检索结果-内蒙古大学图书馆

Scan Specific Artifact Reduction in K-space (SPARK) Neural Networks Synergize with Physics-based Reconstruction to Accelerate MRI

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Arefeen, Yamin Beker, Onur Cho, Jaejin Yu, Heng Adalsteinsson, Elfar Bilgic, Berkin Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA United States Computer and Communication Sciences École Polytechnique Fédérale de Lausanne Lausanne Switzerland Athinoula A. Martinos Center for Biomedical Imaging CharlestownMA United States Department of Automation Tsinghua University Beijing China Harvard-MIT Health Sciences and Technology Massachusetts Institute of Technology CambridgeMA United States Institute for Medical Engineering and Science Massachusetts Institute of Technology CambridgeMA United States Department of Radiology Harvard Medical School BostonMA United States

Purpose: To develop a scan-specific model that estimates and corrects k-space errors made when reconstructing accelerated Magnetic Resonance Imaging (MRI) data. Methods: Scan-Specific Artifact Reduction in k-space (SPARK) trains a convolutional-neural-network to estimate and correct k-space errors made by an input reconstruction technique by back-propagating from the mean-squared-error loss between an auto-calibration signal (ACS) and the input technique's reconstructed ACS. First, SPARK is applied to GRAPPA and demonstrates improved robustness over other scan-specific models, such as RAKI and residual-RAKI. Subsequent experiments demonstrate that SPARK synergizes with residual-RAKI to improve reconstruction performance. SPARK also improves reconstruction quality when applied to advanced acquisition and reconstruction techniques like 2D virtual coil (VC-) GRAPPA, 2D LORAKS, 3D GRAPPA without an integrated ACS region, and 2D/3D wave-encoded imaging. Results: SPARK yields SSIM improvement and 1.5 - 2x RMSE reduction when applied to GRAPPA and improves robustness to ACS size for various acceleration rates in comparison to other scan-specific techniques. When applied to advanced reconstruction techniques such as residual-RAKI, 2D VC-GRAPPA and LORAKS, SPARK achieves up to 20% RMSE improvement. SPARK with 3D GRAPPA also improves RMSE performance by ~2x, SSIM performance, and perceived image quality without a fully sampled ACS region. Finally, SPARK synergizes with non-cartesian, 2D and 3D wave-encoding imaging by reducing RMSE between 20 - 25% and providing qualitative improvements. Conclusion: SPARK synergizes with physics-based acquisition and reconstruction techniques to improve accelerated MRI by training scan-specific models to estimate and correct reconstruction errors in k-space. Copyright © 2021, The Authors. All rights reserved.

关键词： Image reconstruction

Uncertainty quantification using neural networks for molecular property prediction

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Hirschfeld, Lior Swanson, Kyle Yang, Kevin Barzilay, Regina Coley, Connor W. Computer Science and Artificial Intelligence Laboratory MIT CambridgeMA02139 United States Department of Pure Mathematics and Mathematical Statistics University of Cambridge CambridgeCB3 0WB United Kingdom Department of Electrical Engineering and Computer Sciences University of California Berkeley BerkeleyCA94720 United States Department of Chemical Engineering MIT CambridgeMA02139 United States

Uncertainty quantification (UQ) is an important component of molecular property prediction, particularly for drug discovery applications where model predictions direct experimental design and where unanticipated imprecision wastes valuable time and resources. The need for UQ is especially acute for neural models, which are becoming increasingly standard yet are challenging to interpret. While several approaches to UQ have been proposed in the literature, there is no clear consensus on the comparative performance of these models. In this paper, we study this question in the context of regression tasks. We systematically evaluate several methods on five regression datasets using multiple complementary performance metrics. Our experiments show that none of the methods we tested is unequivocally superior to all others, and none produce a particularly reliable ranking of errors across multiple datasets. While we believe these results show that existing UQ methods are not sufficient for all common use cases and further research is needed, we conclude with a practical recommendation as to which existing techniques seem to perform well relative to others. Copyright © 2020, The Authors. All rights reserved.

关键词： Uncertainty analysis

ImgSensingNet: UAV Vision Guided Aerial-Ground Air Quality Sensing System

学校读者我要写书评

暂无评论

ImgSensingNet: UAV Vision Guided Aerial-Ground Air Quality S...

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Yuzhe Yang Zhiwen Hu Kaigui Bian Lingyang Song Computer Science and Artificial Intelligence Laboratory MIT Cambridge MA USA School of Electrical Engineering and Computer Science Peking University Beijing China

Given the increasingly serious air pollution problem, air quality index (AQI) monitoring in urban areas has drawn considerable attention. This paper presents ImgSensingNet, a vision guided aerial-ground sensing system, for air quality monitoring and forecasting by the fusion of haze images taken by the unmanned-aerial-vehicle (UAV) and the AQI data collected by an on-ground wireless sensor network. Specifically, ImgSensingNet first leverages the computer vision technique to tell the AQI scale in different regions from the haze images, where haze-relevant features and a deep convolutional neural network (CNN) are designed for direct learning between haze images and corresponding AQI scale. Based on the learnt AQI scale, ImgSensingNet determines whether to wake up on-ground wireless sensors for small-scale AQI monitoring and inference, which can greatly reduce the energy consumption of the system. An entropy-based model is employed for accurate real-time AQI estimation at un-measured locations and future air quality distribution forecasting. We implement and evaluate ImgSensingNet on two university campuses since Feb. 2018, and has collected 17,630 photos and 2.6 millions of AQI data samples. Experimental results confirm that ImgSensingNet can achieve high estimation accuracy while greatly reduce the battery consumption, compared to other state-of-the-art AQI monitoring approaches.

关键词： Sensors Monitoring Wireless sensor networks Image color analysis Feature extraction Air pollution

Direct prediction of phonon density of states with euclidean neural network

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Chen, Zhantao Andrejevic, Nina Smidt, Tess Ding, Zhiwei Xu, Qian Chi, Yen-Ting Nguyen, Quynh T. Alatas, Ahmet Kong, Jing Li, Mingda Quantum Matter Group MIT CambridgeMA02139 United States Department of Mechanical Engineering MIT CambridgeMA02139 United States Department of Materials Science and Engineering MIT CambridgeMA02139 United States Computational Research Division Lawrence Berkeley National Laboratory BerkeleyCA94720 United States Center for Advanced Mathematics for Energy Research Applications Lawrence Berkeley National Laboratory BerkeleyCA94720 United States Department of Physics MIT CambridgeMA02139 United States Advanced Photon Source Argonne National Laboratory LemontIL60439 United States Department of Electrical Engineering and Computer Science MIT CambridgeMA02139 United States Department of Nuclear Science and Engineering MIT CambridgeMA02139 United States

Machine learning has demonstrated great power in materials design, discovery, and property prediction. However, despite the success of machine learning in predicting discrete properties, challenges remain for continuous property prediction. The challenge is aggravated in crystalline solids due to crystallographic symmetry considerations and data scarcity. Here we demonstrate the direct prediction of phonon density of states using only atomic species and positions as input. We apply Euclidean neural networks, which by construction are equivariant to 3D rotations, translations, and inversion and thereby capture full crystal symmetry, and achieve high-quality prediction using a small training set of ∼ 103 examples with over 64 atom types. Our predictive model reproduces key features of experimental data and even generalizes to materials with unseen elements, and is naturally suited to efficiently predict alloy systems without additional computational cost. We demonstrate the potential of our network by predicting a broad number of high phononic specific heat capacity materials. Our work indicates an efficient approach to explore materials’ phonon structure, and can further enable rapid screening for high-performance thermal storage materials and phonon-mediated superconductors. Copyright © 2020, The Authors. All rights reserved.

关键词： Forecasting

Joint Frequency and Image Space Learning for MRI Reconstruction and Analysis

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Singh, Nalini M. Iglesias, Juan Eugenio Adalsteinsson, Elfar Dalca, Adrian V. Golland, Polina Computer Science and Artificial Intelligence Laboratory MIT CambridgeMA United States Dept. of Health Sciences & Technology MIT CambridgeMA United States A. A. Martinos Center Massachusetts General Hospital BostonMA United States Harvard Medical School CambridgeMA United States Centre for Medical Image Computing UCL London United Kingdom Research Laboratory of Electronics MIT CambridgeMA United States Dept. of Electrical Engineering & Computer Science MIT CambridgeMA United States

We propose neural network layers that explicitly combine frequency and image feature representations and show that they can be used as a versatile building block for reconstruction from frequency space data. Our work is motivated by the challenges arising in MRI acquisition where the signal is a corrupted Fourier transform of the desired image. The proposed joint learning schemes enable both correction of artifacts native to the frequency space and manipulation of image space representations to reconstruct coherent image structures at every layer of the network. This is in contrast to most current deep learning approaches for image reconstruction that treat frequency and image space features separately and often operate exclusively in one of the two spaces. We demonstrate the advantages of joint convolutional learning for a variety of tasks, including motion correction, denoising, reconstruction from undersampled acquisitions, and combined undersampling and motion correction on simulated and real world multicoil MRI data. The joint models produce consistently high quality output images across all tasks and datasets. When integrated into a state of the art unrolled optimization network with physics-inspired data consistency constraints for undersampled reconstruction, the proposed architectures significantly improve the optimization landscape, which yields an order of magnitude reduction of training time. This result suggests that joint representations are particularly well suited for MRI signals in deep learning networks. Our code and pretrained models are publicly available at https://***/nalinimsingh/interlacer. Copyright © 2020, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

k-Variance: A clustered notion of variance

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Solomon, Justin Greenewald, Kristjan Nagaraja, Haikady N. Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA United States MIT–IBM Watson AI Lab CambridgeMA United States Division of Biostatistics The Ohio State University ColumbusOH United States

We introduce k-variance, a generalization of variance built on the machinery of random bipartite matchings. K-variance measures the expected cost of matching two sets of k samples from a distribution to each other, capturing local rather than global information about a measure as k increases;it is easily approximated stochastically using sampling and linear programming. In addition to defining k-variance and proving its basic properties, we provide in-depth analysis of this quantity in several key cases, including one-dimensional measures, clustered measures, and measures concentrated on low-dimensional subsets of Rn. We conclude with experiments and open problems motivated by this new way to summarize distributional shape. Copyright © 2020, The Authors. All rights reserved.

关键词： Machinery

Optimized multi-axis spiral projection MR fingerprinting with subspace reconstruction for rapid whole-brain high-isotropic-resolution quantitative imaging

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cao, Xiaozhi Liao, Congyu Iyer, Siddharth Srinivasan Wang, Zhixing Zhou, Zihan Dai, Erpeng Liberman, Gilad Dong, Zijing Gong, Ting He, Hongjian Zhong, Jianhui Bilgic, Berkin Setsompop, Kawin Department of Radiology Stanford University StanfordCA United States Department of Electrical Engineering Stanford University StanfordCA United States Athinoula A. Martinos Center for Biomedical Imaging Massachusetts General Hospital CharlestownMA United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA United States Department of Biomedical Engineering University of Virginia CharlottesvilleVA United States Center for Brain Imaging Science and Technology College of Biomedical Engineering and Instrumental Science Zhejiang University Zhejiang Hangzhou China Department of Imaging Sciences University of Rochester RochesterNY United States Department of Radiology Harvard Medical School CambridgeMA United States Harvard-MIT Division of Health Sciences and Technology Massachusetts Institute of Technology CambridgeMA United States

Purpose: To improve image quality and accelerate the acquisition of 3D MRF. Methods: Building on the multi-axis spiral-projection MRF technique, a subspace reconstruction with locally low rank (LLR) constraint and a modified spiral-projection spatiotemporal encoding scheme termed tiny-golden-angle-shuffling (TGAS) were implemented for rapid whole-brain high-resolution quantitative mapping. The LLR regularization parameter and the number of subspace bases were tuned using retrospective in-vivo data and simulated examinations, respectively. B0inhomogeneity correction using multi-frequency interpolation was incorporated into the subspace reconstruction to further improve the image quality by mitigating blurring caused by off-resonance effect. Results: The proposed MRF acquisition and reconstruction framework can produce provide high quality 1-mm isotropic whole-brain quantitative maps in a total acquisition time of 1 minute 55 seconds, with higher-quality results than ones obtained from the previous approach in 6 minutes. The comparison of quantitative results indicates that neither the subspace reconstruction nor the TGAS trajectory induce bias for T1 and T2 mapping. High quality whole-brain MRF data were also obtained at 0.66-mm isotropic resolution in 4 minutes using the proposed technique, where the increased resolution was shown to improve visualization of subtle brain structures. Conclusion: The proposed TGAS-SPI-MRF with optimized spiral-projection trajectory and subspace reconstruction can enable high-resolution quantitative mapping with faster acquisition speed. © 2021, CC BY.

关键词： Mapping

Quantum transport and localization in 1d and 2d tight-binding lattices

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Karamlou, Amir H. Braumüller, Jochen Yanay, Yariv Paolo, Agustin Di Harrington, Patrick Kannan, Bharath Kim, David Kjaergaard, Morten Melville, Alexander Muschinske, Sarah Niedzielski, Bethany Vepsäläinen, Antti Winik, Roni Yoder, Jonilyn L. Schwartz, Mollie Tahan, Charles Orlando, Terry P. Gustavsson, Simon Oliver, William D. Research Laboratory of Electronics Massachusetts Institute of Technology CambridgeMA02139 United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02139 United States Laboratory for Physical Sciences College ParkMD20740 United States MIT Lincoln Laboratory LexingtonMA02421 United States Department of Physics Massachusetts Institute of Technology CambridgeMA02139 United States

Particle transport and localization phenomena in condensed-matter systems can be modeled using a tight-binding lattice Hamiltonian. The ideal experimental emulation of such a model utilizes simultaneous, high-fidelity control and readout of each lattice site in a highly coherent quantum system. Here, we experimentally study quantum transport in one-dimensional and two-dimensional tight-binding lattices, emulated by a fully controllable 3 × 3 array of superconducting qubits. We probe the propagation of entanglement throughout the lattice and extract the degree of localization in the Anderson and Wannier-Stark regimes in the presence of site-tunable disorder strengths and gradients. Our results are in quantitative agreement with numerical simulations and match theoretical predictions based on the tight-binding model. The demonstrated level of experimental control and accuracy in extracting the system observables of interest will enable the exploration of larger, interacting lattices where numerical simulations become intractable. Copyright © 2021, The Authors. All rights reserved.

关键词： Numerical models

Fsmi: Fast computation of shannon mutual information for information-theoretic mapping

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhang, Zhengdong Henderson, Trevor Karaman, Sertac Sze, Vivienne Department of Electrical Engineering and Computer Science MIT CambridgeMA United States Department of Aeronautics and Astronautics MIT CambridgeMA United States

Exploration tasks are embedded in many robotics applications, such as search and rescue and space exploration. Information-based exploration algorithms aim to find the most informative trajectories by maximizing an informationtheoretic metric, such as the mutual information between the map and potential future measurements. Unfortunately, most existing information-based exploration algorithms are plagued by the computational difficulty of evaluating the Shannon mutual information metric. In this paper, we consider the fundamental problem of evaluating Shannon mutual information between the map and a range measurement. First, we consider 2D environments. We propose a novel algorithm, called the Fast Shannon Mutual Information (FSMI). The key insight behind the algorithm is that a certain integral can be computed analytically, leading to substantial computational savings. Second, we consider 3D environments, represented by efficient data structures, e.g., an OctoMap, such that the measurements are compressed by Run-Length Encoding (RLE).We propose a novel algorithm, called FSMI-RLE, that efficiently evaluates the Shannon mutual information when the measurements are compressed using RLE. For both the FSMI and the FSMI-RLE, we also propose variants that make different assumptions on the sensor noise distribution for the purpose of further computational savings. We evaluate the proposed algorithms in extensive experiments. In particular, we show that the proposed algorithms outperform existing algorithms that compute Shannon mutual information as well as other algorithms that compute the Cauchy-Schwarz Quadratic mutual information (CSQMI). In addition, we demonstrate the computation of Shannon mutual information on a 3D map for the first time. Copyright © 2019, The Authors. All rights reserved.

关键词： Space research