AUTHOR=Graf Simon , Wohlgemuth Walter A. , Deistung Andreas 

TITLE=Incorporating a-priori information in deep learning models for quantitative susceptibility mapping via adaptive convolution

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 18 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2024.1366165

DOI=10.3389/fnins.2024.1366165

ISSN=1662-453X

ABSTRACT=Quantitative susceptibility mapping (QSM) has attracted considerable interest for tissue characterization (e.g., iron and calcium accumulation, myelination, venous vasculature) in the human brain. It relies on extensive data processing of gradient-echo MRI phase images. One crucial step in this procedure is the solution of the ill-posed inversion of the local magnetic field to the magnetic susceptibility, which has traditionally been performed with regularization-based approaches and more recently with deep learning. While the deep learning approaches have shown great potential, the acquisition parameters applied in clinical settings such as image resolution or image orientation with respect to the magnetic field have not been fully accounted for. Furthermore, the lack of comprehensive training data covering a wide range of acquisition parameters further limits the current QSM deep learning approaches. Here, we propose the integration of a priori information of imaging parameters into convolutional neural networks to solve the field-to-susceptibility inversion. Our approach, adaptive convolution, learns the mapping between the additional presented information (acquisition parameters) and the changes in the phase images associated with these varying acquisition parameters. By associating a-priori information with the network parameters itself, the optimal set of convolution weights is selected based on data-specific attributes, leading to generalizability towards changes in acquisition parameters. Moreover, we demonstrate the feasibility of pre-training on synthetic data and transfer learning to clinical brain data to achieve substantial improvements in the computation of susceptibility maps.