Self-Supervised Joint Reconstruction and Denoising of T2-Weighted PROPELLER MRI of the Lungs at 0.55T

2025-07-18

AI Summary

This study addresses poor image quality, severe noise, and reconstruction artifacts in 0.55T low-field pulmonary T2-weighted PROPELLER MRI. To this end, we propose an unpaired, self-supervised framework jointly optimizing reconstruction and denoising. Methodologically, we exploit structural redundancy among k-space sub-blocks to design a block-wise k-space-driven loss function; integrate decoupled PROPELLER blade segmentation with an unfolding-based reconstruction network; and incorporate coil-domain MPPCA as a baseline. Crucially, the method operates without clean reference images, enabling simultaneous optimization of reconstruction fidelity and noise statistics. Quantitative evaluation demonstrates statistically significant superiority over conventional MPPCA (p < 0.001); qualitative assessment shows markedly improved sharpness and anatomical integrity, with high consistency against CT. Inter-reader agreement is substantial (κ = 0.55, 91% agreement). Moreover, the framework supports halved scan time while preserving diagnostic quality.

Technology Category

• Machine Learning: Unsupervised & Self-Supervised Learning
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Non-convex Optimization

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
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Purpose: This study aims to improve 0.55T T2-weighted PROPELLER lung MRI through a self-supervised joint reconstruction and denoising model. Methods: T2-weighted 0.55T lung MRI dataset including 44 patients with previous covid infection were used. A self-supervised learning framework was developed, where each blade of the PROPELLER acquisition was split along the readout direction into two partitions. One subset trains the unrolled reconstruction network, while the other subset is used for loss calculation, enabling self-supervised training without clean targets and leveraging matched noise statistics for denoising. For comparison, Marchenko-Pastur Principal Component Analysis (MPPCA) was performed along the coil dimension, followed by conventional parallel imaging reconstruction. The quality of the reconstructed lung MRI was assessed visually by two experienced radiologists independently. Results: The proposed self-supervised model improved the clarity and structural integrity of the lung images. For cases with available CT scans, the reconstructed images demonstrated strong alignment with corresponding CT images. Additionally, the proposed model enables further scan time reduction by requiring only half the number of blades. Reader evaluations confirmed that the proposed method outperformed MPPCA-denoised images across all categories (Wilcoxon signed-rank test, p<0.001), with moderate inter-reader agreement (weighted Cohen's kappa=0.55; percentage of exact and within +/-1 point agreement=91%). Conclusion: By leveraging intrinsic structural redundancies between two disjoint splits of k-space subsets, the proposed self-supervised learning model effectively reconstructs the image while suppressing the noise for 0.55T T2-weighted lung MRI with PROPELLER sampling.

Problem

• Improving 0.55T T2-weighted lung MRI clarity
• Self-supervised joint reconstruction and denoising model
• Reducing scan time with fewer PROPELLER blades

Innovation

• Self-supervised learning for MRI reconstruction
• PROPELLER acquisition split for denoising
• Unrolled network with matched noise statistics