Robust Simultaneous Multislice MRI Reconstruction Using Deep Generative Priors

Simultaneous multislice (SMS) imaging is a powerful technique for accelerating magnetic resonance imaging (MRI) acquisitions. However, SMS reconstruction remains challenging due to the complex signal interactions between and within the excited slices. This study presents a robust SMS MRI reconstruction method using deep generative priors. Starting from Gaussian noise, we leverage denoising diffusion probabilistic models (DDPM) to gradually recover the individual slices through reverse diffusion iterations while imposing data consistency from the measured k-space under readout concatenation framework. The posterior sampling procedure is designed such that the DDPM training can be performed on single-slice images without special adjustments for SMS tasks. Additionally, our method integrates a low-frequency enhancement (LFE) module to address a practical issue that SMS-accelerated fast spin echo (FSE) and echo-planar imaging (EPI) sequences cannot easily embed autocalibration signals. Extensive experiments demonstrate that our approach consistently outperforms existing methods and generalizes well to unseen datasets. The code is available at https://github.com/Solor-pikachu/ROGER after the review process.

Simultaneous Multi-Slice Diffusion Imaging using Navigator-free Multishot Spiral Acquisition

Purpose: This work aims to raise a novel design for navigator-free multiband (MB) multishot uniform-density spiral (UDS) acquisition and reconstruction, and to demonstrate its utility for high-efficiency, high-resolution diffusion imaging. Theory and Methods: Our design focuses on the acquisition and reconstruction of navigator-free MB multishot UDS diffusion imaging. For acquisition, radiofrequency (RF) pulse encoding was employed to achieve Controlled Aliasing in Parallel Imaging (CAIPI) in MB imaging. For reconstruction, a new algorithm named slice-POCS-enhanced Inherent Correction of phase Errors (slice-POCS-ICE) was proposed to simultaneously estimate diffusion-weighted images and inter-shot phase variations for each slice. The efficacy of the proposed methods was evaluated in both numerical simulation and in vivo experiments. Results: In both numerical simulation and in vivo experiments, slice-POCS-ICE estimated phase variations more precisely and provided results with better image quality than other methods. The inter-shot phase variations and MB slice aliasing artifacts were simultaneously resolved using the proposed slice-POCS-ICE algorithm. Conclusion: The proposed navigator-free MB multishot UDS acquisition and reconstruction method is an effective solution for high-efficiency, high-resolution diffusion imaging.

East: Efficient and Accurate Secure Transformer Framework for Inference

Transformer has been successfully used in practical applications, such as ChatGPT, due to its powerful advantages. However, users' input is leaked to the model provider during the service. With people's attention to privacy, privacy-preserving Transformer inference is on the demand of such services. Secure protocols for non-linear functions are crucial in privacy-preserving Transformer inference, which are not well studied. Thus, designing practical secure protocols for non-linear functions is hard but significant to model performance. In this work, we propose a framework \emph{East} to enable efficient and accurate secure Transformer inference. Firstly, we propose a new oblivious piecewise polynomial evaluation algorithm and apply it to the activation functions, which reduces the runtime and communication of GELU by over 1.5$\times$ and 2.5$\times$, compared to prior arts. Secondly, the secure protocols for softmax and layer normalization are carefully designed to faithfully maintain the desired functionality. Thirdly, several optimizations are conducted in detail to enhance the overall efficiency. We applied \emph{East} to BERT and the results show that the inference accuracy remains consistent with the plaintext inference without fine-tuning. Compared to Iron, we achieve about 1.8$\times$ lower communication within 1.2$\times$ lower runtime.