Journal Article

DZNE-2026-01125

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Phase-constrained zero-shot self-supervised learning for BLADE liver MRI reconstruction.

Yarach, U. ; Akrasirakul, S. ; Mattern, H.DZNE* ; Speck, O. (Last author)DZNE*

2026
Springer Heidelberg

This record in other databases:    

Please use a persistent id in citations: doi:10.1007/s10334-026-01359-2

Abstract: Liver MRI plays a critical role in the diagnosis and monitoring of liver disease; however, image quality is often degraded by respiratory motion and noise, particularly in high-resolution and diffusion-weighted imaging. Propeller-based sequences such as BLADE improve motion robustness, but advanced reconstruction strategies are required to fully exploit their potential under accelerated conditions.We propose a phase-constrained zero-shot self-supervised learning (PC ZS-SSL) framework for BLADE liver MRI reconstruction. The method embeds BLADE forward and adjoint operators within an unrolled deep network together with an explicit phase estimation module. Unlike supervised approaches, PC ZS-SSL requires no external training data and instead leverages partitioned k-space. The framework was first evaluated using structured phantom experiments assessing spatial resolution and low-contrast detectability, and subsequently applied to in vivo 3 T T2-weighted (T2W, 20 blades) and diffusion-weighted imaging (DWI, 18 and 15 blades, b = 0, 800 s/mm2). Performance was compared with locally low-rank (LLR) and vendor-provided reconstructions.In phantom studies, PC ZS-SSL preserved fine structural details and demonstrated improved sharpness compared with fewer gradient updates and LLR. In vivo, PC ZS-SSL consistently reduced noise and ringing artifacts while maintaining anatomical fidelity. In T2W imaging, it achieved image quality comparable to LLR with fewer artifacts. In DWI, where noise is more pronounced, PC ZS-SSL provided clearer organ boundaries than both LLR and vendor reconstructions. Additional in vivo evaluation demonstrated that PC ZS-SSL remained robust under severe undersampling conditions (e.g., 4 blades) and challenging imaging scenarios, where LLR reconstructions exhibited residual artifacts.PC ZS-SSL enables high-quality, artifact-suppressed BLADE liver MRI without the need for external training data. Its strong performance in both phantom and in vivo experiments-particularly under high-noise diffusion conditions-highlights its potential for clinical translation.

Keyword(s): Phantoms, Imaging (MeSH) ; Humans (MeSH) ; Liver: diagnostic imaging (MeSH) ; Diffusion Magnetic Resonance Imaging (MeSH) ; Supervised Machine Learning (MeSH) ; Algorithms (MeSH) ; Image Processing, Computer-Assisted: methods (MeSH) ; Magnetic Resonance Imaging: methods (MeSH) ; Image Interpretation, Computer-Assisted: methods (MeSH) ; Motion (MeSH) ; Artifacts (MeSH) ; Liver Diseases: diagnostic imaging (MeSH) ; Signal-To-Noise Ratio (MeSH) ; BLADE imaging ; Deep Learning ; Diffusion-weighted imaging ; Liver MRI ; MRI reconstruction ; Zero-shot self-supervised learning

---

Contributing Institute(s):

1. Linking Imaging Projects (AG Speck)
2. Mixed Cerebral Pathologies and Cognitive Aging (AG Schreiber)

Research Program(s):

1. 353 - Clinical and Health Care Research (POF4-353) (POF4-353)

Appears in the scientific report 2026

---

Database coverage:
; Clarivate Analytics Master Journal List ; Current Contents - Clinical Medicine ; DEAL Springer ; DEAL Springer ; Essential Science Indicators ; IF < 5 ; JCR ; SCOPUS ; Science Citation Index Expanded ; Web of Science Core Collection

---