Fat–water MRI separation using deep complex convolution network

Objective Deep complex convolutional networks (DCCNs) utilize complex-valued convolutions and can process complex-valued MRI signals directly without splitting them into two real-valued magnitude and phase components. The performance of DCCN and real-valued U-Net is thoroughly investigated in the ph...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Magma (New York, N.Y.) Jg. 38; H. 6; S. 959 - 977
Hauptverfasser:	Ganeshkumar, Moorthy, Kandasamy, Devasenathipathy, Sharma, Raju, Mehndiratta, Amit
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Cham Springer International Publishing 01.12.2025 Springer Nature B.V
Schlagworte:	Abdomen - diagnostic imaging Adipose Tissue - diagnostic imaging Algorithms Basic Science - Reconstruction algorithms and artificial intelligence Biomedical Engineering and Bioengineering Body Water - diagnostic imaging Computer Appl. in Life Sciences Convex analysis Correlation coefficient Correlation coefficients Datasets Deep Learning Echoes Fatty liver Fatty Liver - diagnostic imaging Health Informatics Humans Image Processing, Computer-Assisted - methods Imaging Knee - diagnostic imaging Magnetic resonance imaging Magnetic Resonance Imaging - methods Medicine Medicine & Public Health Methods Neural Networks, Computer Optimization algorithms Phantoms, Imaging Physics Radiology Reconstruction Research Article Separation Solid State Physics Thigh - diagnostic imaging Water Water - chemistry MRI fat quantification Fat–water separation Physics-informed deep learning Complex-valued convolution Deep complex network
ISSN:	1352-8661, 0968-5243, 1352-8661
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	Objective Deep complex convolutional networks (DCCNs) utilize complex-valued convolutions and can process complex-valued MRI signals directly without splitting them into two real-valued magnitude and phase components. The performance of DCCN and real-valued U-Net is thoroughly investigated in the physics-informed subject-specific ad-hoc reconstruction method for fat–water separation and is compared against a widely used reference approach. Materials and methods A comprehensive test dataset ( n = 33) was used for performance analysis. The 2012 ISMRM fat–water separation workshop dataset containing 28 batches of multi-echo MRIs with 3–15 echoes from the abdomen, thigh, knee, and phantoms, acquired with 1.5 T and 3 T scanners were used. Additionally, five MAFLD patients multi-echo MRIs acquired from our clinical radiology department were also used. Results The quantitative results demonstrated that DCCN produced fat–water maps with better normalized RMS error and structural similarity index with the reference approach, compared to real-valued U-Nets in the ad-hoc reconstruction method for fat–water separation. The DCCN achieved an overall average SSIM of 0.847 ± 0.069 and 0.861 ± 0.078 in generating fat and water maps, respectively, in contrast the U-Net achieved only 0.653 ± 0.166 and 0.729 ± 0.134. The average liver PDFF from DCCN achieved a correlation coefficient R of 0.847 with the reference approach.
Bibliographie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ISSN:	1352-8661 0968-5243 1352-8661
DOI:	10.1007/s10334-025-01268-w