Physics-Informed Joint Multi-TE Super-Resolution with Implicit Neural Representation for Robust Fetal T2 Mapping

2025-08-14

AI Summary

Fetal brain T2 mapping at low-field (0.55T) MRI is hindered by motion artifacts, low spatial resolution due to thick-slice acquisitions, and prolonged scan times with heightened motion sensitivity from repeated multi-echo-time (TE) sampling. To address these challenges, we propose a physics-guided implicit neural representation framework that jointly models multi-TE data, unifying slice-to-volume reconstruction, cross-TE information sharing, super-resolution, and T2 decay physical constraints within a single end-to-end optimization pipeline. Unlike conventional stepwise approaches, our method avoids error propagation and achieves significant improvements in T2 map quality on both simulated and in vivo fetal datasets. It enables, for the first time, high-fidelity in vivo fetal brain T2 mapping at 0.55T and reduces the required number of slice stacks by approximately 50%. This work establishes a novel paradigm for quantitative fetal brain development imaging at low-field MRI.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Machine Learning: Matrix & Tensor Methods
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

T2 mapping in fetal brain MRI has the potential to improve characterization of the developing brain, especially at mid-field (0.55T), where T2 decay is slower. However, this is challenging as fetal MRI acquisition relies on multiple motion-corrupted stacks of thick slices, requiring slice-to-volume reconstruction (SVR) to estimate a high-resolution (HR) 3D volume. Currently, T2 mapping involves repeated acquisitions of these stacks at each echo time (TE), leading to long scan times and high sensitivity to motion. We tackle this challenge with a method that jointly reconstructs data across TEs, addressing severe motion. Our approach combines implicit neural representations with a physics-informed regularization that models T2 decay, enabling information sharing across TEs while preserving anatomical and quantitative T2 fidelity. We demonstrate state-of-the-art performance on simulated fetal brain and in vivo adult datasets with fetal-like motion. We also present the first in vivo fetal T2 mapping results at 0.55T. Our study shows potential for reducing the number of stacks per TE in T2 mapping by leveraging anatomical redundancy.

Problem

• Improving fetal brain T2 mapping at mid-field MRI
• Reducing motion sensitivity and scan time in T2 mapping
• Enhancing reconstruction accuracy with physics-informed neural representations

Innovation

• Joint reconstruction across TEs for motion robustness
• Implicit neural representations with physics-informed regularization
• Reducing stacks per TE using anatomical redundancy