Spinet-QSM: model-based deep learning with schatten p-norm regularization for improved quantitative susceptibility mapping

Venkatesh, V and Mathew, RS and Yalavarthy, PK (2024) Spinet-QSM: model-based deep learning with schatten p-norm regularization for improved quantitative susceptibility mapping. In: Magnetic Resonance Materials in Physics, Biology and Medicine .

PDF mag_res_mat_phy_bio_med_2024.pdf - Published Version Restricted to Registered users only Download (4MB) | Request a copy

Abstract

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 l2-norm or l1-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. © The Author(s), under exclusive licence to European Society for Magnetic Resonance in Medicine and Biology (ESMRMB) 2024.

Item Type:	Journal Article
Publication:	Magnetic Resonance Materials in Physics, Biology and Medicine
Publisher:	Springer Science and Business Media Deutschland GmbH
Additional Information:	The copyright for this article belongs to Springer Science and Business Media Deutschland GmbH.
Department/Centre:	Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited:	24 May 2024 11:20
Last Modified:	24 May 2024 11:20
URI:	https://eprints.iisc.ac.in/id/eprint/84888

Actions (login required)

View Item