Deep learning initialized compressed sensing (Deli-CS) in volumetric spatio-temporal subspace reconstruction.

Object: Spatio-temporal MRI methods offer rapid whole-brain multi-parametric mapping, yet they are often hindered by prolonged reconstruction times or prohibitively burdensome hardware requirements. The aim of this project is to reduce reconstruction time using deep learning.

Materials And Methods: This study focuses on accelerating the reconstruction of volumetric multi-axis spiral projection MRF, aiming for whole-brain T1 and T2 mapping, while ensuring a streamlined approach compatible with clinical requirements.

Blip-up blip-down circular EPI (BUDA-cEPI) for distortion-free dMRI with rapid unrolled deep learning reconstruction.

Purpose: BUDA-cEPI has been shown to achieve high-quality, high-resolution diffusion magnetic resonance imaging (dMRI) with fast acquisition time, particularly when used in conjunction with S-LORAKS reconstruction. However, this comes at a cost of more complex reconstruction that is computationally prohibitive. In this work we develop rapid reconstruction pipeline for BUDA-cEPI to pave the way for its deployment in routine clinical and neuroscientific applications.

Enhancing efficiency in detection of COVID-19 through AI-driven colorimetric isothermal detection with multiplex primers.

COVID-19 has afflicted millions of lives worldwide. Although there are many rapid methods to detect it based on colorimetric loop-mediated isothermal amplification, there remains room for improvement. This study aims to 1) integrate multiple primers into a singleplex assay to enhance the diagnostic sensitivity, and 2) utilize a high-throughput smartphone-operatable AI-driven color reading tool to enable a rapid result analysis.

Conflicting Sensory Information Sharpens the Neural Representations of Early Selective Visuospatial Attention.

Adaptive behaviors require the ability to resolve conflicting information caused by the processing of incompatible sensory inputs. Prominent theories of attention have posited that early selective attention helps mitigate cognitive interference caused by conflicting sensory information by facilitating the processing of task-relevant sensory inputs and filtering out behaviorally irrelevant information. Surprisingly, many recent studies that investigated the role of early selective attention on conflict mitigation have failed to provide positive evidence.

Deep learning-based super-resolution of structural brain MRI at 1.5 T: application to quantitative volume measurement.

Objective: This study investigated the feasibility of using deep learning-based super-resolution (DL-SR) technique on low-resolution (LR) images to generate high-resolution (HR) MR images with the aim of scan time reduction. The efficacy of DL-SR was also assessed through the application of brain volume measurement (BVM).

Materials And Methods: In vivo brain images acquired with 3D-T1W from various MRI scanners were utilized.

Sustained attention operates via dissociable neural mechanisms across different eccentric locations.

In primates, foveal and peripheral vision have distinct neural architectures and functions. However, it has been debated if selective attention operates via the same or different neural mechanisms across eccentricities. We tested these alternative accounts by examining the effects of selective attention on the steady-state visually evoked potential (SSVEP) and the fronto-parietal signal measured via EEG from human subjects performing a sustained visuospatial attention task.

Improved reconstruction for highly accelerated propeller diffusion 1.5 T clinical MRI.

Purpose: Propeller fast-spin-echo diffusion magnetic resonance imaging (FSE-dMRI) is essential for the diagnosis of Cholesteatoma. However, at clinical 1.5 T MRI, its signal-to-noise ratio (SNR) remains relatively low.

Sustained attention operates via dissociable neural mechanisms across different eccentric locations.

In primates, foveal and peripheral vision have distinct neural architectures and functions. However, it has been debated if selective attention operates via the same or different neural mechanisms across eccentricities. We tested these alternative accounts by examining the effects of selective attention on the steady-state visually evoked potential (SSVEP) and the fronto-parietal signal measured via EEG from human subjects performing a sustained visuospatial attention task.

Attentive pairwise interaction network for AI-assisted clock drawing test assessment of early visuospatial deficits.

Dementia is a debilitating neurological condition which impairs the cognitive function and the ability to take care of oneself. The Clock Drawing Test (CDT) is widely used to detect dementia, but differentiating normal from borderline cases requires years of clinical experience. Misclassifying mild abnormal as normal will delay the chance to investigate for potential reversible causes or slow down the progression.

Deep Learning Initialized Compressed Sensing (Deli-CS) in Volumetric Spatio-Temporal Subspace Reconstruction.

Introduction: Spatio-temporal MRI methods enable whole-brain multi-parametric mapping at ultra-fast acquisition times through efficient k-space encoding, but can have very long reconstruction times, which limit their integration into clinical practice. Deep learning (DL) is a promising approach to accelerate reconstruction, but can be computationally intensive to train and deploy due to the large dimensionality of spatio-temporal MRI. DL methods also need large training data sets and can produce results that don't match the acquired data if data consistency is not enforced.

An explainable self-attention deep neural network for detecting mild cognitive impairment using multi-input digital drawing tasks.

Background: Mild cognitive impairment (MCI) is an early stage of cognitive decline which could develop into dementia. An early detection of MCI is a crucial step for timely prevention and intervention. Recent studies have developed deep learning models to detect MCI and dementia using a bedside task like the classic clock drawing test (CDT).

One-step colorimetric isothermal detection of COVID-19 with AI-assisted automated result analysis: A platform model for future emerging point-of-care RNA/DNA disease diagnosis.

Colorimetric loop-mediated DNA isothermal amplification-based assays have gained momentum in the diagnosis of COVID-19 owing to their unmatched feasibility in low-resource settings. However, the vast majority of them are restricted to proprietary pH-sensitive dyes that limit downstream assay optimization or hinder efficient result interpretation. To address this problem, we developed a novel dual colorimetric RT-LAMP assay using in-house pH-dependent indicators to maximize the visual detection and assay simplicity, and further integrated it with the artificial intelligence (AI) operated tool (RT-LAMP-DETR) to enable a more precise and rapid result analysis in large scale testing.

Nonlinear dipole inversion (NDI) enables robust quantitative susceptibility mapping (QSM).

High-quality Quantitative Susceptibility Mapping (QSM) with Nonlinear Dipole Inversion (NDI) is developed with pre-determined regularization while matching the image quality of state-of-the-art reconstruction techniques and avoiding over-smoothing that these techniques often suffer from. NDI is flexible enough to allow for reconstruction from an arbitrary number of head orientations and outperforms COSMOS even when using as few as 1-direction data. This is made possible by a nonlinear forward-model that uses the magnitude as an effective prior, for which we derived a simple gradient descent update rule.

Highly accelerated multishot echo planar imaging 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: Single-shot EPI is an efficient encoding technique, but does not lend itself well to high-resolution imaging because of severe distortion artifacts and blurring. Although 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.

Quantitative susceptibility mapping using deep neural network: QSMnet.

Deep neural networks have demonstrated promising potential for the field of medical image reconstruction, successfully generating high quality images for CT, PET and MRI. In this work, an MRI reconstruction algorithm, which is referred to as quantitative susceptibility mapping (QSM), has been developed using a deep neural network in order to perform dipole deconvolution, which restores magnetic susceptibility source from an MRI field map. Previous approaches of QSM require multiple orientation data (e.

Dynamic 2D self-phase-map Nyquist ghost correction for simultaneous multi-slice echo planar imaging.

Purpose: To develop a reconstruction pipeline that intrinsically accounts for both simultaneous multislice echo planar imaging (SMS-EPI) reconstruction and dynamic slice-specific Nyquist ghosting correction in time-series data.

Methods: After 1D slice-group average phase correction, the separate polarity (i.e.

Model-based iterative reconstruction for single-shot EPI at 7T.

Purpose: To describe a model-based reconstruction strategy for single-shot echo planar imaging (EPI) that intrinsically accounts for k-space nonuniformity, Nyquist ghosting, and geometric distortions during rather than before or after image reconstruction.

Methods: Ramp sampling and inhomogeneous B0 field-induced distortion cause the EPI samples to lie on a non-Cartesian grid, thus requiring the nonuniform fast Fourier transform. Additionally, a 2D Nyquist ghost phase correction without the need for extra navigator acquisition is included in the proposed reconstruction.

Single-step quantitative susceptibility mapping with variational penalties.

Quantitative susceptibility mapping (QSM) estimates the underlying tissue magnetic susceptibility from the gradient echo (GRE) phase signal through background phase removal and dipole inversion steps. Each of these steps typically requires the solution of an ill-posed inverse problem and thus necessitates additional regularization. Recently developed single-step QSM algorithms directly relate the unprocessed GRE phase to the unknown susceptibility distribution, thereby requiring the solution of a single inverse problem.

Vectorial total generalized variation for accelerated multi-channel multi-contrast MRI.

Purpose: To develop and implement an efficient reconstruction technique to improve accelerated multi-channel multi-contrast MRI.

Theory And Methods: The vectorial total generalized variation (TGV) operator is used as a regularizer for the sensitivity encoding (SENSE) technique to improve image quality of multi-channel multi-contrast MRI. The alternating direction method of multipliers (ADMM) is used to efficiently reconstruct the data.

Organ-targeted high-throughput in vivo biologics screen identifies materials for RNA delivery.

Therapies based on biologics involving delivery of proteins, DNA, and RNA are currently among the most promising approaches. However, although large combinatorial libraries of biologics and delivery vehicles can be readily synthesized, there are currently no means to rapidly characterize them in vivo using animal models. Here, we demonstrate high-throughput in vivo screening of biologics and delivery vehicles by automated delivery into target tissues of small vertebrates with developed organs.

Accelerated H MRSI using randomly undersampled spiral-based k-space trajectories.

Purpose: To develop and evaluate the performance of an acquisition and reconstruction method for accelerated MR spectroscopic imaging (MRSI) through undersampling of spiral trajectories.

Theory And Methods: A randomly undersampled spiral acquisition and sensitivity encoding (SENSE) with total variation (TV) regularization, random SENSE+TV, is developed and evaluated on single-slice numerical phantom, in vivo single-slice MRSI, and in vivo three-dimensional (3D)-MRSI at 3 Tesla. Random SENSE+TV was compared with five alternative methods for accelerated MRSI.

Fast image reconstruction with L2-regularization.

Purpose: We introduce L2-regularized reconstruction algorithms with closed-form solutions that achieve dramatic computational speed-up relative to state of the art L1- and L2-based iterative algorithms while maintaining similar image quality for various applications in MRI reconstruction.

Materials And Methods: We compare fast L2-based methods to state of the art algorithms employing iterative L1- and L2-regularization in numerical phantom and in vivo data in three applications; (i) Fast Quantitative Susceptibility Mapping (QSM), (ii) Lipid artifact suppression in Magnetic Resonance Spectroscopic Imaging (MRSI), and (iii) Diffusion Spectrum Imaging (DSI). In all cases, proposed L2-based methods are compared with the state of the art algorithms, and two to three orders of magnitude speed up is demonstrated with similar reconstruction quality.

Fast dictionary-based reconstruction for diffusion spectrum imaging.

Diffusion spectrum imaging reveals detailed local diffusion properties at the expense of substantially long imaging times. It is possible to accelerate acquisition by undersampling in q-space, followed by image reconstruction that exploits prior knowledge on the diffusion probability density functions (pdfs). Previously proposed methods impose this prior in the form of sparsity under wavelet and total variation transforms, or under adaptive dictionaries that are trained on example datasets to maximize the sparsity of the representation.

A framework for the automatic generation of surface topologies for abdominal aortic aneurysm models.

Patient-specific abdominal aortic aneurysms (AAAs) are characterized by local curvature changes, which we assess using a feature-based approach on topologies representative of the AAA outer wall surface. The application of image segmentation methods yields 3D reconstructed surface polygons that contain low-quality elements, unrealistic sharp corners, and surface irregularities. To optimize the quality of the surface topology, an iterative algorithm was developed to perform interpolation of the AAA geometry, topology refinement, and smoothing.