Non-locally Encoder-Decoder Convolutional Network for Whole Brain QSM Inversion
This work addresses limitations in QSM reconstruction for clinical translation, offering improved accuracy and efficiency, though it appears incremental as it builds on existing neural network approaches for a specific medical imaging domain.
The paper tackles the challenging inverse problem of Quantitative Susceptibility Mapping (QSM) reconstruction, which suffers from artifacts and slow computation, by proposing a non-locally encoder-decoder gated convolutional neural network that outperforms existing methods on synthetic, public challenge, and clinical datasets in terms of quantitative metrics and visual assessment of image sharpness and artifact suppression.
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.