Non-locally Encoder-Decoder Convolutional Network for Whole Brain QSM Inversion

TL;DR

This paper introduces a non-local encoder-decoder CNN for QSM inversion that improves image quality and reduces artifacts, facilitating clinical application of brain susceptibility mapping.

Contribution

A novel non-local encoder-decoder CNN architecture for whole brain QSM inversion that outperforms existing methods in accuracy and artifact suppression.

Findings

Outperforms existing methods on synthetic and clinical datasets

Preserves fine features and reduces streaking artifacts

Potential to accelerate clinical adoption of QSM

Abstract

Quantitative Susceptibility Mapping (QSM) reconstruction is a challenging inverse problem driven by ill conditioning of its field-to -susceptibility transformation. State-of-art QSM reconstruction methods either suffer from image artifacts or long computation times, which limits QSM clinical translation efforts. To overcome these limitations, a non-locally encoder-decoder gated convolutional neural network is trained to infer whole brain susceptibility map, using the local field and brain mask as the inputs. The performance of the proposed method is evaluated relative to synthetic data, a publicly available challenge dataset, and clinical datasets. The proposed approach can outperform existing methods on quantitative metrics and visual assessment of image sharpness and streaking artifacts. The estimated susceptibility maps can preserve conspicuity of fine features and suppress streaking artifacts. The demonstrated methods have potential value in advancing QSM clinical research and aiding in the translation of QSM to clinical operations.