Unsupervised motion artifact correction of turbo spin‐echo MRI using deep image prior

• Published in: Magnetic resonance in medicine Vol. 92; no. 1; pp. 28 - 42
• Main Authors: Lee, Jongyeon, Seo, Hyunseok, Lee, Wonil, Park, HyunWook
• Format: Journal Article
• Language: English
• Published: United States Wiley Subscription Services, Inc 01.07.2024
• Subjects: Ablation; Algorithms; Artificial neural networks; Brain - diagnostic imaging; Computer Simulation; Datasets; deep image prior; Deep Learning; High impedance; Humans; Image acquisition; Image degradation; Image Processing, Computer-Assisted - methods; Image quality; Machine learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Motion; Motion simulation; Neural networks; Neural Networks, Computer; Parameterization; Simulation models; Synthesis; turbo spin‐echo; unsupervised motion correction; turbo spin‐echo; deep learning; deep image prior; unsupervised motion correction

Purpose In MRI, motion artifacts can significantly degrade image quality. Motion artifact correction methods using deep neural networks usually required extensive training on large datasets, making them time‐consuming and resource‐intensive. In this paper, an unsupervised deep learning‐based motion...