🤖 AI Summary
High-resolution MRI clinical deployment is hindered by prolonged acquisition times. While parallel imaging (PI) accelerates acquisition, conventional methods suffer from poor generalizability, subject- or acceleration-factor-specific tuning, and computationally expensive reconstruction. To address these limitations, we propose a generalized implicit neural representation (INR) framework featuring a novel scale-embedding encoder that enables voxel-wise scale-invariant feature extraction. By jointly encoding spatial coordinates and prior features, our end-to-end differentiable network reconstructs high-fidelity images directly from undersampled k-space data—without retraining—across diverse acceleration factors (4×–6×) and subjects. Quantitatively, it achieves significant PSNR and SSIM improvements over state-of-the-art methods, while reducing computational load, GPU memory consumption, and inference latency—demonstrating strong potential for real-time clinical deployment.
📝 Abstract
High-resolution magnetic resonance imaging (MRI) is essential in clinical diagnosis. However, its long acquisition time remains a critical issue. Parallel imaging (PI) is a common approach to reduce acquisition time by periodically skipping specific k-space lines and reconstructing images from undersampled data. This study presents a generalized implicit neural representation (INR)-based framework for MRI PI reconstruction, addressing limitations commonly encountered in conventional methods, such as subject-specific or undersampling scale-specific requirements and long reconstruction time. The proposed method overcomes these limitations by leveraging prior knowledge of voxel-specific features and integrating a novel scale-embedded encoder module. This encoder generates scale-independent voxel-specific features from undersampled images, enabling robust reconstruction across various undersampling scales without requiring retraining for each specific scale or subject. The framework's INR model treats fully sampled MR images as a continuous function of spatial coordinates and prior voxel-specific features, efficiently reconstructing high-quality MR images from undersampled data. Extensive experiments on publicly available MRI datasets demonstrate the superior performance of the proposed method in reconstructing images at multiple acceleration factors (4x, 5x, and 6x), achieving higher evaluation metrics and visual fidelity compared to state-of-the-art methods. In terms of efficiency, this INR-based approach exhibits notable advantages, including reduced floating point operations and GPU usage, allowing for accelerated processing times while maintaining high reconstruction quality. The generalized design of the model significantly reduces computational resources and time consumption, making it more suitable for real-time clinical applications.
