Rapid Whole Brain Mesoscale In-vivo MR Imaging using Multi-scale Implicit Neural Representation

2025-02-12

AI Summary

Multi-view thick-slice MRI suffers from prolonged acquisition time and a fundamental trade-off between reconstruction resolution and signal-to-noise ratio (SNR). To address this, we propose ROVER-MRI, an unsupervised rotational-view super-resolution framework that pioneers the integration of implicit neural representations (INRs) with multi-scale thick-slice data fusion. ROVER-MRI enables in vivo human whole-brain T2-weighted imaging at 180 μm isotropic resolution in just 17 minutes—without requiring image registration or prior anatomical knowledge—and achieves high-fidelity super-resolution fusion via unsupervised neural reconstruction. Validated on a 7T MRI system, ROVER-MRI reduces relative reconstruction error by 22.4% and narrows the point spread function full width at half maximum (FWHM) by 7.5% compared to LS-SRR; it also yields substantial improvements in SNR and anatomical detail visibility while doubling scanning efficiency. This work establishes a novel paradigm for rapid, mesoscale whole-brain MRI.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Purpose: To develop and validate a novel image reconstruction technique using implicit neural representations (INR) for multi-view thick-slice acquisitions while reducing the scan time but maintaining high signal-to-noise ratio (SNR). Methods: We propose Rotating-view super-resolution (ROVER)-MRI, an unsupervised neural network-based algorithm designed to reconstruct MRI data from multi-view thick slices, effectively reducing scan time by 2-fold while maintaining fine anatomical details. We compare our method to both bicubic interpolation and the current state-of-the-art regularized least-squares super-resolution reconstruction (LS-SRR) technique. Validation is performed using ground-truth ex-vivo monkey brain data, and we demonstrate superior reconstruction quality across several in-vivo human datasets. Notably, we achieve the reconstruction of a whole human brain in-vivo T2-weighted image with an unprecedented 180{mu}m isotropic spatial resolution, accomplished in just 17 minutes of scan time on a 7T MRI scanner. Results: ROVER-MRI outperformed LS-SRR method in terms of reconstruction quality with 22.4% lower relative error (RE) and 7.5% lower full-width half maximum (FWHM) indicating better preservation of fine structural details in nearly half the scan time. Conclusion: ROVER-MRI offers an efficient and robust approach for mesoscale MR imaging, enabling rapid, high-resolution whole-brain scans. Its versatility holds great promise for research applications requiring anatomical details and time-efficient imaging.

Problem

• Develops rapid whole-brain MR imaging technique
• Reduces scan time while maintaining high SNR
• Achieves high-resolution in-vivo brain imaging

Innovation

• Implicit neural representation reconstruction
• Rotating-view super-resolution algorithm
• Rapid high-resolution whole-brain scan