Aligning a pair of cross-modality images (e.g., MR-CT, CBCT-CT) is important, yet conventional approaches, including registration or image-to-image (I2I) translation methods often have limitations. To overcome these challenges, we introduce a "Register by Generation (RbG)" framework, a novel 2D deep learning approach designed to generate images that are structurally well-aligned with the fixed image while preserving the detailed intensity and contrast of the moving image, which we refer to as the reference image. Our approach operates in two sequential key stages: first, we employ a novel semi-global reference-augmented image synthesis network incorporating Patch Adaptive Instance Normalization (PAdaIN). This method leverages a down-sampled reference image to guide local adaptive synthesis, generating a more accurately aligned image with a reduced risk of hallucinations. In the second stage, we introduce a detailed refining reference-augmented network featuring a Deformation-Aware Cross-Attention (DACA) block, which aims to recover finer details and textures that may be missing from the initial stage. This unique component (DACA block) enables the transfer of corresponding relevant features from the reference image, effectively performing a "copy-and-paste" operation within the latent feature space. Additionally, we propose a novel combination of loss functions that enables self-supervised training on misaligned datasets, eliminating the need for pre-aligned data. We rigorously evaluate our method on multiple misaligned datasets using metrics focused on structural alignment and distributional consistency, demonstrating comprehensively superior performance. Furthermore, we test its robustness by simulating intentional misalignments in a well-aligned dataset. Additionally, experiments from a case study and downstream segmentation tasks highlight the broad applicability of our approach.

Multi-echo gradient-echo (mGRE)-based myelin water fraction (MWF) mapping is a promising myelin water imaging (MWI) modality but is vulnerable to noise and artifact corruption. The linear dimensionality reduction (LDR) method has recently shown improvements with regard to these challenges. However, the magnitude value based low rank operators have been shown to misestimate the MWF for regions with [Formula: see text] anisotropy. This paper presents a nonlinear dimensionality reduction (NLDR) method to estimate the MWF map better by encouraging nonlinear low dimensionality of mGRE signal sources. Specifically, we implemented a fully connected deep autoencoder to extract the low-dimensional features of complex-valued signals and incorporated a sparse regularization to separate the anomaly sources that do not reside in the low-dimensional manifold. Simulations and in vivo experiments were performed to evaluate the accuracy of the MWF map under various situations. The proposed NLDR-based MWF improves the accuracy of the MWF map over the conventional nonlinear least-squares method and the LDR-based MWF and maintains robustness against noise and artifact corruption.

In conventional gradient-echo myelin water imaging (GRE-MWI), myelin water fraction (MWF) is estimated by fitting the multi-echo gradient recalled echo (mGRE) signal to a pre-assumed numerical model (e.g., multi-component exponential curves or three component exponential curves). However, in mGRE, imaging artifacts (e.g., voxel spread function and physiological noise) and noise render the signal to deviate from the numerical model, leading to misfit of the model parameters. Here, as an alternative to the model-based GRE-MWI, a blind source separation (BSS) technique for the separation of multi-exponential mGRE signal is proposed. Among the various BSS techniques, a modified robust principal component analysis (rPCA) is presented to separate signal sources by enforcing the data-driven properties such as “low rankness” and “sparsity.” Considering the signal evolution of T*2relaxation (i.e., non-negative exponential decay), low rankness of exponential decay was enforced by nonnegative matrix factorization (NMF) and hankelization. This method provides the separation of slow-decaying, fast-decaying exponential components and artifact components from mGRE images. After the separation, MWF map is reconstructed as the ratio of the fast-decaying component to the total decaying components. The proposed method was demonstrated in numerical simulations and in vivo scans. The method provided a robust estimation of MWF in the presence of statistical noise and imaging artifacts.

Magnetic resonance electrical property tomography (MREPT) is a technique used to extract the electrical properties of tissues (conductivity in particular) using a magnetic resonance imaging system. In this paper, we propose an improved data acquisition scheme for the electrical property tomography technique by utilizing T2modulation in fast spin echo (FSE) imaging. This technique was motivated by a numerical analysis of conductivity reconstruction in the frequency domain; results reveal the spatial frequency-dependent noise texture of conventional methods. A data-acquisition scheme using the FSE sequence was formulated to concentrate the signal within a specific frequency range where notable noise amplification is observed in the conventional method. Through numerical studies, the performance of the proposed acquisition was investigated. Furthermore, a compensation scheme was applied to reduce quantification errors due to tissue-specific T2modulation, which is inherent in FSE imaging. The technique was applied to phantom and in vivo experiments. Results showed improved conductivity contrasts in both experiments, as compared with conventional MREPT methods.