arXiv subjects

Jongho Lee

Publications and source records attributed to Jongho Lee.

48 records · Page 3Linked to original sources

arXiv2020

Machine-Learning Approach to Analyze the Status of Forklift Vehicles with Irregular Movement in a Shipyard

In large shipyards, the management of equipment, which are used for building a variety of ships, is critical. Because orders vary year to year, shipyard managers are required to determine methods to make the most of their limited resources. A particular difficulty that arises because of the nature and size of shipyards is the management of moving vehicles. In recent years, shipbuilding companies have attempted to manage and track the locations and movements of vehicles using Global Positioning System (GPS) modules. However, because certain vehicles, such as forklifts, roam irregularly around a yard, identifying their working status without being onsite is difficult. Location information alone is not sufficient to determine whether a vehicle is working, moving, waiting, or resting. This study proposes an approach based on machine learning to identify the work status of each forklift. We use the DBSCAN and k-means algorithms to identify the area in which a particular forklift is operating and the type of work it is performing. We developed a business intelligence system to collect information from forklifts equipped with GPS and Internet of Things (IoT) devices. The system provides visual information on the status of individual forklifts and helps in the efficient management of their movements within large shipyards.

cs.LG↗

arXiv2020

Deep Reinforcement Learning Designed Shinnar-Le Roux RF Pulse using Root-Flipping: DeepRF_SLR

A novel approach of applying deep reinforcement learning to an RF pulse design is introduced. This method, which is referred to as DeepRF_SLR, is designed to minimize the peak amplitude or, equivalently, minimize the pulse duration of a multiband refocusing pulse generated by the Shinar Le-Roux (SLR) algorithm. In the method, the root pattern of SLR polynomial, which determines the RF pulse shape, is optimized by iterative applications of deep reinforcement learning and greedy tree search. When tested for the designs of the multiband factors of three and seven RFs, DeepRF_SLR demonstrated improved performance compared to conventional methods, generating shorter duration RF pulses in shorter computational time. In the experiments, the RF pulse from DeepRF_SLR produced a slice profile similar to the minimum-phase SLR RF pulse and the profiles matched to that of the computer simulation. Our approach suggests a new way of designing an RF by applying a machine learning algorithm, demonstrating a machine-designed MRI sequence.

cs.LG↗

arXiv2020

A geometric approach to separate the effects of magnetic susceptibility and chemical shift/exchange in a phantom with isotropic magnetic susceptibility

Purpose: To separate the effects of magnetic susceptibility and chemical shift/exchange in a phantom with isotropic magnetic susceptibility. To generate a chemical shift/exchange-corrected quantitative susceptibility mapping (QSM) result. Theory and Methods: Magnetic susceptibility and chemical shift/exchange are the properties of a material. Both are known to induce the resonance frequency shift in MRI. In current QSM, the susceptibility is reconstructed from the frequency shift, ignoring the contribution of the chemical shift/exchange. In this work, a simple geometric approach, which averages the frequency shift maps from three orthogonal B0 directions to generate a chemical shift/exchange map, is developed using the fact that the average nullifies the (isotropic) susceptibility effects. The resulting chemical shift/exchange map is subtracted from the total frequency shift, producing a frequency shift map solely from susceptibility. Finally, this frequency shift map is reconstructed to a susceptibility map using a QSM algorithm. The proposed method is validated in numerical simulations and applied to phantom experiments with olive oil, bovine serum albumin, ferritin, and iron oxide solutions. Results: Both simulations and experiments confirm that the method successfully separates the contributions of the susceptibility and chemical shift/exchange, reporting the susceptibility and chemical shift/exchange of olive oil (susceptibility: 0.62 ppm, chemical shift: -3.60 ppm), bovine serum albumin (susceptibility: -0.059 ppm, chemical shift: 0.008 ppm), ferritin (susceptibility: 0.125 ppm, chemical shift: -0.005 ppm), and iron oxide (susceptibility: 0.30 ppm, chemical shift: -0.039 ppm) solutions. Conclusion: The proposed method successfully separates the susceptibility and chemical shift/exchange in phantoms with isotropic magnetic susceptibility.

eess.IV↗

arXiv2020

DeepResp: Deep learning solution for respiration-induced B0 fluctuation artifacts in multi-slice GRE

Respiration-induced B$_0$ fluctuation corrupts MRI images by inducing phase errors in k-space. A few approaches such as navigator have been proposed to correct for the artifacts at the expense of sequence modification. In this study, a new deep learning method, which is referred to as DeepResp, is proposed for reducing the respiration-artifacts in multi-slice gradient echo (GRE) images. DeepResp is designed to extract the respiration-induced phase errors from a complex image using deep neural networks. Then, the network-generated phase errors are applied to the k-space data, creating an artifact-corrected image. For network training, the computer-simulated images were generated using artifact-free images and respiration data. When evaluated, both simulated images and in-vivo images of two different breathing conditions (deep breathing and natural breathing) show improvements (simulation: normalized root-mean-square error (NRMSE) from 7.8% to 1.3%; structural similarity (SSIM) from 0.88 to 0.99; ghost-to-signal-ratio (GSR) from 7.9% to 0.6%; deep breathing: NRMSE from 13.9% to 5.8%; SSIM from 0.86 to 0.95; GSR 20.2% to 5.7%; natural breathing: NRMSE from 5.2% to 4.0%; SSIM from 0.94 to 0.97; GSR 5.7% to 2.8%). Our approach does not require any modification of the sequence or additional hardware, and may therefore find useful applications. Furthermore, the deep neural networks extract respiration-induced phase errors, which is more interpretable and reliable than results of end-to-end trained networks.

eess.IV↗

arXiv2019

Overview of quantitative susceptibility mapping using deep learning -- Current status, challenges and opportunities

Quantitative susceptibility mapping (QSM) has gained broad interests in the field by extracting biological tissue properties, predominantly myelin, iron and calcium from magnetic resonance imaging (MRI) phase measurements in vivo. Thereby, QSM can reveal pathological changes of these key components in a variety of diseases. QSM requires multiple processing steps such as phase unwrapping, background field removal and field-to-source-inversion. Current state of the art techniques utilize iterative optimization procedures to solve the inversion and background field correction, which are computationally expensive and require a careful choice of regularization parameters. With the recent success of deep learning using convolutional neural networks for solving ill-posed reconstruction problems, the QSM community also adapted these techniques and demonstrated that the QSM processing steps can be solved by efficient feed forward multiplications not requiring iterative optimization nor the choice of regularization parameters. Here, we review the current status of deep learning based approaches for processing QSM, highlighting limitations and potential pitfalls, and discuss the future directions the field may take to exploit the latest advances in deep learning for QSM.

eess.IV↗

arXiv2019

B1+ Homogenization in 7T MRI Using Mode-shaping with High Permittivity Materials

Ultra high field (UHF) brain MRI has proved its value by providing enhanced SNR, contrast, and higher resolution derived from the higher magnetic field (B0). Nonetheless, with the increased B0 of UHF MRI, the transmit RF magnetic field (B1+) inhomogeneity also became one of the critical issues requiring attention. As the effective wavelength of RF becomes comparable or smaller than the dimension of the brain at B0 larger than 7 Tesla, the increased B1+ inhomogeneity of UHF MRI results in poor SNR and uneven contrast. While parallel transmission techniques (PTx) and high permittivity material (HPM) structures for the mitigation of B1+ inhomogeneity have been suggested, the associated complexity in PTx and restricted volume of homogenization with HPM approach still remain as challenges. In this work, we address the B1+ inhomogeneity in the notion of mode-shaping. Treating a brain phantom as a dielectric potential-well resonator, we apply a phantom-conformal HPM potential-well in combination with a low-index potential barrier (air), to achieve the homogeneity of B1+ in the region of interest (ROI). Based on the electromagnetic simulations using a realistic brain model at 7T, we show that the proposed HPM structure reduces both the average deviation of B1+ in axial slices by 54% and peak SAR by 42%, respectively.

physics.med-ph↗

arXiv2019

Exploring linearity of deep neural network trained QSM: QSMnet+

Recently, deep neural network-powered quantitative susceptibility mapping (QSM), QSMnet, successfully performed ill conditioned dipole inversion in QSM and generated high-quality susceptibility maps. In this paper, the network, which was trained by healthy volunteer data, is evaluated for hemorrhagic lesions that have substantially higher susceptibility than healthy tissues in order to test linearity of QSMnet for susceptibility. The results show that QSMnet underestimates susceptibility in hemorrhagic lesions, revealing degraded linearity of the network for the untrained susceptibility range. To overcome this limitation, a data augmentation method is proposed to generalize the network for a wider range of susceptibility. The newly trained network, which is referred to as QSMnet+, is assessed in computer-simulated lesions with an extended susceptibility range (-1.4 ppm to +1.4 ppm) and also in twelve hemorrhagic patients. The simulation results demonstrate improved linearity of QSMnet+ over QSMnet (root mean square error of QSMnet+: 0.04 ppm vs. QSMnet: 0.36 ppm). When applied to patient data, QSMnet+ maps show less noticeable artifacts to those of conventional QSM maps. Moreover, the susceptibility values of QSMnet+ in hemorrhagic lesions are better matched to those of the conventional QSM method than those of QSMnet when analyzed using linear regression (QSMnet+: slope = 1.05, intercept = -0.03, R2 = 0.93; QSMnet: slope = 0.68, intercept = 0.06, R2 = 0.86), consolidating improved linearity in QSMnet+. This study demonstrates the importance of the trained data range in deep neural network-powered parametric mapping and suggests the data augmentation approach for generalization of network. The new network can be applicable for a wide range of susceptibility quantification.

eess.IV↗

arXiv2019

Nonlinear Dipole Inversion (NDI) enables Quantitative Susceptibility Mapping (QSM) without parameter tuning

We propose Nonlinear Dipole Inversion (NDI) for high-quality Quantitative Susceptibility Mapping (QSM) without regularization tuning, while matching the image quality of state-of-the-art reconstruction techniques. In addition to avoiding over-smoothing that these techniques often suffer from, we also obviate the need for parameter selection. 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. We synergistically combine this physics-model with a Variational Network (VN) to leverage the power of deep learning in the VaNDI algorithm. This technique adopts the simple gradient descent rule from NDI and learns the network parameters during training, hence requires no additional parameter tuning. Further, we evaluate NDI at 7T using highly accelerated Wave-CAIPI acquisitions at 0.5 mm isotropic resolution and demonstrate high-quality QSM from as few as 2-direction data.

eess.IV↗

arXiv2019

Artificial neural network for myelin water imaging

Purpose: To demonstrate the application of artificial-neural-network (ANN) for real-time processing of myelin water imaging (MWI). Methods: Three neural networks, ANN-IMWF, ANN-IGMT2, and ANN-II, were developed to generate MWI. ANN-IMWF and ANN-IGMT2 were designed to output myelin water fraction (MWF) and geometric mean T2 (GMT2,IEW), respectively whereas ANN-II generates a T2 distribution. For the networks, gradient and spin echo data from 18 healthy controls (HC) and 26 multiple sclerosis patients (MS) were utilized. Among them, 10 HC and 12 MS had the same scan parameters and were used for training (6 HC and 6 MS), validation (1 HC and 1 MS), and test sets (3 HC and 5 HC). The remaining data had different scan parameters and were applied to exam the effects of the scan parameters. The network results were compared with those of conventional MWI in the white matter mask and regions of interest (ROI). Results: The networks produced highly accurate results, showing averaged normalized root-mean-squared error under 3% for MWF and 0.4% for GMT2,IEW in the white matter mask of the test set. In the ROI analysis, the differences between ANNs and conventional MWI were less than 0.1% in MWF and 0.1 ms in GMT2,IEW (no statistical difference and R2 > 0.97). Datasets with different scan parameters showed increased errors. The average processing time was 0.68 sec in ANNs, gaining 11,702 times acceleration in the computational speed (conventional MWI: 7,958 sec). Conclusion: The proposed neural networks demonstrate the feasibility of real-time processing for MWI with high accuracy.

eess.IV↗

arXiv2018

Quantitative Susceptibility Mapping using Deep Neural Network: QSMnet

Deep neural networks have demonstrated promising potential for the field of medical image reconstruction. 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.g. Calculation of Susceptibility through Multiple Orientation Sampling or COSMOS) or regularization terms (e.g. Truncated K-space Division or TKD; Morphology Enabled Dipole Inversion or MEDI) to solve the ill-conditioned deconvolution problem. Unfortunately, they either require long multiple orientation scans or suffer from artifacts. To overcome these shortcomings, a deep neural network, QSMnet, is constructed to generate a high quality susceptibility map from single orientation data. The network has a modified U-net structure and is trained using gold-standard COSMOS QSM maps. 25 datasets from 5 subjects (5 orientation each) were applied for patch-wise training after doubling the data using augmentation. Two additional datasets of 5 orientation data were used for validation and test (one dataset each). The QSMnet maps of the test dataset were compared with those from TKD and MEDI for image quality and consistency in multiple head orientations. Quantitative and qualitative image quality comparisons demonstrate that the QSMnet results have superior image quality to those of TKD or MEDI and have comparable image quality to those of COSMOS. Additionally, QSMnet maps reveal substantially better consistency across the multiple orientations than those from TKD or MEDI. As a preliminary application, the network was tested for two patients. The QSMnet maps showed similar lesion contrasts with those from MEDI, demonstrating potential for future applications.

eess.IV↗

arXiv2013

Water Filtration Using Plant Xylem

Effective point-of-use devices for providing safe drinking water are urgently needed to reduce the global burden of waterborne disease. Here we show that plant xylem from the sapwood of coniferous trees - a readily available, inexpensive, biodegradable, and disposable material - can remove bacteria from water by simple pressure-driven filtration. Approximately 3 cm3 of sapwood can filter water at the rate of several liters per day, sufficient to meet the clean drinking water needs of one person. The results demonstrate the potential of plant xylem to address the need for pathogen-free drinking water in developing countries and resource-limited settings.

physics.flu-dyn↗

arXiv2012

Uniform wafer-scale synthesis of graphene on evaporated Cu (111) film with quality comparable to exfoliated monolayer

Monolayer graphene has been grown on crystallized Cu (111) films on standard oxidized Si 100 mm wafers. The monolayer graphene demonstrates high uniformity (>97% coverage), with immeasurable defects (>95% defect-negligible) across the entire wafer. Key to these results is the phase transition of evaporated copper films from amorphous to crystalline at the growth temperature as corroborated by X-ray diffraction and electron backscatter diffraction. Noticeably, phase transition of copper film is observed on technologically ubiquitous oxidized Si wafer where the oxide is a standard amorphous thermal oxide. Ion mass spectroscopy indicates that the copper films can be purposely hydrogen-enriched during a hydrogen anneal which subsequently affords graphene growth with a sole carbonaceous precursor for low defect densities. Owing to the strong hexagonal lattice match, the graphene domains align to the Cu (111) domains, suggesting a pathway for increasing the graphene grains by maximizing the copper grain sizes. Fabricated graphene transistors on a flexible polyimide film yield a peak carrier mobility ~4,930 cm2/Vs.

cond-mat.mtrl-sci↗