13 November 2021 in Conference on Computer Vision and Pattern Recognition (CVPR)
Fast and accurate reconstruction of magnetic resonance (MR) images from under-sampled data is important in many clinical applications. In recent years, deep learning-based methods have been shown to produce superior performance on MR image reconstruction. However, these methods require large amounts of data which is difficult to collect and share due to the high cost of acquisition and medical data privacy regulations. In order to overcome this challenge, we propose a federated learning (FL) based solution in which we take advantage of the MR data available at different institutions while preserving patients’ privacy. However, the generalizability of models trained with the FL setting can still be suboptimal due to domain shift, which results from the data collected at multiple institutions with different sensors, disease types, and acquisition protocols, etc. With the motivation of circumventing this challenge, we propose a cross-site modeling for MR image reconstruction in which the learned intermediate latent features among different source sites are aligned with the distribution of the latent features at the target site. Extensive experiments are conducted to provide various insights about FL for MR image reconstruction. Experimental results demonstrate that the proposed framework is a promising direction to uti-lize multi-institutional data without compromising patients’ privacy for achieving improved MR image reconstruction. Our code is available at https://github.com/guopengf/FL-MRCM.
13 September 2023 in IEEE Transactions on Medical Imaging
The accelerating magnetic resonance imaging (MRI) reconstruction process is a challenging ill-posed inverse problem due to the excessive under-sampling operation in k-space. In this paper, we propose a recurrent Transformer model, namely ReconFormer, for MRI reconstruction, which can iteratively reconstruct high-fidelity magnetic resonance images from highly under-sampled k-space data (e.g., up to 8× acceleration). In particular, the proposed architecture is built upon Recurrent Pyramid Transformer Layers (RPTLs). The core design of the proposed method is Recurrent Scale-wise Attention (RSA), which jointly exploits intrinsic multi-scale information at every architecture unit as well as the dependencies of the deep feature correlation through recurrent states. Moreover, benefiting from its recurrent nature, ReconFormer is lightweight compared to other baselines and only contains 1.1 M trainable parameters. We validate the effectiveness of ReconFormer on multiple datasets with different magnetic resonance sequences and show that it achieves significant improvements over the state-of-the-art methods with better parameter efficiency. The implementation code and pre-trained weights are available at https://github.com/guopengf/ReconFormer.
30 September 2021 in IEEE Transactions on Medical Imaging
Data-driven automatic approaches have demonstrated their great potential in resolving various clinical diagnostic dilemmas in neuro-oncology, especially with the help of standard anatomic and advanced molecular MR images. However, data quantity and quality remain a key determinant, and a significant limit of the potential applications. In our previous work, we explored the synthesis of anatomic and molecular MR image networks (SAMR) in patients with post-treatment malignant gliomas. In this work, we extend this through a confidence-guided SAMR (CG-SAMR) that synthesizes data from lesion contour information to multi-modal MR images, including T1-weighted ( ${T}_{1}\text{w}$ ), gadolinium enhanced ${T}_{1}\text{w}$ (Gd- ${T}_{1}\text{w}$ ), T2-weighted ( ${T}_{2}\text{w}$ ), and fluid-attenuated inversion recovery ( $\textit {FLAIR}$ ), as well as the molecular amide proton transfer-weighted ( $\textit {APT}\text{w}$ ) sequence. We introduce a module that guides the synthesis based on a confidence measure of the intermediate results. Furthermore, we extend the proposed architecture to allow training using unpaired data. Extensive experiments on real clinical data demonstrate that the proposed model can perform better than current the state-of-the-art synthesis methods. Our code is available at https://github.com/guopengf/CG-SAMR .