Single-shell to multi-shell dMRI transformation using spatial and volumetric multilevel hierarchical reconstruction framework

A hybrid network for fiber orientation distribution reconstruction employing multi-scale information

BACKGROUND

Accurate fiber orientation distribution (FOD) is crucial for resolving complex neural fiber structures. However, existing reconstruction methods often fail to integrate both global and local FOD information, as well as the directional information of fixels, which limits reconstruction accuracy. Additionally, these methods overlook the spatial positional relationships between voxels, resulting in extracted features that lack continuity. In regions with signal distortion, many methods also exhibit issues with reconstruction artifacts.

PURPOSE

This study addresses these challenges by introducing a new neural network called Fusion-Net.

METHODS

Fusion-Net comprises both the FOD reconstruction network and the peak direction estimation network. The FOD reconstruction network efficiently fuses the global and local features of the FOD, providing these features with spatial positional information through a competitive coordinate attention mechanism and a progressive updating mechanism, thus ensuring feature continuity. The peak direction estimation network redefines the task of estimating fixel peak directions as a multi-class classification problem. It uses a direction-aware loss function to supply directional information to the FOD reconstruction network. Additionally, we introduce a larger input scale for Fusion-Net to compensate for local signal distortion by incorporating more global information.

RESULTS

Experimental results demonstrate that the rich FOD features contribute to promising performance in Fusion-Net. The network effectively utilizes these features to enhance reconstruction accuracy while incorporating more global information, effectively mitigating the issue of local signal distortion.

CONCLUSIONS

This study demonstrates the feasibility of Fusion-Net for reconstructing FOD, providing reliable references for clinical applications.

Geometric deep learning for diffusion MRI signal reconstruction with continuous samplings (DISCUS)

Diffusion-weighted magnetic resonance imaging (dMRI) permits a detailed in-vivo analysis of neuroanatomical microstructure, invaluable for clinical and population studies. However, many measurements with different diffusion-encoding directions and possibly b-values are necessary to infer the underlying tissue microstructure within different imaging voxels accurately. Two challenges particularly limit the utility of dMRI: long acquisition times limit feasible scans to only a few directional measurements, and the heterogeneity of acquisition schemes across studies makes it difficult to combine datasets. Left unaddressed by previous learning-based methods that only accept dMRI data adhering to the specific acquisition scheme used for training, there is a need for methods that accept and predict signals for arbitrary diffusion encodings. Addressing these challenges, we describe the first geometric deep learning method for continuous dMRI signal reconstruction for arbitrary diffusion sampling schemes for both the input and output. Our method combines the reconstruction accuracy and robustness of previous learning-based methods with the flexibility of model-based methods, for example, spherical harmonics or SHORE. We demonstrate that our method outperforms model-based methods and performs on par with discrete learning-based methods on single-, multi-shell, and grid-based diffusion MRI datasets. Relevant for dMRI-derived analyses, we show that our reconstruction translates to higher-quality estimates of frequently used microstructure models compared to other reconstruction methods, enabling high-quality analyses even from very short dMRI acquisitions.

Effects of mixed metal exposures on MRI diffusion features in the medial temporal lobe

Background

Environmental exposure to metal mixtures is common and may be associated with increased risk for neurodegenerative disorders including Alzheimer's disease.

Objective

This study examined associations of mixed metal exposures with medial temporal lobe (MTL) MRI structural metrics and neuropsychological performance.

Methods

Metal exposure history, whole blood metal, and neuropsychological tests were obtained from subjects with/without a history of mixed metal exposure from welding fumes (42 exposed subjects; 31 controls). MTL structures (hippocampus, entorhinal and parahippocampal cortices) were assessed by morphologic (volume, cortical thickness) and diffusion tensor imaging [mean (MD), axial (AD), radial diffusivity (RD), and fractional anisotropy (FA)] metrics. In exposed subjects, correlation, multiple linear, Bayesian kernel machine regression, and mediation analyses were employed to examine effects of single- or mixed-metal predictor(s) and their interactions on MTL structural and neuropsychological metrics; and on the path from metal exposure to neuropsychological consequences.

Results

Compared to controls, exposed subjects had higher blood Cu, Fe, K, Mn, Pb, Se, and Zn levels (p's<0.026) and poorer performance in processing/psychomotor speed, executive, and visuospatial domains (p's<0.046). Exposed subjects displayed higher MD, AD, and RD in all MTL ROIs (p's<0.040) and lower FA in entorhinal and parahippocampal cortices (p's<0.033), but not morphological differences. Long-term mixed-metal exposure history indirectly predicted lower processing speed performance via lower parahippocampal FA (p=0.023). Higher whole blood Mn and Cu predicted higher entorhinal diffusivity (p's<0.043) and lower Delayed Story Recall performance (p=0.007) without overall metal mixture or interaction effects.

Discussion

Mixed metal exposure predicted MTL structural and neuropsychological features that are similar to Alzheimer's disease at-risk populations. These data warrant follow-up as they may illuminate the path for environmental exposure to Alzheimer's disease-related health outcomes.

Computational approaches for the reconstruction of optic nerve fibers along the visual pathway from medical images: a comprehensive review

Optic never fibers in the visual pathway play significant roles in vision formation. Damages of optic nerve fibers are biomarkers for the diagnosis of various ophthalmological and neurological diseases; also, there is a need to prevent the optic nerve fibers from getting damaged in neurosurgery and radiation therapy. Reconstruction of optic nerve fibers from medical images can facilitate all these clinical applications. Although many computational methods are developed for the reconstruction of optic nerve fibers, a comprehensive review of these methods is still lacking. This paper described both the two strategies for optic nerve fiber reconstruction applied in existing studies, i.e., image segmentation and fiber tracking. In comparison to image segmentation, fiber tracking can delineate more detailed structures of optic nerve fibers. For each strategy, both conventional and AI-based approaches were introduced, and the latter usually demonstrates better performance than the former. From the review, we concluded that AI-based methods are the trend for optic nerve fiber reconstruction and some new techniques like generative AI can help address the current challenges in optic nerve fiber reconstruction.

TrGANet: Transforming 3T to 7T dMRI using Trapezoidal Rule and Graph based Attention Modules

Diffusion MRI (dMRI) is a non-invasive tool for assessing the white matter region of the brain by approximating the fiber streamlines, structural connectivity, and estimation of microstructure. This modality can yield useful information for diagnosing several mental diseases as well as for surgical planning. The higher angular resolution diffusion imaging (HARDI) technique is helpful in obtaining more robust fiber tracts by getting a good approximation of regions where fibers cross. Moreover, HARDI is more sensitive to tissue changes and can accurately represent anatomical details in the human brain at higher magnetic strengths. In other words, magnetic strengths affect the quality of the image, and hence high magnetic strength has good tissue contrast with better spatial resolution. However, a higher magnetic strength scanner (like 7T) is costly and unaffordable to most hospitals. Hence, in this work, we have proposed a novel CNN architecture for the transformation of 3T to 7T dMRI. Additionally, we have also reconstructed the multi-shell multi-tissue fiber orientation distribution function (MSMT fODF) at 7T from single-shell 3T. The proposed architecture consists of a CNN-based ODE solver utilizing the Trapezoidal rule and graph-based attention layer alongwith L₁ and total variation loss. Finally, the model has been validated on the HCP data set quantitatively and qualitatively.

VRfRNet: Volumetric ROI fODF reconstruction network for estimation of multi-tissue constrained spherical deconvolution with only single shell dMRI

Diffusion MRI (dMRI) is one of the most popular techniques for studying the brain structure, mainly the white matter region. Among several sampling methods in dMRI, the high angular resolution diffusion imaging (HARDI) technique has attracted researchers due to its more accurate fiber orientation estimation. However, the current single-shell HARDI makes the intravoxel structure challenging to estimate accurately. While multi-shell acquisition can address this problem, it takes a longer scanning time, restricting its use in clinical applications. In addition, most existing dMRI scanners with low gradient-strengths often acquire single-shell up to b=1000s/mm² because of signal-to-noise ratio issues and severe image artefacts. Hence, we propose a novel generative adversarial network, VRfRNet, for the reconstruction of multi-shell multi-tissue fiber orientation distribution function from single-shell HARDI volumes. Such a transformation learning is performed in the spherical harmonics (SH) space, as raw input HARDI volume is transformed to SH coefficients to soften gradient directions. The proposed VRfRNet consists of several modules, such as multi-context feature enrichment module, feature level attention, and softmax level attention. In addition, three loss functions have been used to optimize network learning, including L₁, adversarial, and total variation. The network is trained and tested using standard qualitative and quantitative performance metrics on the publicly available HCP data-set.