Physics-Informed Deep Unrolled Network for Portable MR Image Reconstruction

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ilıcak, Efe, Rao, Chinmay, Najac, Chloé, Lena, Beatrice, Imre, Baris, Galve, Fernando, Alonso, Joseba, Webb, Andrew, Staring, Marius
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915495085604864
author Ilıcak, Efe
Rao, Chinmay
Najac, Chloé
Lena, Beatrice
Imre, Baris
Galve, Fernando
Alonso, Joseba
Webb, Andrew
Staring, Marius
author_facet Ilıcak, Efe
Rao, Chinmay
Najac, Chloé
Lena, Beatrice
Imre, Baris
Galve, Fernando
Alonso, Joseba
Webb, Andrew
Staring, Marius
contents Magnetic resonance imaging (MRI) is the gold standard imaging modality for numerous diagnostic tasks, yet its usefulness is tempered due to its high cost and infrastructural requirements. Low-cost very-low-field portable scanners offer new opportunities, while enabling imaging outside conventional MRI suites. However, achieving diagnostic-quality images in clinically acceptable scan times remains challenging with these systems. Therefore methods for improving the image quality while reducing the scan duration are highly desirable. Here, we investigate a physics-informed 3D deep unrolled network for the reconstruction of portable MR acquisitions. Our approach includes a novel network architecture that utilizes momentum-based acceleration and leverages complex conjugate symmetry of k-space for improved reconstruction performance. Comprehensive evaluations on emulated datasets as well as 47mT portable MRI acquisitions demonstrate the improved reconstruction quality of the proposed method compared to existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2509_11790
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Physics-Informed Deep Unrolled Network for Portable MR Image Reconstruction
Ilıcak, Efe
Rao, Chinmay
Najac, Chloé
Lena, Beatrice
Imre, Baris
Galve, Fernando
Alonso, Joseba
Webb, Andrew
Staring, Marius
Medical Physics
Magnetic resonance imaging (MRI) is the gold standard imaging modality for numerous diagnostic tasks, yet its usefulness is tempered due to its high cost and infrastructural requirements. Low-cost very-low-field portable scanners offer new opportunities, while enabling imaging outside conventional MRI suites. However, achieving diagnostic-quality images in clinically acceptable scan times remains challenging with these systems. Therefore methods for improving the image quality while reducing the scan duration are highly desirable. Here, we investigate a physics-informed 3D deep unrolled network for the reconstruction of portable MR acquisitions. Our approach includes a novel network architecture that utilizes momentum-based acceleration and leverages complex conjugate symmetry of k-space for improved reconstruction performance. Comprehensive evaluations on emulated datasets as well as 47mT portable MRI acquisitions demonstrate the improved reconstruction quality of the proposed method compared to existing methods.
title Physics-Informed Deep Unrolled Network for Portable MR Image Reconstruction
topic Medical Physics
url https://arxiv.org/abs/2509.11790