arXiv subjects

Istvan Homolya

Publications and source records attributed to Istvan Homolya.

3 recordsLinked to original sources

arXiv2025

Controlling spatial correlation in k-space interpolation networks for MRI reconstruction: denoising versus apparent blurring

Purpose: Interpretability is essential for the clinical adoption of state-of-the-art machine learning (ML) methods in magnetic resonance imaging (MRI). Conventional evaluation of ML reconstructions relies heavily on aggregate image metrics that require fully sampled references. These metrics, inherited from classical image processing and natural image ML, often overlook the critical challenge of noise amplification specific to medical image reconstruction. This study aims to analyze the influence of nonlinear activations on spatial noise variance distribution of k-space interpolation networks (RAKI) and to provide a framework for incorporating variance maps during network training. Methods: We present an analytical framework that decomposes pixel-level noise variance into components reflecting linear and nonlinear characteristics of RAKI. By applying automatic differentiation on the image-space equivalent of the network, variance maps are computed during each training iteration, enabling runtime quality assessment beyond data consistency. We introduce apparent blurring, quantifying nonlinear signal mixing without dependence on reference images. By incorporating variance maps into the traning loss as regularizers, our self-informed RAKI architecture (G-factor-informed RAKI, GIF-RAKI) can directly integrate updated noise characteristics during runtime. Results: Experimental results demonstrate that variance components quantitatively explain network behavior. GIF-RAKI outperforms conventional RAKI variants in image fidelity and noise suppression. Conclusion: Our methodology advances practical and theoretical aspects of ML-based MRI reconstruction by reinstating reconstruction noise characterization as a cornerstone for performance evaluation, eliminating the need for fully sampled references. GIF-RAKI also enables optimization of the trade-off between denoising and apparent blurring.

physics.med-ph↗

arXiv2024

Phantom-based gradient waveform measurements with compensated variable-prephasing: Description and application to EPI at 7T

Purpose: Introducing "compensated variable-prephasing" (CVP), a phantom-based method for gradient waveform measurements. The technique is based on the "variable-prephasing" (VP) method, but takes into account the effects of all gradients involved in the measurement. Methods: We conducted measurements of a trapezoidal test gradient, and of an EPI readout gradient train with three approaches: VP, CVP, and "fully compensated variable-prephasing" (FCVP). We compared them to one another and to predictions based on the gradient system transfer function. Furthermore, we used the measured and predicted EPI gradients for trajectory corrections in phantom images on a 7T scanner. Results: The VP gradient measurements are confounded by lingering oscillations of the prephasing gradients, which are compensated in the CVP and FCVP measurements. FCVP is vulnerable to a sign asymmetry in the gradient chain. However, the trajectories determined by all three methods resulted in comparably high EPI image quality. Conclusion: We present a new approach allowing for phantom-based gradient waveform measurements with high precision, which can be useful for trajectory corrections in non-Cartesian or single-shot imaging techniques. In our experimental setup, the proposed "compensated variable-prephasing" method provided the most reliable gradient measurements of the different techniques we compared.

physics.med-ph↗

arXiv2024

Image space formalism of convolutional neural networks for k-space interpolation

Purpose: Noise resilience in image reconstructions by scan-specific robust artificial neural networks for k-space interpolation (RAKI) is linked to nonlinear activations in k-space. To gain a deeper understanding of this relationship, an image space formalism of RAKI is introduced for analyzing noise propagation analytically, identifying and characterizing image reconstruction features and to describe the role of nonlinear activations in a human readable manner. Methods: The image space formalism for RAKI inference is employed by expressing nonlinear activations in k-space as element-wise multiplications with activation masks, which transform into convolutions in image space. Jacobians of the de-aliased, coil-combined image relative to the aliased coil images can be expressed algebraically, and thus, the noise amplification is quantified analytically (g-factor maps). We analyze the role of nonlinearity for noise resilience by controlling the degree of nonlinearity in the reconstruction model via the negative slope parameter in leaky ReLU. Results: The analytical g-factor maps correspond with those obtained from Monte Carlo simulations and from an auto differentiation approach for in vivo brain images. Apparent blurring and contrast loss artifacts are identified as implications of enhanced noise resilience. These residual artifacts can be traded against noise resilience by adjusting the degree of nonlinearity in the model (Tikhonov-like regularization) in case of limited training data. The inspection of image space activations reveals an autocorrelation pattern leading to a potential center artifact. Conclusion: The image space formalism of RAKI provides the means for analytical quantitative noisepropagation analysis and human-readable visualization of the effects of the nonlinear activation functions in k-space.

cs.CV↗