Kernel Principal Component Analysis of Coil Compression in Parallel Imaging

Optimization of through-time radial GRAPPA with coil compression and weight sharing

PURPOSE

This work proposes principal component analysis (PCA) coil compression and weight sharing to reduce acquisition and reconstruction time of through-time radial GRAPPA.

METHODS

Through-time radial GRAPPA enables ungated free-breathing motion-resolved cardiac imaging but requires a long calibration acquisition and GRAPPA weight calculation time. PCA coil compression reduces calibration data requirements and associated acquisition time, and weight sharing reduces the number of unique GRAPPA weight sets and associated weight computation time. In vivo cardiac data reconstructed with coil compression and weight sharing are compared to a gold standard to demonstrate improvement in calibration acquisition and reconstruction performance with minimal loss of image quality.

RESULTS

Coil compression from 30 physical to 12 virtual coils (90% of signal variance) decreases requisite calibration data by 60%, reducing calibration acquisition time to 6.7 s/slice from 31.5 s/slice reported in original through-time radial GRAPPA work. Resulting images have small increase in RMS error (RMSE). Reconstruction with a weight sharing factor of 8 results in eight-fold reduction in GRAPPA weight calculation time with a comparable RMSE to reconstructions with no weight sharing. Optimized parameters for coil compression and weight sharing applied to reconstructions enables images to be collected with a temporal resolution of 66 ms/frame and spatial resolution of 2.34 × 2.34 mm while reducing calibration acquisition time from 34 to 6.7 s, weight calculation time from 200 to 3 s, and weight application time 18 to 5 s.

CONCLUSION

Coil compression and weight sharing applied to through-time radial GRAPPA enables fast free-breathing ungated cardiac cine without compromising image quality.

Interpretable Dimension Reduction for MRI Channel Suppression

Channel suppression can reduce the redundant information in multiple channel receiver coils and accelerate reconstruction speed to meet real-time imaging requirements. The principal component analysis has been used for channel suppression, but it is difficult to be interpreted because all channels contribute to principal components. Furthermore, the importance of interpretability in machine learning has recently attracted increasing attention in radiology. To improve the interpretability of PCA-based channel suppression, a sparse PCA method is proposed to reduce the most coils' loadings to be zero. Channel suppression is formulated as solving a nonlinear eigenvalue problem using the inverse power method instead of the direct matrix decomposition. Experimental results of in vivo data show that the sparse PCA-based channel suppression not only improves the interpretability with sparse channels, but also improves reconstruction quality compared to the standard PCA-based reconstruction with the similar reconstruction time.

Virtual Conjugate Coil for Improving KerNL Reconstruction

Ker NL is a general kernel-based framework for auto calibrated reconstruction method, which does not need any explicit formulas of the kernel function for characterizing nonlinear relationships between acquired and unacquired k-space data. It is non-iterative without requiring a large amount of computational costs. Since the limited autocalibration signals (ACS) are acquired to perform KerNL calibration and the calibration suffers from the overfitting problem, more training data can improve the kernel model accuracy. In this work, virtual conjugate coil data are incorporated into the KerNL calibration and estimation process for enhancing reconstruction performance. Experimental results show that the proposed method can further suppress noise and aliasing artifacts with fewer ACS data and higher acceleration factors. Computation efficiency is still retained to keep fast reconstruction with the random projection.

A dual-interpolator method for improving parallel MRI reconstruction

Autocalibration signal is acquired in the k-space-based parallel MRI reconstruction for estimating interpolation coefficients and reconstructing missing unacquired data. Many ACS lines can suppress aliasing artifacts and noise by covering the low-frequency signal region. However, more ACS lines will delay the data acquisition process and therefore elongate the scan time. Furthermore, a single interpolator is often used for recovering missing k-space data, and model error may exist if the single interpolator size is not selected appropriately. In this work, based on the idea of the disagreement-based semi-supervised learning, a dual-interpolator strategy is proposed to collaboratively reconstruct missing k-space data. Two interpolators with different sizes are alternatively applied to estimate and re-estimate missing data in k-space. The disagreement between two interpolators is converged and real missing values are co-estimated from two views. The experimental results show that the proposed method outperforms GRAPPA, SPIRiT, and Nonlinear GRAPPA methods using relatively low number of ACS data, and reduces aliasing artifacts and noise in reconstructed images.

Group feature selection for enhancing information gain in MRI reconstruction

Magnetic resonance imaging (MRI) has revolutionized the radiology. As a leading medical imaging modality, MRI not only visualizes the structures inside body, but also produces functional imaging. However, due to the slow imaging speed constrained by the MR physics, MRI cost is expensive, and patient may feel not comfortable in a scanner for a long time. Parallel MRI has accelerated the imaging speed through the sub-Nyquist sampling strategy and the missing data are interpolated by the multiple coil data acquired. Kernel learning has been used in the parallel MRI reconstruction to learn the interpolation weights and re-construct the undersampled data. However, noise and aliasing artifacts still exist in the reconstructed image and a large number of auto-calibration signal lines are needed. To further improve the kernel learning-based MRI reconstruction and accelerate the speed, this paper proposes a group feature selection strategy to improve the learning performance and enhance the reconstruction quality. An explicit kernel mapping is used for selecting a subset of features which contribute most to estimate the missing k-space data. The experimental results show that the learning behaviours can be better predicted and therefore the reconstructed image quality is improved.