Spinet-QSM: model-based deep learning with schatten p-norm regularization for improved quantitative susceptibility mapping
Magnetic Resonance Materials in Physics, Biology and Medicine · 2024
DOI: 10.1007/s10334-024-01158-7 ↗Kurz gefasst
Fachartikel in der Zeitschrift Magnetic Resonance Materials in Physics, Biology and Medicine, 2024. Verfasst von Vaddadi Venkatesh und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computational and Data Sciences, Indian Institute of Science, Bangalore, Karnataka, 560012, India. Hauptthemen laut MEDLINE: Deep Learning, Magnetic Resonance Imaging, Image Processing, Computer-Assisted, Algorithms. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 33 Literaturangaben. Gefördert von: Department of Biotechnology, Ministry of Science and Technology, India.
Abstract (Originalsprache)
OBJECTIVE: Quantitative susceptibility mapping (QSM) provides an estimate of the magnetic susceptibility of tissue using magnetic resonance (MR) phase measurements. The tissue magnetic susceptibility (source) from the measured magnetic field distribution/local tissue field (effect) inherent in the MR phase images is estimated by numerically solving the inverse source-effect problem. This study aims to develop an effective model-based deep-learning framework to solve the inverse problem of QSM. MATERIALS AND METHODS: This work proposes a Schatten p -norm-driven model-based deep learning framework for QSM with a learnable norm parameter p to adapt to the data. In contrast to other model-based architectures that enforce the l 2 -norm or l 1 -norm for the denoiser, the proposed approach can enforce any p -norm ( 0 < p ≤ 2 ) on a trainable regulariser. RESULTS: The proposed method was compared with deep learning-based approaches, such as QSMnet, and model-based deep learning approaches, such as learned proximal convolutional neural network (LPCNN). Reconstructions performed using 77 imaging volumes with different acquisition protocols and clinical conditions, such as hemorrhage and multiple sclerosis, showed that the proposed approach outperformed existing state-of-the-art methods by a significant margin in terms of quantitative merits. CONCLUSION: The proposed SpiNet-QSM showed a consistent improvement of at least 5% in terms of the high-frequency error norm (HFEN) and normalized root mean squared error (NRMSE) over other QSM reconstruction methods with limited training data.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computational and Data Sciences, Indian Institute of Science, Bangalore, Karnataka, 560012, India.
- School of Data Science, Indian Institute of Science Education and Research, Thiruvananthapuram, Kerala, 695551, India.
- Department of Computational and Data Sciences, Indian Institute of Science, Bangalore, Karnataka, 560012, India. yalavarthy@iisc.ac.in.
Förderung
- Department of Biotechnology, Ministry of Science and Technology, India
Zitieren
APA
Venkatesh, V., Mathew, R. S., & Yalavarthy, P. K. (2024). Spinet-QSM: model-based deep learning with schatten p-norm regularization for improved quantitative susceptibility mapping. Magnetic Resonance Materials in Physics, Biology and Medicine. https://doi.org/10.1007/s10334-024-01158-7
Vancouver
Venkatesh V, Mathew RS, Yalavarthy PK. Spinet-QSM: model-based deep learning with schatten p-norm regularization for improved quantitative susceptibility mapping. Magnetic Resonance Materials in Physics, Biology and Medicine. 2024. doi:10.1007/s10334-024-01158-7
BibTeX
@article{Venkatesh2024,
author = {Venkatesh, Vaddadi and Mathew, Raji Susan and Yalavarthy, Phaneendra K},
title = {Spinet-QSM: model-based deep learning with schatten p-norm regularization for improved quantitative susceptibility mapping},
journal = {Magnetic Resonance Materials in Physics, Biology and Medicine},
year = {2024},
doi = {10.1007/s10334-024-01158-7}
}
EUVIMED