检索结果-内蒙古大学图书馆

A cascaded residual UNET for fully automated segmentation of prostate and peripheral zone in T2-weighted 3D fast spin echo images

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Umapathy, Lavanya Unger, Wyatt Shareef, Faryal Arif, Hina Martin, Diego Altbach, Maria Bilgin, Ali Electrical and Computer Engineering University of Arizona TucsonAZ United States Medical Imaging University of Arizona TucsonAZ United States Biomedical Engineering University of Arizona TucsonAZ United States

Multi-parametric MR images have been shown to be effective in the non-invasive diagnosis of prostate cancer. Automated segmentation of the prostate eliminates the need for manual annotation by a radiologist which is time consuming. This improves efficiency in the extraction of imaging features for the characterization of prostate tissues. In this work, we propose a fully automated cascaded deep learning architecture with residual blocks, Cascaded MRes-UNET, for segmentation of the prostate gland and the peripheral zone in one pass through the network. The network yields high Dice scores (0.91±.02), precision (0.91±.04), and recall scores (0.92±.03) in prostate segmentation compared to manual annotations by an experienced radiologist. The average difference in total prostate volume estimation is less than 5%. © 2020, CC BY-NC-ND.

关键词： Urology

Temporal Uncertainty Localization to Enable Human-in-the-loop Analysis of Dynamic Contrast-enhanced Cardiac MRI Datasets

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yalcinkaya, Dilek M. Youssef, Khalid Heydari, Bobak Simonetti, Orlando Dharmakumar, Rohan Raman, Subha Sharif, Behzad IndianapolisIN United States Elmore Family School of Electrical & Computer Engineering Purdue University West LafayetteIN United States Krannert Cardiovascular Research Center IUSM IU Health Cardiovascular Institute IndianapolisIN United States Stephenson Cardiac Imaging Centre University of Calgary Alberta Canada Department of Internal Medicine Division of Cardiovascular Medicine Davis Heart and Lung Research Institute The Ohio State University ColumbusOH United States Weldon School of Biomedical Eng. Purdue University West LafayetteIN United States

Dynamic contrast-enhanced (DCE) cardiac magnetic resonance imaging (CMRI) is a widely used modality for diagnosing myocardial blood flow (perfusion) abnormalities. During a typical free-breathing DCE-CMRI scan, close to 300 time-resolved images of myocardial perfusion are acquired at various contrast "wash in/out" phases. Manual segmentation of myocardial contours in each time-frame of a DCE image series can be tedious and time-consuming, particularly when non-rigid motion correction has failed or is unavailable. While deep neural networks (DNNs) have shown promise for analyzing DCE-CMRI datasets, a "dynamic quality control" (dQC) technique for reliably detecting failed segmentations is lacking. Here we propose a new space-time uncertainty metric as a dQC tool for DNN-based segmentation of free-breathing DCE-CMRI datasets by validating the proposed metric on an external dataset and establishing a human-in-the-loop framework to improve the segmentation results. In the proposed approach, we referred the top 10% most uncertain segmentations as detected by our dQC tool to the human expert for refinement. This approach resulted in a significant increase in the Dice score (p © 2023, CC BY.

关键词： Deep neural networks

Nonequilibrium transport and the fluctuation theorem in the thermodynamic behaviors of nonlinear photonic systems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Yang Lu, Jincheng Xiong, Zhongfei Wu, Fan O. Christodoulides, Demetrios Chen, Yuntian Jiang, Jian-Hua School of Physical Science and Technology Collaborative Innovation Center of Suzhou Nano Science and Technology Soochow University 1 Shizi Street Suzhou215006 China Jiangsu Key Laboratory of Micro and Nano Heat Fluid Flow Technology and Energy Application School of Physical Science and Technology Suzhou University of Science and Technology Suzhou215009 China School of Optical and Electronic Information Huazhong University of Science and Technology Wuhan430074 China CREOL College of Optics and Photonics University of Central Florida OrlandoFL32816-2700 United States Ming Hsieh Department of Electrical and Computer Engineering University of Southern California Los AngelesCA90089 United States School of Biomedical Engineering Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou215123 China School of Physics University of Science and Technology of China Hefei230026 China

Nonlinear multimode optical systems have attracted substantial attention due to their rich physical properties. Complex interplay between the nonlinear effects and mode couplings makes it difficult to understand the collective dynamics of photons. Recent studies show that such collective phenomena can be effectively described by a Rayleigh–Jeans thermodynamics theory which is a powerful tool for the study of nonlinear multimode photonic systems. These systems, in turn, offer a compelling platform for investigating fundamental issues in statistical physics, attributed to their tunability and the ability to access negative temperature regimes. However, to date, a theory for the nonequilibrium transport and fluctuations is yet to be established. Here, we employ the full counting statistics theory to study the nonequilibrium transport of particle and energy in nonlinear multimode photonic systems in both positive and negative temperature regimes. Furthermore, we discover that in situations involving two reservoirs of opposite temperatures and chemical potentials, an intriguing phenomenon known as the loop current effect can arise, wherein the current in the positive energy sector runs counter to that in the negative energy sector. In addition, we numerically confirm that the fluctuation theorem remains applicable in optical thermodynamics systems across all regimes, from positive temperature to negative ones. Our findings closely align with numerical simulations based on first-principles nonlinear wave equations. Our work seeks to deepen the understanding of irreversible non-equilibrium processes and statistical fluctuations in nonlinear many-body photonic systems which will enhance our grasp of collective phenomena of photons and foster a fruitful intersection between optics and statistical physics. © 2024, CC BY-NC-ND.

关键词： Temperature

Corrigendum to “Non- invasive Localization of the Ectopic Foci of Focal Atrial Tachycardia by Using ECG Signal based Sparse Decomposition Algorithm”

学校读者我要写书评

暂无评论

biomedical Signal Processing and Control 2022年 71卷

作者： Fatemeh Mohammadi Ali Sheikhani Farbod Razzazi Alireza Ghorbani Sharif Biomedical Engineering Faculty of Medical Sciences and Technologies Science and Research Branch Islamic Azad University Tehran Iran Electrical Engineering Faculty of Electrical and Computer Engineering Science Science and Research Branch Islamic Azad University Tehran Iran Cardiologist Interventional Electrophysiologist of The Arrhythmia Centre Tehran Iran

A Mathematical Model of Lung Functionality using Pressure Signal for Volume-Controlled Ventilation

学校读者我要写书评

暂无评论

A Mathematical Model of Lung Functionality using Pressure Si...

IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)

作者： Husam Y. Al-Hetari Muhammad Nomani Kabir Mahmoud A. Al-Rumaima Noman Q. Al-Naggar Yasser M. Alginahi Md Munirul Hasan Faculty of Computing University Malaysia Pahang Malaysia Kuantan Malaysia Dept. of Biomedical Engineering University of Science and Technology Yemen Dept. of Electrical and Computer Engineering University of Windsor Windsor Canada

ISBN: (数字)9781728161334

ISBN: (纸本)9781728161341

Mechanical Ventilation is used to support the respiratory system malfunction by assisting recovery breathing process which could result from diseases and viruses such as pneumonia and COVID-19. Mathematical models are used to study and simulate the respiratory system supported by mechanical ventilation using different modes such as volume-controlled ventilation (VCV). In this research, a single compartment lung model ventilated by VCV is developed during real time mechanical ventilation using pressure signal. This mathematical model describes the lung volume and compliance correctly considering positive end expiration pressure (PEEP) value. The model is implemented using LabVIEW tools and can be used to monitor the volume, flow and compliance as outputs of the model. Two experiments are carried out on the proposed lung model at three input scenarios of volume (400, 500 and 600 ml) for each experiment considering a PEEP value. To validate the model, an artificial lung connected to a VCV with the same scenarios is used. Validation check is conducted by comparing the outputs of the lung model to that of the artificial lung. The experimental results showed that the measured lung model outputs with negative feedback are the same for pressure and flow as the outputs without negative feedback, whereas the measured volume is comparatively lower for negative feedback. Average percent error in the experiment with negative feedback (5.14%) is smaller compared to the experiment without negative feedback (9.28%). Furthermore, the average error of the calculated compliance decreases from 16% (without negative feedback) to 2% (with negative feedback). The obtained results of the proposed method showed good performance and acceptable accuracy. Thus, the model facilitates the clinicians and practitioners as a training tool to learn real-time mechanical ventilation functionalities.

关键词： Lung Ventilation Mathematical model Solid modeling Negative feedback Atmospheric modeling Real-time systems

Sub-second multi-channel magnetic control of select neural circuits in behaving flies

学校读者我要写书评

暂无评论

Research Square

Research Square 2021年

作者： Sebesta, Charles Torres, Daniel Wang, Boshuo Li, Zhongxi Duret, Guillaume Jiang, Kaiyi Xiao, Zhen Zhang, Qingbo Colvin, Vicki Goetz, Stefan M. Peterchev, Angel V. Dierick, Herman Bao, Gang Robinson, Jacob T. Department of Bioengineering Rice University HoustonTX United States Department of Electrical and Computer Engineering Rice University HoustonTX United States Department of Psychiatry & Behavioral Sciences School of Medicine Duke University DurhamNC United States Department of Electrical and Computer Engineering School of Engineering Duke University DurhamNC United States Department of Neurosurgery School of Medicine Duke University DurhamNC United States Department of Biomedical Engineering School of Engineering Duke University DurhamNC United States Department of Neuroscience Baylor College of Medicine HoustonTX United States Department of Human and Molecular Genetics Baylor College of Medicine HoustonTX United States Department of Chemistry Brown University ProvidenceRI United States

Precisely timed activation of genetically targeted cells is a powerful tool for studying neural circuits and controlling cell-based therapies. Magnetic control of cell activity or "magnetogenetics" using magnetic nanoparticle heating of temperature-sensitive ion channels enables remote, non-invasive activation of neurons for deep-tissue applications and studies of freely behaving animals. However, the in vivo response time of thermal magnetogenetics is currently tens of seconds, which prevents the precise temporal modulation of neural activity similar to light-based optogenetics. Moreover, magnetogenetics has not provided a means to selectively activate multiple channels to drive behavior. Here we demonstrate that by combining magnetic nanoparticles with a rate-sensitive thermoreceptor (TRPA1-A) it is possible to achieve sub-second behavioral responses in Drosophila melanogaster. Furthermore, by tuning the properties of magnetic nanoparticles to respond to different magnetic field strengths and frequencies, we can achieve fast, multi-channel stimulation, analogous to optogenetic stimulation with different wavelengths of light. These results bring magnetogenetics closer to the temporal resolution and multiplexed stimulation possible with optogenetics while maintaining the minimal invasiveness and deep-tissue stimulation only possible by magnetic control. © 2021, CC BY.

关键词： Cells

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

学校读者我要写书评

暂无评论

arXiv 2020年

作者： An, Hongjun Shin, Hyeong-Geol Ji, Sooyoen Jung, Woojin Oh, Sehong Shin, Dongmyung Park, Juhyung Lee, Jongho Laboratory for Imaging Science and Technology Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of Division of Biomedical Engineering Hankuk University of Foreign Studies Gyeonggi-do Korea Republic of

Respiration-induced B0 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 ± 5.2% to 1.3 ± 0.6%;structural similarity (SSIM) from 0.88 ± 0.08 to 0.99 ± 0.01;ghost-to-signal-ratio (GSR) from 7.9 ± 7.2% to 0.6 ± 0.6%;deep breathing: NRMSE from 13.9 ± 4.6% to 5.8 ± 1.4%;SSIM from 0.86 ± 0.03 to 0.95 ± 0.01;GSR 20.2 ± 10.2% to 5.7 ± 2.3%;natural breathing: NRMSE from 5.2 ± 3.3% to 4.0 ± 2.5%;SSIM from 0.94 ± 0.04 to 0.97 ± 0.02;GSR 5.7 ± 5.0% to 2.8 ± 1.1%). 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. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

A fuzzy logic controller for tasks scheduling using unreliable cloud resources

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Oikonomou, Panagiotis Kolomvatsos, Kostas Tziritas, Nikos Theodoropoulos, Georgios Loukopoulos, Thanasis Stamoulis, Georgios Computer Science and Engineering Southern Univ. of Science and Technology Shenzhen China Computer Science and Telecomm University of Thessaly Lamia Greece Comp. Science and Biomedical Informatics University of Thessaly Lamia Greece Electrical and Computer Engineering University of Thessaly Volos Greece

The Cloud infrastructure offers to end users a broad set of heterogenous computational resources using the pay-as-you-go model. These virtualized resources can be provisioned using different pricing models like the unreliable model where resources are provided at a fraction of the cost but with no guarantee for an uninterrupted processing. However, the enormous gamut of opportunities comes with a great caveat as resource management and scheduling decisions are increasingly complicated. Moreover, the presented uncertainty in optimally selecting resources has also a negatively impact on the quality of solutions delivered by scheduling algorithms. In this paper, we present a dynamic scheduling algorithm (i.e., the Uncertainty-Driven Scheduling - UDS algorithm) for the management of scientific workflows in Cloud. Our model minimizes both the makespan and the monetary cost by dynamically selecting reliable or unreliable virtualized resources. For covering the uncertainty in decision making, we adopt a Fuzzy Logic Controller (FLC) to derive the pricing model of the resources that will host every task. We evaluate the performance of the proposed algorithm using real workflow applications being tested under the assumption of different probabilities regarding the revocation of unreliable resources. Numerical results depict the performance of the proposed approach and a comparative assessment reveals the position of the paper in the relevant literature. Copyright © 2020, The Authors. All rights reserved.

关键词： Fuzzy logic

Autotuning plug-and-play algorithms for MRI

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Shastri, Saurav K. Ahmad, Rizwan Schniter, Philip Dept. of Electrical and Computer Engineering Ohio State University ColumbusOH43210 United States Dept. of Biomedical Engineering Ohio State University ColumbusOH43210 United States

For magnetic resonance imaging (MRI), recently proposed "plug-and-play" (PnP) image recovery algorithms have shown remarkable performance. These PnP algorithms are similar to traditional iterative algorithms like FISTA, ADMM, or primal-dual splitting (PDS), but differ in that the proximal update is replaced by a call to an application-specific image denoiser, such as BM3D or DnCNN. The fixed-points of PnP algorithms depend upon an algorithmic stepsize parameter, however, which must be tuned for optimal performance. In this work, we propose a fast and robust auto-tuning PnP-PDS algorithm that exploits knowledge of the measurement-noise variance that is available from a pre-scan in MRI. Experimental results show that our algorithm converges very close to genie-tuned performance, and does so significantly faster than existing autotuning approaches. © 2020, CC BY.

关键词： Magnetic resonance imaging