-dimensional [2D] sections) on the fastMRI test set collected at New York University, consisting of 558 image volumes. In a sample of 69 volumes, reconstructions were classified by radiologists for identification of two clinical thresholds: (a) general-purpose diagnostic imaging and (b) potential use in a screening protocol. A Monte Carlo procedure was developed to estimate reconstruction error with only undersampled data. The model was evaluated on both in-domain and out-of-domain data. The 95% CIs were calculated using the percentile bootstrap method. Results Radiologists rated 100% of 69 volumes as having sufficient image quality for general-purpose imaging at up to 4× acceleration and 65 of 69 volumes (94%) as having sufficient image quality for screening at up to 14× acceleration. The Monte Carlo procedure estimated ground truth peak signal-to-noise ratio and mean squared error with coefficients of determination greater than 0.5 at 2× to 20× acceleration levels. Out-of-distribution experiments demonstrated the model’s ability to produce images substantially distinct from the training set, even at 100× acceleration. Conclusion For 2D brain images using deep learning–based reconstruction, maximum acceleration for potential screening was three to four times higher than that for diagnostic general-purpose imaging. Keywords: MRI Reconstruction, High Acceleration, Deep Learning, Screening, Out of Distribution Supplemental material is available for this article. © RSNA, 2022
Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.
Le contrôle bibliographique ouvert
DOI retrouvé dans Crossref DOI retrouvé ; titre concordant.
- Titre Crossref
- Exploring the Acceleration Limits of Deep Learning Variational Network–based Two-dimensional Brain MRI
- Date Crossref
- 01/11/2022
- Éditeur
- Radiological Society of North America (RSNA)
- Type
- journal-article
Ce recoupement confirme des métadonnées liées au DOI. Il ne confirme ni la méthode ni les conclusions de l’étude, et il ne compte pas comme une seconde source scientifique indépendante.
Où se fait cette recherche
-
Meta (Israel) pays non établi dans la noticeEntreprise
-
NYU Langone Health Department of Radiology pays non établi dans la noticeÉtablissement de santé
-
Meta (United States) pays non établi dans la noticeEntreprise
-
Stealth BioTherapeutics (United States) pays non établi dans la noticeEntreprise
-
Friedrich-Alexander-Universität Erlangen-Nürnberg pays non établi dans la noticeUniversité ou école supérieure
-
Meta AI pays non établi dans la noticeInstitution
-
Department of Artificial Intelligence Research pays non établi dans la noticeInstitution
-
Department Artificial Intelligence in Biomedical Engineering pays non établi dans la noticeInstitution
Meta (Israel), Department of Radiology — NYU Langone Health et Meta (United States), avec 5 autres affiliations.
Une affiliation ne permet pas de déduire la nationalité d’un auteur.