检索结果-内蒙古大学图书馆

Speech Motion Anomaly Detection via Cross-Modal Translation of 4D Motion Fields from Tagged MRI

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Xiaofeng Xing, Fangxu Zhuo, Jiachen Stone, Maureen Prince, Jerry L. El Fakhri, Georges Woo, Jonghye Gordon Center for Medical Imaging Massachusetts General Hospital Harvard Medical School BostonMA02114 United States Dept. of Radiology University of Maryland School of Medicine BaltimoreMD21201 United States Dept. of Neural and Pain Sciences University of Maryland School of Dentistry BaltimoreMD21201 United States Dept. of Electrical and Computer Engineering Johns Hopkins University BaltimoreMD21218 United States Dept. of Radiology and Biomedical Imaging Yale University New HeavenCT06519 United States

Understanding the relationship between tongue motion patterns during speech and their resulting speech acoustic outcomes—i.e., articulatory-acoustic relation—is of great importance in assessing speech quality and developing innovative treatment and rehabilitative strategies. This is especially important when evaluating and detecting abnormal articulatory features in patients with speech-related disorders. In this work, we aim to develop a framework for detecting speech motion anomalies in conjunction with their corresponding speech acoustics. This is achieved through the use of a deep cross-modal translator trained on data from healthy individuals only, which bridges the gap between 4D motion fields obtained from tagged MRI and 2D spectrograms derived from speech acoustic data. The trained translator is used as an anomaly detector, by measuring the spectrogram reconstruction quality on healthy individuals or patients. In particular, the cross-modal translator is likely to yield limited generalization capabilities on patient data, which includes unseen out-of-distribution patterns and demonstrates subpar performance, when compared with healthy individuals. A one-class SVM is then used to distinguish the spectrograms of healthy individuals from those of patients. To validate our framework, we collected a total of 39 paired tagged MRI and speech waveforms, consisting of data from 36 healthy individuals and 3 tongue cancer patients. We used both 3D convolutional and transformer-based deep translation models, training them on the healthy training set and then applying them to both the healthy and patient testing sets. Our framework demonstrates a capability to detect abnormal patient data, thereby illustrating its potential in enhancing the understanding of the articulatory-acoustic relation for both healthy individuals and patients. © 2024, CC BY.

关键词： Anomaly detection

Global sensitivity methods for design of experiments in lithium-ion battery context

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Pozzi, A. Xie, X. Raimondo, D.M. Schenkendorf, R. Institute of Energy and Process Systems Engineering Tu Braunschweig Braunschweig38106 Germany Department of Electrical Computer and Biomedical Engineering University of Pavia Pavia27100 Italy

Battery management systems may rely on mathematical models to provide higher performance than standard charging protocols. Electrochemical models allow us to capture the phenomena occurring inside a lithium-ion cell and therefore, could be the best model choice. However, to be of practical value, they require reliable model parameters. Uncertainty quantification and optimal experimental design concepts are essential tools for identifying systems and estimating parameters precisely. Approximation errors in uncertainty quantification result in sub-optimal experimental designs and consequently, less-informative data, and higher parameter unreliability. In this work, we propose a highly efficient design of experiment method based on global parameter sensitivities. This novel concept is applied to the single-particle model with electrolyte and thermal dynamics (SPMeT), a well-known electrochemical model for lithium-ion cells. The proposed method avoids the simplifying assumption of output-parameter linearization (i.e., local parameter sensitivities) used in conventional Fisher information matrix-based experimental design strategies. Thus, the optimized current input profile results in experimental data of higher information content and in turn, in more precise parameter estimates. Copyright © 2020, The Authors. All rights reserved.

关键词： Design of experiments

Interpretable graph-based models on multimodal biomedical data integration: A technical review and benchmarking

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Sadeghi, Alireza Hajati, Farshid Argha, Ahmadreza Lovell, Nigel H. Yang, Min Alinejad-Rokny, Hamid Holcombe Department of Electrical and Computer Engineering Clemson University ClemsonSC United States School of Science and Technology Faculty of Science Agriculture Business and Law University of New England ArmidaleNSW2350 Australia School of Biomedical Engineering UNSW Sydney SydneyNSW2052 Australia Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China School of Biomedical Engineering UNSW Sydney SydneyNSW2052 Australia UNSW Sydney SydneyNSW2052 Australia

In healthcare, integrating diverse biomedical data modalities is critical for comprehensive analyses that can lead to better patient outcomes. Graph-based models have emerged as effective tools for handling such complex, non-Euclidean data by leveraging spatial and relational structures. However, model interpretability remains crucial for their successful deployment and for regulatory-approved implementations in clinical settings, as healthcare practitioners need transparent insights to build trust and guide decision-making. In this work, we present a technical and comprehensive review of research on interpretable graph-based models applied to multimodal biomedical data, covering studies from January 2019 to September 2024. Our analysis of published papers reveals a dominant focus on disease classification (particularly cancer) and a heavy reliance on static graph construction methods (e.g., Pearson correlation, Euclidean distance). While some approaches incorporate inherently interpretable designs, most rely on post-hoc techniques originally developed for non-graph data—such as gradient-based saliency or SHAP (Shapley additive explanations)—and only a small fraction utilize graph-specific methods like GNNExplainer. To address these gaps, we categorize existing explainable artificial intelligence (XAI) approaches according to their interpretability strategies and highlight evolving trends, including the graph-in-graph paradigm, the integration of knowledge graphs, and dynamic edge construction. To illuminate their practical implications, we compare and benchmark representative XAI techniques (sensitivity analysis, gradient saliency, SHAP, and graph masking) using a real-world Alzheimer’s disease (AD) dataset. Our findings show that while SHAP and sensitivity analysis reveal a broader spectrum of established disease-related pathways and Gene Ontology terms, gradient saliency and graph masking highlight unique metabolic and transport processes, underscoring the comple

关键词： Graph neural networks

Machine Learning for Improved Current Density Reconstruction from 2D Vector Magnetic Images

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Reed, Niko R. Bhutto, Danyal Turner, Matthew J. Daly, Declan M. Oliver, Sean M. Tang, Jiashen Olsson, Kevin S. Langellier, Nicholas Ku, Mark J.H. Rosen, Matthew S. Walsworth, Ronald L. Department of Physics University of Maryland College ParkMD United States Quantum Technology Center University of Maryland College ParkMD United States Joint Quantum Institute University of Maryland College ParkMD United States Department of Biomedical Engineering Boston University BostonMA United States A. A. Martinos Center for Biomedical Imaging Massachusetts General Hospital CharlestownMA United States Department of Electrical and Computer Engineering University of Maryland College ParkMD United States The MITRE Corporation McLeanVA22102 United States Intelligence Community Postdoctoral Research Fellowship Program University of Maryland College ParkMD20742 United States Department of Physics Harvard University CambridgeMA United States Department of Materials Science and Engineering University of Delaware NewarkDE19716 United States Department of Physics and Astronomy University of Delaware NewarkDE19716 United States Harvard Medical School 25 Shattuck St. BostonMA United States

The reconstruction of electrical current densities from magnetic field measurements is an important technique with applications in materials science, circuit design, quality control, plasma physics, and biology. Analytic reconstruction methods exist for planar currents, but break down in the presence of high spatial frequency noise or large standoff distance, restricting the types of systems that can be studied. Here, we demonstrate the use of a deep convolutional neural network for current density reconstruction from two-dimensional (2D) images of vector magnetic fields acquired by a quantum diamond microscope (QDM). Trained network performance significantly exceeds analytic reconstruction for data with high noise or large standoff distances. This machine learning technique can perform quality inversions on lower SNR data, significantly reducing the data collection time and permitting reconstructions of weaker and three-dimensional current sources. © 2024, CC BY.

关键词： Magnetic fields

IPMN Risk Assessment Under Federated Learning Paradigm

学校读者我要写书评

暂无评论

IPMN Risk Assessment Under Federated Learning Paradigm

IEEE International Symposium on biomedical Imaging

作者： Hongyi Pan Ziliang Hong Gorkem Durak Elif Keles Halil Ertugrul Aktas Yavuz Taktak Alpay Medetalibeyoglu Zheyuan Zhang Yury Velichko Concetto Spampinato Ivo Schoots Marco J. Bruno Pallavi Tiwari Candice Bolan Tamas Gonda Frank Miller Rajesh N. Keswani Michael B. Wallace Ziyue Xu Ulas Bagci Department of Radiology Northwestern University Chicago IL USA Department of Radiology Istanbul Faculty of Medicine Istanbul University Istanbul Turkey Department of Internal Medicine Istanbul Faculty of Medicine Istanbul University Istanbul Turkey Department of Electrical Electronic and Computer Engineering University of Catania Catania Italy Department of Radiology and Nuclear Medicine Erasmus Medical Center Rotterdam Netherlands Department of Gastroenterology and Hepatology Erasmus Medical Center Rotterdam Netherlands Department of Biomedical Engineering and Radiology University of Wisconsin Madison WI USA Division of Gastroenterology and Hepatology Mayo Clinic Jacksonville FL USA Division of Gastroenterology and Hepatology New York University New York NY USA Department of Gastroenterology and Hepatology Northwestern University Chicago IL USA NVIDIA Bethesda MD USA

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Accurate classification of Intraductal Papillary Mucinous Neoplasms (IPMN) is essential for identifying high-risk cases that require timely intervention. In this study, we develop a federated learning framework for multi-center IPMN classification utilizing a comprehensive pancreas MRI dataset. This dataset includes 652 T1-weighted and 655 T2-weighted MRI images, accompanied by corresponding IPMN risk scores from 7 leading medical institutions, making it the largest and most diverse dataset for IPMN classification to date. We assess the performance of DenseNet-121 in both centralized and federated settings for training on distributed data. Our results demonstrate that the federated learning approach achieves high classification accuracy comparable to centralized learning while ensuring data privacy across institutions. This work marks a significant advancement in collaborative IPMN classification, facilitating secure and high-accuracy model training across multiple centers.

关键词： Training Data privacy Accuracy Three-dimensional displays Federated learning Magnetic resonance imaging Pancreas Risk management Neoplasms biomedical imaging

New Closed-form Joint Localization and Synchronization using Sequential One-way TOAs

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Guo, Ningyan Zhao, Sihao Zhang, Xiao-Ping Yao, Zheng Cui, Xiaowei Lu, Mingquan The School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China The Department of Electronic Engineering Tsinghua University Beijing100084 China The Department of Electrical Computer and Biomedical Engineering Ryerson University TorontoONM5B 2K3 Canada The Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

It is an essential technique for the moving user nodes (UNs) with clock offset and clock skew to resolve the joint localization and synchronization (JLAS) problem. Existing iterative maximum likelihood methods using sequential one-way time-of-arrival (TOA) measurements from the anchor nodes' (AN) broadcast signals require a good initial guess and have a computational complexity that grows with the number of iterations, given the size of the problem. In this paper, we propose a new closed-form JLAS approach, namely CFJLAS, which achieves the asymptotically optimal solution in one shot without initialization when the noise is small, and has a low computational complexity. After squaring and differencing the sequential TOA measurement equations, we devise two intermediate variables to reparameterize the non-linear problem. In this way, we convert the problem to a simpler one of solving two simultaneous quadratic equations. We then solve the equations analytically to obtain a raw closed-form JLAS estimation. Finally, we apply a weighted least squares (WLS) step to optimize the estimation. We derive the Cramér-Rao lower bound (CRLB), analyze the estimation error, and show that the estimation accuracy of the CFJLAS reaches the CRLB under the small noise condition. The complexity of the new CFJLAS is only determined by the size of the problem, unlike the conventional iterative method, whose complexity is additionally multiplied by the number of iterations. Simulations in a 2D scene verify that the estimation accuracies of the new CFJLAS method in position, velocity, clock offset, and clock skew all reach the CRLB under the small noise condition. Compared with the conventional iterative method, which requires a proper initialization to converge and has a growing complexity with more iterations, the proposed new CFJLAS method does not require initialization, obtains the optimal solution under the small noise condition, and has a low computational complexity. © 2021, CC BY-NC

关键词： Iterative methods

A CMOS-based Characterisation Platform for Emerging RRAM Technologies

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Mifsud, Andrea Shen, Jiawei Feng, Peilong Xie, Lijie Wang, Chaohan Pan, Yihan Maheshwari, Sachin Agwa, Shady Stathopoulos, Spyros Wang, Shiwei Serb, Alexander Papavassiliou, Christos Prodromakis, Themis Constandinou, Timothy G. Department of Electrical and Electronic Engineering Imperial College London SW7 2BT United Kingdom Centre for Bio-Inspired Technology Institute of Biomedical Engineering Imperial College London SW7 2AZ United Kingdom Care Research & Technology Centre UK Dementia Research Institute United Kingdom Centre for Electronics Frontiers Electronics and Computer Science University of Southampton SO17 1BJ United Kingdom

Mass characterisation of emerging memory devices is an essential step in modelling their behaviour for integration within a standard design flow for existing integrated circuit designers. This work develops a novel characterisation platform for emerging resistive devices with a capacity of up to 1 million devices on-chip. Split into four independent sub-arrays, it contains on-chip column-parallel DACs for fast voltage programming of the DUT. On-chip readout circuits with ADCs are also available for fast read operations covering 5-decades of input current (20 nA to 2 mA). This allows a device’s resistance range to be between 1 kΩ and 10 MΩ with a minimum voltage range of ±1.5 V on the device. © 2022, CC BY-NC-SA.

关键词： RRAM

Quasi-Real Time Multi-Frequency 3D Shear Wave Absolute Vibro-Elastography (S-WAVE) System for Prostate

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Aleef, Tajwar Abrar Lobo, Julio Baghani, Ali Eskandari, Hani Moradi, Hamid Rohling, Robert Goldenberg, S. Larry Morris, William James Mahdavi, S. Sara Salcudean, Septimiu E. The School of Biomedical Engineering University of British Columbia VancouverBC Canada The Department of Electrical and Computer Engineering University of British Columbia VancouverBC Canada Sonic Incytes Medical Corp. VancouverBC Canada Salesforce TorontoON Canada Ladybug Robotics VancouverBC Canada BC Cancer - Vancouver Centre BC Canada The Department of Urological Sciences University of British Columbia VancouverBC Canada Radiation Oncologist BC Cancer - Vancouver Centre BC Canada

This article describes a novel quasi-real time system for quantitative and volumetric measurement of tissue elasticity in the prostate. Tissue elasticity is computed by using a local frequency estimator to measure the three dimensional local wavelengths of a steady-state shear wave within the prostate gland. The shear wave is created using a mechanical voice coil shaker which transmits multi-frequency vibrations transperineally. Radio frequency data is streamed directly from a BK Medical 8848 trans-rectal ultrasound transducer to an external computer where tissue displacement due to the excitation is measured using a speckle tracking algorithm. Bandpass sampling is used that eliminates the need for an ultra fast frame rate to track the tissue motion and allows for accurate reconstruction at a sampling frequency that is below the Nyquist rate. A roll motor with computer control is used to rotate the sagittal array of the transducer and obtain the 3D data. Two CIRS phantoms were used to validate both the accuracy of the elasticity measurement as well as the functional feasibility of using the system for in vivo prostate imaging. The system has been used in two separate clinical studies as a method for cancer identification. The results, presented here, show numerical and visual correlations between our stiffness measurements and cancer likelihood as determined from pathology results. Initial published results using this system include an area under the receiver operating characteristic curve of 0.82±0.01 with regards to prostate cancer identification in the peripheral zone. © 2022, CC BY-NC-ND.

关键词： Diseases

Kirchhoff's Current Law with Displacement Current

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Eisenberg, Robert Oriols, Xavier Ferry, David K. Department of Physiology and Biophysics Rush University Medical Center ChicagoIL United States Department of Applied Mathematics Illinois Institute of Technology ChicagoIL United States Department of Biomedical Engineering University of Illinois Chicago ChicagoIL United States Departament d’Enginyeria Electrònica Universitat Autònoma de Barcelona Barcelona08193 Spain School of Electrical Computer and Energy Engineering Arizona State University TempeAZ85287USA United States