arXiv subjects

Susie Y. Huang

Publications and source records attributed to Susie Y. Huang.

9 recordsLinked to original sources

arXiv2026

MWF-MIMOSA for efficient simultaneous relaxometry and myelin water fraction mapping

Quantitative magnetic resonance imaging (qMRI) provides improved sensitivity and specificity to tissue composition and pathological alterations compared with conventional contrast-weighted imaging. Among various qMRI biomarkers, myelin water imaging is of particular interest because myelin plays a central role in brain function and its alteration is closely associated with many neurological diseases. However, conventional myelin water fraction (MWF) mapping techniques are often limited by long scan times, low spatial resolution, reduced signal-to-noise ratio (SNR), and high specific absorption rate (SAR). Here, we propose MWF-MIMOSA for efficient simultaneous T1, T2, T2* mapping, magnetic susceptibility source separation, and MWF estimation. To achieve this, multi-contrast and multi-slice zero-shot self-supervised learning (MZS-SSL) was used to jointly reconstruct whole-brain complex-valued images. To improve computational efficiency of the parameter estimation step, a multilayer perceptron (MLP) was trained within the GACELLE GPU-accelerated parameter estimation framework to circumvent the computationally intensive Bloch simulation process, resulting in a >100-fold computational speed-up in MWF estimation. Numerical simulations were performed to evaluate the accuracy and precision of MWF-MIMOSA, and in-vivo results further demonstrated its robustness. Comparison with existing myelin water imaging methods showed that MWF-MIMOSA is highly correlated with established approaches, while providing complementary quantitative parameter maps at higher spatial resolution and with shorter scan times. Notably, simultaneous multi-parametric mapping was achieved in 5 min at 1 mm isotropic resolution, and in 10 min at 0.7 mm isotropic resolution. These results demonstrate the potential of MWF-MIMOSA for fast, high-resolution simultaneous relaxometry and myelin water imaging.

physics.med-ph↗

arXiv2026

Reduced NEXI protocol for the quantification of human gray matter microstructure on the Connectome 2.0 scanner

Biophysical diffusion MRI models like Neurite Exchange Imaging (NEXI) are essential for probing gray matter microstructure, estimating compartment diffusivities, neurite fraction, and exchange time. However, NEXI's multi-shell, multi-diffusion-time requirements cause prohibitively long acquisitions. Leveraging the Connectome 2.0 ultra-high gradient scanner, we developed a time-efficient protocol using an Explainable AI (XAI) framework. Combining XGBoost, SHAP, and Recursive Feature Elimination trained on synthetic signals, XAI identified an optimal 8-feature subset, cutting scan time from 27 to 14 minutes. Validated in vivo in seven healthy participants, the XAI protocol was benchmarked against the full 15-feature acquisition, a Cram'er-Rao Lower Bound (CRLB) theoretical optimum, and two heuristics ("Mid-Range" and "Corner"). It robustly reproduced parameter estimates and maintained test-retest reproducibility. Remarkably, the XAI selection converged to the CRLB optimum. This validates XAI's optimality while highlighting its main advantage: achieving gold-standard optimization without complex analytical Jacobians, making it easily adaptable to numerical models or complex noise where CRLB is intractable. Furthermore, XAI showed superior in vivo robustness over heuristics: "Mid-Range" sampling yielded biased exchange time estimates from insufficient temporal diversity, while "Corner" sampling gave unstable intra-neurite diffusivity estimates (5-fold higher CV) due to noise sensitivity. Ultimately, this robust 14-minute protocol accelerates exchange-sensitive microstructural mapping, establishing a model-agnostic optimization framework adaptable to future ultra-high gradient systems and existing clinical scanners.

physics.med-ph↗

arXiv2026

Dependence of the extra-cellular diffusion coefficient on the fractions of neurites and cell bodies in gray matter

Purpose: The dependence of the long-time (tortuosity) limit of the extra-cellular diffusivity on the intra-cellular volume fraction is of fundamental importance for microstructure modeling. While such dependencies have been explored for the white matter, the tortuosity limit in gray matter is unknown due to complex cell composition and geometry. Here we rationalize and validate numerically the analytical relation between the extra-cellular diffusivity and intra-cellular fractions of cell bodies (somas) and neurites. Methods: The tortuosity relation for extra-cellular diffusivity qualitatively follows from effective medium theory, coarse-grained by diffusion outside somas (spheres) and neurites (cylinders), respectively. This problem is equivalent to finding the overall conductivity in a medium of grains in a matrix, with methodology dating back to the 19th century. We extend the effective medium methodology to populations of impermeable spheres and randomly oriented cylinders with various volume fractions, yielding closed-form expressions corroborated by Monte Carlo simulations. Results: We establish the power-law scaling of the extra-cellular diffusivity with the volume fractions of the extra-soma and extra-neurite spaces. We further evaluate the proposed framework using simulations in realistic tissue geometries. Conclusion: Theory and simulations relate extra-cellular tortuosity to soma and neurite fractions, potentially offering a diffusion MRI protocol design optimized for in vivo assessment of soma size and soma/neurite fractions within clinical scan times. Such in vivo measurements can be used to study development, aging and neurodegenerative disorders.

physics.bio-ph↗

arXiv2026

TRACED: In vivo imaging of extracellular intrinsic diffusivity, tortuosity, cell size distribution and cell density in human glioma patients

The lack of analytical models describing diffusion time dependence at intermediate time scales in complex tissue microstructure limits the accurate quantification of extracellular diffusivity and tissue microstructure. We introduce TRACED, a biophysical model that incorporates diffusion time dependence in cell distributions to quantify pathologically-relevant properties in solid tumors. Neural networks were trained on Monte Carlo diffusion simulations using sphere distribution-based geometries to enable the rapid computation of time-dependent diffusion MRI signals in cell populations of variable cell size. Model sensitivity and fit performance were assessed via simulation. Diffusion data from eight mixed-grade glioma patients was fitted using the TRACED model. Data fitting was performed using a novel physics-informed transfer learning pipeline, Sim2PINN. In two patients, cell size measurements were compared directly with image-localized histology. Simulation results indicate improved parameter estimation compared to the simple two-compartment model. TRACED enabled the simultaneous in vivo quantification of intracellular volume fraction, cell size distribution, extracellular intrinsic diffusivity, and tortuosity in glioma patients. Neural network implementations of diffusion time-dependence and tortuosity showed behavior consistent with coarse-graining and effective medium theory, respectively. Future work will explore the clinical utility of TRACED parameters in additional patients.

physics.med-ph↗

arXiv2025

GACELLE: GPU-accelerated tools for model parameter estimation and image reconstruction

Quantitative MRI (qMRI) offers tissue-specific biomarkers that can be tracked over time or compared across populations; however, its adoption in clinical research is hindered by significant computational demands of parameter estimation. Images acquired at high spatial resolution or requiring fitting multiple parameters often require lengthy processing time, constraining their use in routine pipelines and slowing methodological innovation and clinical translation. We present GACELLE, an open source, GPU-accelerated framework for high-throughput qMRI analysis. GACELLE provides a stochastic gradient descent optimiser and a stochastic sampler in MATLAB, enabling fast parameter mapping, improved estimation robustness via spatial regularisation, and uncertainty quantification. GACELLE prioritises accessibility: users only need to provide a forward signal model, while GACELLE's backend manages computational parallelisation, automatic parameter updates, and memory-batching. The stochastic solver performs fully vectorised Markov chain Monte Carlo with identical likelihood on CPU and GPU, ensuring reproducibility across hardware. Benchmarking demonstrates up to 451-fold acceleration for the stochastic gradient descent solver and 14,380-fold acceleration for stochastic sampling compared to CPU-based estimation, without compromising accuracy. We demonstrated GACELLE's versatility on three representative qMRI models and on an image reconstruction task. Across these applications, GACELLE improves parameter precision, enhances test-retest reproducibility, and reduces noise in quantitative maps. By combining speed, usability and flexibility, GACELLE provides a generalisable optimisation framework for medical image analysis. It lowers the computational barrier for qMRI, paving the way for reproducible biomarker development, large-scale imaging studies, and clinical translation.

eess.IV↗

arXiv2025

Interplay between MRI-based axon diameter and myelination estimates in macaque and human brain

Axon diameter and myelin thickness affect the conduction velocity of action potentials in the nervous system. Imaging them non-invasively with MRI-based methods is thus valuable for studying brain microstructure and function. Electron microscopy studies suggest that axon diameter and myelin thickness are closely related to each other. However, the relationship between MRI-based estimates of these microstructural measures, known to be relative indices, have not been investigated across the brain mainly due to methodological limitations. In recent years, studies using ultra-high gradient strength diffusion MRI (dMRI) have demonstrated improved estimation of axon diameter index across white-matter (WM) tracts in the human brain, making such investigations feasible. In this study, we aim to investigate relationships between tissue microstructure properties across white-matter tracts, as estimated with MRI-based methods. We collected dMRI with ultra-high gradient strength and multi-echo spin-echo MRI on ex vivo macaque and human brain samples on a preclinical scanner. From these data, we found that the correlations between axon diameter index and other microstructural imaging parameters were weak but consistent across WM tracts in samples estimated with sufficient signal to noise ratio. In well-myelinated regions, tissue voxels with larger axon diameter indices were associated with lower packing density, lower MWF and a tendency of higher g-ratio. We also found that intra-axonal signal fractions and MWF were not consistently correlated when assessed in different samples. Overall, the findings suggest that MRI-based axon geometry and myelination measures can provide complementary information about fiber morphology, and the relationships between these measures agree with prior electron microscopy studies in smaller field of views.

physics.med-ph↗

arXiv2021

SDnDTI: Self-supervised deep learning-based denoising for diffusion tensor MRI

The noise in diffusion-weighted images (DWIs) decreases the accuracy and precision of diffusion tensor magnetic resonance imaging (DTI) derived microstructural parameters and leads to prolonged acquisition time for achieving improved signal-to-noise ratio (SNR). Deep learning-based image denoising using convolutional neural networks (CNNs) has superior performance but often requires additional high-SNR data for supervising the training of CNNs, which reduces the practical feasibility. We develop a self-supervised deep learning-based method entitled "SDnDTI" for denoising DTI data, which does not require additional high-SNR data for training. Specifically, SDnDTI divides multi-directional DTI data into many subsets, each consisting of six DWI volumes along optimally chosen diffusion-encoding directions that are robust to noise for the tensor fitting, and then synthesizes DWI volumes along all acquired directions from the diffusion tensors fitted using each subset of the data as the input data of CNNs. On the other hand, SDnDTI synthesizes DWI volumes along acquired diffusion-encoding directions with higher SNR from the diffusion tensors fitted using all acquired data as the training target. SDnDTI removes noise from each subset of synthesized DWI volumes using a deep 3-dimensional CNN to match the quality of the cleaner target DWI volumes and achieves even higher SNR by averaging all subsets of denoised data. The denoising efficacy of SDnDTI is demonstrated on two datasets provided by the Human Connectome Project (HCP) and the Lifespan HCP in Aging. The SDnDTI results preserve image sharpness and textural details and substantially improve upon those from the raw data. The results of SDnDTI are comparable to those from supervised learning-based denoising and outperform those from state-of-the-art conventional denoising algorithms including BM4D, AONLM and MPPCA.

eess.IV↗

arXiv2021

SRDTI: Deep learning-based super-resolution for diffusion tensor MRI

High-resolution diffusion tensor imaging (DTI) is beneficial for probing tissue microstructure in fine neuroanatomical structures, but long scan times and limited signal-to-noise ratio pose significant barriers to acquiring DTI at sub-millimeter resolution. To address this challenge, we propose a deep learning-based super-resolution method entitled "SRDTI" to synthesize high-resolution diffusion-weighted images (DWIs) from low-resolution DWIs. SRDTI employs a deep convolutional neural network (CNN), residual learning and multi-contrast imaging, and generates high-quality results with rich textural details and microstructural information, which are more similar to high-resolution ground truth than those from trilinear and cubic spline interpolation.

eess.IV↗

arXiv2019

Highly Accelerated Multishot EPI through Synergistic Machine Learning and Joint Reconstruction

Purpose: To introduce a combined machine learning (ML) and physics-based image reconstruction framework that enables navigator-free, highly accelerated multishot echo planar imaging (msEPI), and demonstrate its application in high-resolution structural and diffusion imaging. Methods: Singleshot EPI is an efficient encoding technique, but does not lend itself well to high-resolution imaging due to severe distortion artifacts and blurring. While msEPI can mitigate these artifacts, high-quality msEPI has been elusive because of phase mismatch arising from shot-to-shot variations which preclude the combination of the multiple-shot data into a single image. We employ deep learning to obtain an interim image with minimal artifacts, which permits estimation of image phase variations due to shot-to-shot changes. These variations are then included in a Joint Virtual Coil Sensitivity Encoding (JVC-SENSE) reconstruction to utilize data from all shots and improve upon the ML solution. Results: Our combined ML + physics approach enabled Rinplane x MultiBand (MB) = 8x2-fold acceleration using 2 EPI-shots for multi-echo imaging, so that whole-brain T2 and T2* parameter maps could be derived from an 8.3 sec acquisition at 1x1x3mm3 resolution. This has also allowed high-resolution diffusion imaging with high geometric fidelity using 5-shots at Rinplane x MB = 9x2-fold acceleration. To make these possible, we extended the state-of-the-art MUSSELS reconstruction technique to Simultaneous MultiSlice (SMS) encoding and used it as an input to our ML network. Conclusion: Combination of ML and JVC-SENSE enabled navigator-free msEPI at higher accelerations than previously possible while using fewer shots, with reduced vulnerability to poor generalizability and poor acceptance of end-to-end ML approaches.

eess.IV↗