A5000930536- Advanced MRI Techniques and Applications
- Medical Imaging Techniques and Applications
- Advanced Neuroimaging Techniques and Applications
- MRI in cancer diagnosis
- Osteoarthritis Treatment and Mechanisms
- Cardiac Imaging and Diagnostics
- Atomic and Subatomic Physics Research
- Advanced NMR Techniques and Applications
- Helicobacter pylori-related gastroenterology studies
- Sparse and Compressive Sensing Techniques
- Knee injuries and reconstruction techniques
- Gastroesophageal reflux and treatments
- Liver Disease Diagnosis and Treatment
- Orthopedic Surgery and Rehabilitation
- Functional Brain Connectivity Studies
- Advanced X-ray Imaging Techniques
- Lanthanide and Transition Metal Complexes
- Photoacoustic and Ultrasonic Imaging
- Eosinophilic Esophagitis
- Lower Extremity Biomechanics and Pathologies
- Electron Spin Resonance Studies
- Total Knee Arthroplasty Outcomes
- Cardiovascular Function and Risk Factors
- Hernia repair and management
- Ultrasound Imaging and Elastography
University of Wisconsin–Madison
2016-2025
Lomonosov Moscow State University
2023
Highland Community College - Illinois
2021
Moscow State University of Medicine and Dentistry
2014-2021
Ministry of Health of the Russian Federation
2021
University of Minnesota
2018
National Research Tomsk State University
2016
National Institute on Aging
2015
National Institutes of Health
2015
University of Utah
2002-2004
Purpose To describe and evaluate a new fully automated musculoskeletal tissue segmentation method using deep convolutional neural network (CNN) three‐dimensional (3D) simplex deformable modeling to improve the accuracy efficiency of cartilage bone within knee joint. Methods A pipeline was built by combining semantic CNN 3D modeling. technique called SegNet applied as core perform high resolution pixel‐wise multi‐class classification. The refined output from preserve overall shape maintain...
Purpose To determine the feasibility of using a deep learning approach to detect cartilage lesions (including softening, fibrillation, fissuring, focal defects, diffuse thinning due degeneration, and acute injury) within knee joint on MR images. Materials Methods A fully automated learning-based lesion detection system was developed by segmentation classification convolutional neural networks (CNNs). Fat-suppressed T2-weighted fast spin-echo MRI data sets 175 patients with pain were...
.
To investigate the feasibility of using a deep learning-based approach to detect an anterior cruciate ligament (ACL) tear within knee joint at MRI by arthroscopy as reference standard.A fully automated diagnosis system was developed two convolutional neural networks (CNNs) isolate ACL on MR images followed classification CNN structural abnormalities isolated ligament. With institutional review board approval, sagittal proton density-weighted and fat-suppressed T2-weighted fast spin-echo in...
MR parameter mapping requires sampling along additional (parametric) dimension, which often limits its clinical appeal due to a several‐fold increase in scan times compared conventional anatomic imaging. Data undersampling combined with parallel imaging is an attractive way reduce time such applications. However, inherent SNR penalties of MRI noise amplification limit utility even at moderate acceleration factors, requiring regularization by prior knowledge. In this work, we propose novel...
To develop and evaluate a novel deep learning-based reconstruction framework called SANTIS (Sampling-Augmented Neural neTwork with Incoherent Structure) for efficient MR image improved robustness against sampling pattern discrepancy.With combination of data cycle-consistent adversarial network, end-to-end convolutional neural network mapping, fidelity enforcement reconstructing undersampled data, additionally utilizes sampling-augmented training strategy by extensively varying undersampling...
We present MRiLab, a new comprehensive simulator for large-scale realistic MRI simulations on regular PC equipped with modern graphical processing unit (GPU). MRiLab combines tissue modeling numerical virtualization of an system and scanning experiment to enable assessment broad range approaches including advanced quantitative methods inferring microstructure sub-voxel level. A flexible representation is achieved in by employing the generalized model multiple exchanging water macromolecular...
Abstract A novel method for iterative reconstruction of images from undersampled MRI data acquired by multiple receiver coil systems is presented. Based on Projection onto Convex Sets (POCS) formalism, the SENSitivity Encoded (POCSENSE) can be readily modified to include various linear and nonlinear constraints. Such constraints may beneficial reconstructing highly overcritically sets improve image quality. POCSENSE conceptually simple numerically efficient reconstruct sampled arbitrary k...
To evaluate the clinical utility of fast whole-brain macromolecular proton fraction ( MPF ) mapping in multiple sclerosis MS and compare with established quantitative magnetic resonance (MR) imaging measures tissue damage including magnetization transfer MT ratio relaxation rate (R1).
Purpose To investigate the feasibility of using compressed sensing (CS) to accelerate three‐dimensional fast spin‐echo (3D‐FSE) imaging knee. Materials and Methods A 3D‐FSE sequence was performed at 3T with CS (CUBE‐CS 3:16‐minute scan time) without (CUBE 4:44‐minute twice on knees 10 healthy volunteers assess signal‐to‐noise ratio (SNR) addition‐subtraction method once 50 symptomatic patients diagnostic performance. SNR cartilage, muscle, synovial fluid, bone marrow CUBE CUBE‐CS images were...
Background: Characterization of cognitive impairment (CI) in multiple sclerosis into distinct phenotypes holds promise for individualized treatments and biomarker exploration. Objective: Apply a previously validated, neuropsychologically driven diagnostic algorithm to identify taxonomy the type sclerosis. Methods: An developed validated other neurological diseases was applied cohort 1281 people with who underwent clinical neuropsychological evaluation across three centers. A domain marked...
Anisotropic diffusion filtering is widely used for MR image enhancement. However, the anisotropic filter nonoptimal images with spatially varying noise levels, such as reconstructed from sensitivity-encoded data and intensity inhomogeneity-corrected images. In this work, a new method levels presented. method, priori information regarding level spatial distribution utilized local adjustment of filter. Our was validated compared standard on simulated real MRI data. The noise-adaptive...
Noninvasive biomarkers of intracellular accumulation fat within the liver (hepatic steatosis) are urgently needed for detection and quantitative grading nonalcoholic fatty disease, most common cause chronic disease in United States. Accurate quantification with MRI is challenging due presence several confounding factors, including T*(2) decay. The specific purpose this work to quantify impact decay develop a multiexponential correction method improved accuracy quantification, relaxing...
Purpose To introduce a new technique called MPnRAGE, which produces hundreds of images with different T 1 contrasts and B1 corrected map. Theory Methods An interleaved three‐dimensional radial k‐space trajectory sliding window reconstruction is used in conjunction magnetization preparation pulses. This work modifies the SNAPSHOT‐FLASH fitting equations for imaging view‐sharing develops rapid B correction procedure. MPnRAGE demonstrated phantoms volunteers, including two volunteers eight...
Abstract Non‐Cartesian and rapid imaging sequences are more sensitive to scanner imperfections such as gradient delays eddy currents. These vary between scanners over time can be a significant impediment successful implementation eventual adoption of non‐Cartesian techniques by manufacturers. Differences the k ‐space trajectory desired actually acquired lead misregistration reduction in image quality. While early calibration methods required considerable scan time, recent work quickly making...
Purpose To develop and evaluate a retrospective method to minimize motion artifacts in structural MRI. Materials Methods The motion-correction strategy was developed for three-dimensional radial data collection demonstrated with MPnRAGE, technique that acquires high-resolution volumetric magnetization-prepared rapid gradient-echo, or MPRAGE, images multiple tissue contrasts. Forty-four pediatric participants (32 autism spectrum disorder [mean age ± standard deviation, 13 years 3] 12...
Purpose To accelerate dynamic MR imaging through development of a novel image reconstruction technique using low‐rank temporal signal models preestimated from training data. Theory We introduce the model consistency condition (MOCCO) technique, which utilizes to regularize without constraining solution be low‐rank, as is performed in related techniques. This achieved by data‐driven design transform for compressed sensing‐type regularization. The enforcement general compliance with...
Abstract A new time‐efficient and accurate technique for simultaneous mapping of T 1 B is proposed based on a combination the actual flip angle (FA) imaging variable FA methods. Variable FA–actual utilizes single one or more spoiled gradient‐echo acquisitions with nonlinear fitting procedure to yield / maps. The advantage high accuracy at either short times long repetition in sequence. Simulations show this method 0.03% 0.07% ratios time T1 over range 0.01–0.45. We case brain that it...
Abstract This study describes a new approach to reconstruct data that has been corrupted by unfavorable magnetization evolution. In this framework, images are reconstructed in weighted least squares fashion using all available and measure of consistency determined from the itself. The reconstruction scheme optimally balances uncertainties noise error with those inconsistency, is compatible methods model signal corruption, may be advantageous for more accurate precise many squares‐based image...