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

TL;DR

This paper introduces a self-supervised learning approach for joint reconstruction and denoising of low-field T2-weighted PROPELLER lung MRI, improving image quality and enabling faster scans without clean training targets.

Contribution

The study presents a novel self-supervised framework that leverages data redundancy in PROPELLER MRI for improved reconstruction and denoising at 0.55T, eliminating the need for clean training data.

Findings

Enhanced image clarity and structural integrity in reconstructed lung MRI.

Strong alignment of MRI with CT images in cases with available scans.

Outperformed traditional MPPCA-denoising in quantitative assessments.

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.