Robust Simultaneous Multislice MRI Reconstruction Using Deep Generative Priors

2024-07-31

arXiv.org

AI Summary

To address inter- and intra-slice signal interference artifacts and distortions in simultaneous multi-slice (SMS) MRI reconstruction, this paper proposes ROGER: a denoising diffusion probabilistic model (DDPM)-based general prior integrated into a readout-stitching framework, enabling data-consistent single-slice reconstruction via iterative backward diffusion. Key contributions include: (1) the first DDPM prior requiring no SMS-specific training; (2) a low-frequency enhancement (LFE) module that alleviates the clinical bottleneck of insufficient fully sampled autocalibration signals in FSE/EPI sequences; and (3) strong out-of-distribution generalization capability. Experiments demonstrate that ROGER significantly outperforms state-of-the-art methods on both retrospective and prospective accelerated SMS data, yielding superior anatomical and functional image quality. The source code and sample data are publicly available.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Intelligent Robots: Learning & Optimization for ROB
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Simultaneous multislice (SMS) imaging is a powerful technique for accelerating magnetic resonance imaging (MRI) acquisitions. However, SMS reconstruction remains challenging due to complex signal interactions between and within the excited slices. In this study, we introduce ROGER, a robust SMS MRI reconstruction method based on deep generative priors. Utilizing denoising diffusion probabilistic models (DDPM), ROGER begins with Gaussian noise and gradually recovers individual slices through reverse diffusion iterations while enforcing data consistency from measured k-space data within the readout concatenation framework. The posterior sampling procedure is designed such that the DDPM training can be performed on single-slice images without requiring modifications for SMS tasks. Additionally, our method incorporates a low-frequency enhancement (LFE) module to address the practical issue that SMS-accelerated fast spin echo (FSE) and echo planar imaging (EPI) sequences cannot easily embed fully-sampled autocalibration signals. Extensive experiments on both retrospectively and prospectively accelerated datasets demonstrate that ROGER consistently outperforms existing methods, enhancing both anatomical and functional imaging with strong out-of-distribution generalization. The source code and sample data for ROGER are available at https://github.com/Solor-pikachu/ROGER.

Problem

• Synchronized Multi-Slice Imaging
• Magnetic Resonance Imaging
• Image Reconstruction

Innovation

• ROGER
• DDPM Model
• Low-frequency Enhancement Module