Diffusion Probabilistic Generative Models for Accelerated, in-NICU Permanent Magnet Neonatal MRI

2025-05-21

AI Summary

In neonatal intensive care units (NICUs), low-field permanent-magnet MRI (1T) suffers from low signal-to-noise ratio (SNR) and limited coil configurations, resulting in prohibitively long scan times—posing significant challenges for fragile neonates. Method: We propose the first diffusion probabilistic reconstruction framework tailored to real-world clinical 1T neonatal MRI data. Our approach employs a self-supervised denoising pre-trained multi-resolution U-Net, decoupling class-conditional embedding from the forward measurement model. It supports dual acceleration factors (e.g., 1.5×) within a single model without retraining and incorporates Bayesian posterior sampling averaging to enhance robustness. Contribution/Results: At 1.5× undersampling, reconstructed images received clinical approval from pediatric neuroradiologists. Quantitatively, our method significantly outperforms baseline methods across standard metrics (e.g., PSNR, SSIM). Moreover, it demonstrates strong generalization—adapting seamlessly to varying acceleration factors without model retraining.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Neuro-Symbolic Learning
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Purpose: Magnetic Resonance Imaging (MRI) enables non-invasive assessment of brain abnormalities during early life development. Permanent magnet scanners operating in the neonatal intensive care unit (NICU) facilitate MRI of sick infants, but have long scan times due to lower signal-to-noise ratios (SNR) and limited receive coils. This work accelerates in-NICU MRI with diffusion probabilistic generative models by developing a training pipeline accounting for these challenges. Methods: We establish a novel training dataset of clinical, 1 Tesla neonatal MR images in collaboration with Aspect Imaging and Sha'are Zedek Medical Center. We propose a pipeline to handle the low quantity and SNR of our real-world dataset (1) modifying existing network architectures to support varying resolutions; (2) training a single model on all data with learned class embedding vectors; (3) applying self-supervised denoising before training; and (4) reconstructing by averaging posterior samples. Retrospective under-sampling experiments, accounting for signal decay, evaluated each item of our proposed methodology. A clinical reader study with practicing pediatric neuroradiologists evaluated our proposed images reconstructed from 1.5x under-sampled data. Results: Combining all data, denoising pre-training, and averaging posterior samples yields quantitative improvements in reconstruction. The generative model decouples the learned prior from the measurement model and functions at two acceleration rates without re-training. The reader study suggests that proposed images reconstructed from approximately 1.5x under-sampled data are adequate for clinical use. Conclusion: Diffusion probabilistic generative models applied with the proposed pipeline to handle challenging real-world datasets could reduce scan time of in-NICU neonatal MRI.

Problem

• Accelerates NICU neonatal MRI with diffusion models
• Handles low SNR and limited data in MRI scans
• Reduces scan time while maintaining clinical adequacy

Innovation

• Modified network architectures for varying resolutions
• Single model trained with class embedding vectors
• Self-supervised denoising before training