检索结果-内蒙古大学图书馆

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： M. Teimoorisichani S. Cho v. Khalilzad Sharghi M. Judenhofer J. Cabello v. Panin M. Aykac M. Conti Siemens Medical Solutions Inc. Knoxville Tennessee United States of America

Detectors of the Siemens Biograph vision PET scanner do not provide depth-of-interaction (DOI) information. The lack of DOI causes image resolution degradation at large radial offsets due to parallax error. In the current work, we explore an artificial intelligence-based method that can enable DOI without any hardware changes to the detectors. To detect DOI information from the single-ended readout detectors, a long short-term memory (LSTM) network was trained using energy signals from the SiPM channels digitized at 60 MHz. The training dataset was collected using a bench detector identical to the detector block of the Biograph vision (5 × 5 array of LSO crystals with size 3.2 × 3.2 × 20 mm 3 ) at known interaction depths every 2 mm. The trained network was evaluated using a separate test dataset. Also, to show the effects of DOI on the image quality of the Biograph vision PET scanner, a Monte Carlo simulation study was done. Assuming ideal DOI accuracy, photon interaction positions were used to extract DOI information given 2-layer discrete DOI detectors with an equal layer thickness of 10 mm. A Derenzo-like phantom with rods of diameter 4.6 to 19.0 mm positioned at a transaxial offset of 13 cm along both the x- and y-axes was scanned. Simulated data were histogrammed into two sets of sinograms with and without DOI and were reconstructed using the time-of-flight OS-EM reconstruction algorithm. Analysis of the test data acquired on a bench detector showed that the proposed DOI approach has an accuracy of up to 91% in classifying events into their correct DOI. The average accuracy was measured to be around 76% across all studied interaction depths. Profiles across the set of three smallest rods on images with and without DOI were drawn to study the potential gain from DOI. Reconstructed images with and without DOI suggest that a dual layer DOI detector improves the peak-to-valley ratio of the 6.4 mm rods by about 44% at a radial offset of 18 cm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using bootstrap identifiability as a metric for model selection for dynamic [/sup 11/C]DASB PET data

Using bootstrap identifiability as a metric for model select...

引用

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： R.T. Ogden A. Ojha K. Erlandsson R. van Heertum J.J. Mann R.v. Parsey Department of Psychiatry Columbia University New York NY USA Department of Radiology Columbia University New York NY USA

Numerous tracer kinetic models have been developed for estimation of neuroreceptor binding parameters from dynamic PET and SPECT brain studies. We have used the bootstrap technique to determine the variability of the parameter estimation as an aid in selecting the most appropriate kinetic model to use. This technique made it possible to take into account different sources of variability. We applied the method to data from 11 healthy subjects, each one scanned twice with the PET serotonin transporter ligand [ 11 C]DASB. Tracer binding was quantified for different brain regions by kinetic analysis, based on metabolite corrected arterial plasma input functions. Six different analysis methods were used, including iterative as well as non-iterative implementations of 1- and 2-tissue compartmental models (1TC, 2TC, 1TCNI, 2TCNI), likelihood estimation in graphical analysis (LEGA), and basis pursuit (Basis). We applied the bootstrap technique to the PET data, as well as to the plasma and metabolite data. Standard errors (SE) were calculated for the total volume distribution (v T ), as well as different binding potential estimates. The average and standard deviation (SD) of the estimated SE values were calculated across subjects. For comparison, we also estimated the variability of the outcome measures by bootstrapping only the tissue data. The results of the full bootstrap analysis showed that Basis was in general the best method. However, when only the tissue data were bootstrapped, the results indicated that 1TCNI was best. This shows that it can be important to take into account all sources of variability when using bootstrap identifiability for model selection

关键词： Positron emission tomography Kinetic theory Parameter estimation Plasma measurements Brain modeling Plasma transport processes image reconstruction Plasma sources Iterative methods Psychiatry

来源：评论

学校读者我要写书评

暂无评论

Can PET FDG Deep Texture Representations Be Made Robust?

Can PET FDG Deep Texture Representations Be Made Robust?

引用

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： R. R. John I. Ackerely R. Smith A. Robinson v. Prakash M. Shastry P. Strouhal K. Wells Centre for Vision Speech and Signal Processing University of Surrey Guildford United Kingdom Medical Physics and Clinical Engineering Department Cardiff and Vale University Health Board Cardiff United Kingdom National Physical Laboratory Teddington United Kingdom Department of Nuclear Medicine Royal Surrey County Hospital Guildford United Kingdom Alliance Medical Ltd Warwick United Kingdom Medical Imaging Group Centre for Vision Speech and Signal Processing University of Surrey Guildford United Kingdom

ISBN: (数字)9798350388152

ISBN: (纸本)9798350388169

The efficacy of Convolutional Neural Networks (CNNs) in recognizing cancerous textures in PET scans is well acknowledged, yet model generalizability across different cancer types, imaging acquisitions, and reconstruction protocols remains largely unexplored. This study evaluates a 3D CNN originally trained on esophageal cancer data, applied to lung cancer and lymphoma. We test the model using organ-specific PET data from four glycolytic volumes with high Standardized Uptake values (SUv), acquired from different scanners and acquisition protocols. Through Principal Component Analysis (PCA) of the network’s sub-logit layer activations, we demonstrate its ability to distinctly identify textural features across different cancers, scanners and acquisition protocols, highlighting its robust cross-cancer applicability and potential for enhancing diagnostic precision.

关键词： Microwave integrated circuits Protocols Three-dimensional displays image recognition Semiconductor detectors Lung cancer data models

来源：评论

学校读者我要写书评

暂无评论

Reconstructed Dynamics of the Imaging Photoplethysmogram

Reconstructed Dynamics of the Imaging Photoplethysmogram

引用

Annual International conference of the IEEE Engineering in Medicine and Biology Society

作者： Nina Sviridova vladimir Savchenko Maria Savchenko Kazuyuki Aihara Kunihiko Okada Tiejun Zhao Tokyo Daigaku Bunkyo-ku Tokyo JP Hosei Daigaku Chiyoda-ku Tokyo JP Meiji Daigaku Chiyoda-ku Tokyo JP Nogyo Shokuhin Sangyo Gijutsu Sogo Kenkyu Kiko Tsukuba Ibaraki JP Niigata Agro-Food University Niigata 959-2702 Japan

Human photoplethysmogram (PPG) is one of the signals widely applied for health monitoring. Development of the new techniques made possible evolution of traditional contact PPG which was measured at red and near-infrared light (NIR) to the contactless, imaging PPG (iPPG) that can be recorded at various light wavelengths, including ambient visible light. However, despite the numerous advantages of iPPG its applications demonstrated so far are quite limited. The NIR PPG was previously found to be useful for various applications in the area of physiological and mental health monitoring by utilizing advanced methods of nonlinear time-series analysis applied on its reconstructed dynamics. The main purpose of this study is to demonstrate data-driven approach with time-delay-reconstructed attractor obtained from the iPPG. The results of this study demonstrated that the iPPG dynamics can be reconstructed with fine data resolution, and its time-delay-reconstructed trajectory is almost deterministic, though contains noise. The obtained results might be useful for further applied studies on the iPPG.

关键词： Trajectory Cameras Time series analysis image reconstruction Interpolation Monitoring Heart rate

来源：评论

学校读者我要写书评

暂无评论

3D reconstruction and Segmentation of Dissection Photographs for MRI-Free Neuropathology 23rd

3D Reconstruction and Segmentation of Dissection Photographs...

引用

23rd International conference on Medical image Computing and Computer-Assisted Intervention, MICCAI 2020

作者： Tregidgo, Henry F. J. Casamitjana, Adrià Latimer, Caitlin S. Kilgore, Mitchell D. Robinson, Eleanor Blackburn, Emily van Leemput, Koen Fischl, Bruce Dalca, Adrian v. Donald, Christine L. Mac Keene, C. Dirk Iglesias, Juan Eugenio Centre for Medical Image Computing University College London London United Kingdom Department of Pathology University of Washington SeattleWA United States Queen Square Institute of Neurology University College London London United Kingdom Martinos Center for Biomedical Imaging MGH and Harvard Medical School Boston United States Department of Health Technology DTU Lyngby Denmark Computer Science and Artificial Intelligence Laboratory MIT Cambridge United States Department of Neurological Surgery University of Washington SeattleWA United States

ISBN: (纸本)9783030597214

Neuroimaging to neuropathology correlation (NTNC) promis-es to enable the transfer of microscopic signatures of pathology to in vivo imaging with MRI, ultimately enhancing clinical care. NTNC traditionally requires a volumetric MRI scan, acquired either ex vivo or a short time prior to death. Unfortunately, ex vivo MRI is difficult and costly, and recent premortem scans of sufficient quality are seldom available. To bridge this gap, we present methodology to 3D reconstruct and segment full brain image volumes from brain dissection photographs, which are routinely acquired at many brain banks and neuropathology departments. The 3D reconstruction is achieved via a joint registration framework, which uses a reference volume other than MRI. This volume may represent either the sample at hand (e.g., a surface 3D scan) or the general population (a probabilistic atlas). In addition, we present a Bayesian method to segment the 3D reconstructed photographic volumes into 36 neuroanatomical structures, which is robust to nonuniform brightness within and across photographs. We evaluate our methods on a dataset with 24 brains, using Dice scores and volume correlations. The results show that dissection photography is a valid replacement for ex vivo MRI in many volumetric analyses, opening an avenue for MRI-free NTNC, including retrospective data. The code is available at https://***/htregidgo/DissectionPhotovolumes. © 2020, Springer Nature Switzerland AG.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Animating the Past: Reconstruct Trilobite via video Generation

Animating the Past: Reconstruct Trilobite via Video Generati...

引用

IEEE International conference on Big data

作者： Xiaoran Wu Zien Huang Chonghan Yu AI Lab Yishi Inc. Hangzhou China The International Department Experimental High School Beijing Normal University School of Ocean Sciences China University of Geoscience Beijing China

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Paleontology, the study of past life, fundamentally relies on fossils to reconstruct ancient ecosystems and understand evolutionary dynamics. Trilobites, as an important group of extinct marine arthropods, offer valuable insights into Paleozoic environments through their well-preserved fossil records. Reconstructing trilobite behaviour from static fossils will set new standards for dynamic reconstructions in scientific research and education. Despite the potential, current computational methods for this purpose like text-to-video (T2v) face significant challenges, such as maintaining visual realism and consistency, which hinder their application in science contexts. To overcome these obstacles, we introduce an automatic T2v prompt learning method. Within this framework, prompts for a fine-tuned video generation model are generated by a large language model, which is trained using rewards that quantify the visual realism and smoothness of the generated video. The fine-tuning of the video generation model, along with the reward calculations make use of a collected dataset of 9,088 Eoredlichia intermedia fossil images, which provides a common representative of visual details of all class of trilobites. Qualitative and quantitative experiments show that our method can generate trilobite videos with significantly higher visual realism compared to powerful baselines, promising to boost both scientific understanding and public engagement.

关键词： Learning systems visualization Generative AI Large language models Education Text to video image reconstruction Paleontology Standards Faces

来源：评论

学校读者我要写书评

暂无评论

First results from the high-resolution mouse SPECT annular scintillation camera

First results from the high-resolution mouse SPECT annular s...

引用

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： A.L. Goertzen D.W. Jones J. Seidel K. Li M.v. Green McConnell Brain Imaging Centre Montreal Neurological Institute Montreal QUE Canada NIMH SPECT Laboratory Clinical Brain Disorders Branch IRP National Institute of Mental Health Bethesda MD USA Imaging Physics Laboratory Clinical Center National Institutes of Health DHHS Bethesda MD USA

High resolution SPECT imaging in small animals is often limited by poor sensitivity, leading to prolonged imaging times, very large injected doses, or both. To increase sensitivity while maintaining spatial resolution, we designed and constructed a multi-pinhole collimator array to replace the parallel hole collimators of a Ceraspect/spl trade/ human SPECT brain scanner. The Ceraspect scanner is comprised of an annular NaI(Tl) crystal within which the eight pinhole collimators (1 mm diameter holes) rotate while projecting non-overlapping images of the object onto the stationary annular crystal. In this manner, only 1/8/sup th/ of a collimator rotation is required to acquire a complete tomographic data set. The imaging field of view (FOv) is 2.56 cm, which is sufficient to encompass a mouse. data is currently acquired in step-and-shoot mode, however the system is capable of list mode acquisition with the collimator continuously rotating. images are reconstructed using a cone-beam OSEM method. The reconstructed spatial resolution of the system is 1.7 mm and the sensitivity at the centre of the FOv is 13.8 cps/microCi. A whole-body bone scan of a mouse injected with Tc-99 m MDP clearly revealed skeletal structures such as the ribs and vertebral bodies. These preliminary results suggest that this approach is a good tradeoff between resolution and sensitivity and, with further refinement, may permit dynamic imaging in living animals.

关键词： Mice Cameras Collimators Spatial resolution image resolution High-resolution imaging Animals image reconstruction Humans Tomography

来源：评论

学校读者我要写书评

暂无评论

Rapid estimation of 4DCT motion-artifact severity based on 1D breathing-surrogate periodicity

引用

MEDICAL PHYSICS 2014年第11期41卷 111717页

作者： Li, Guang Caraveo, Marshall Wei, Jie Rimner, Andreas Wu, Abraham J. Goodman, Karyn A. Yorke, Ellen Mem Sloan Kettering Canc Ctr Dept Med Phys New York NY 10065 USA CUNY City Coll Dept Comp Sci New York NY 10031 USA Mem Sloan Kettering Canc Ctr Dept Radiat Oncol New York NY 10065 USA

Purpose: Motion artifacts are common in patient four-dimensional computed tomography (4DCT) images, leading to an ill-defined tumor volume with large variations for radiotherapy treatment and a poor foundation with low imaging fidelity for studying respiratory motion. The authors developed a method to estimate 4DCT image quality by establishing a correlation between the severity of motion artifacts in 4DCT images and the periodicity of the corresponding 1D respiratory waveform (1DRW) used for phase binning in 4DCT reconstruction. Methods: Discrete Fourier transformation (DFT) was applied to analyze 1DRW periodicity. The breathing periodicity index (BPI) was defined as the sum of the largest five Fourier coefficients, ranging from 0 to 1. Distortional motion artifacts (excluding blurring) of cine-scan 4DCT at the junctions of adjacent couch positions around the diaphragm were classified in three categories: incomplete, overlapping, and duplicate anatomies. To quantify these artifacts, discontinuity of the diaphragm at the junctions was measured in distance and averaged along six directions in three orthogonal views. Artifacts per junction (APJ) across the entire diaphragm were calculated in each breathing phase and phase-averaged (APJ) over bar, defined as motion-artifact severity (MAS), was obtained for each patient. To make MAS independent of patient-specific motion amplitude, two new MAS quantities were defined: MAS(D) is normalized to the maximum diaphragmatic displacement and MAS(v) is normalized to the mean diaphragmatic velocity (the breathing period was obtained from DFT analysis of 1DRW). Twenty-six patients' free-breathing 4DCT images and corresponding 1DRW data were studied. Results: Higher APJ values were found around midventilation and full inhalation while the lowest APJ values were around full exhalation. The distribution of MAS is close to Poisson distribution with a mean of 2.2 mm. The BPI among the 26 patients was calculated with a value ranging fro

关键词： 4DCT image quality motion artifacts respiratory surrogate radiotherapy

来源：评论

学校读者我要写书评

暂无评论

Multiobjective method for fitting pinhole image intensity profiles of implosion cores driven by a Pareto genetic algorithm

引用

REvIEW OF SCIENTIFIC INSTRUMENTS 2006年第10期77卷

作者： Nagayama, T. Mancini, R. C. Welser, L. A. Louis, S. Golovkin, I. E. Tommasini, R. Koch, J. A. Izumi, N. Delettrez, J. Marshall, F. J. Regan, S. P. Smalyuk, v. Haynes, D. Kyrala, G. Univ Nevada Dept Phys Reno NV 89557 USA Univ Nevada Dept Comp Sci Reno NV 89557 USA Prism Computat Sci Madison WI 53711 USA Lawrence Livermore Natl Lab Livermore CA 94550 USA Univ Rochester Laser Energet Lab Rochester NY 14623 USA Los Alamos Natl Lab Los Alamos NM 87545 USA

We discuss a method for the simultaneous and self-consistent fitting of a set of intensity or emissivity spatial profiles from several narrow-band x-ray pinhole images from argon-doped inertial confinement fusion implosion cores, and the space-integrated line spectrum. A Pareto genetic algorithm (PGA) combines the search and optimization capabilities of a single-objective genetic algorithm with the Pareto domination technique of multiobjective optimization. Further, the PGA search is followed up by a fine-tuning step based on a nonlinear least-squares-minimization procedure. The result is a robust search and reconstruction method that finds the optimal core spatial structure subject to multiple constraints. This method is independent of geometry inversions and could take advantage of not only optically thin but also optically thick image data. Results are shown for two combinations of three-objectives based on gated argon He beta and Ly beta image data and the line spectrum. (c) 2006 American Institute of Physics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

data-Driven Fault Diagnosis for Sensors in Commercial Proton Exchange Membrane Fuel Cell System Using Transfer Learning

Data-Driven Fault Diagnosis for Sensors in Commercial Proton...

引用

IEEE conference and Expo Transportation Electrification Asia-Pacific (ITEC Asia-Pacific)

作者： Cenyu Wang Hao Yuan Xudong Liu Bo Jiang Xueyuan Wang Jiangong Zhu Xuezhe Wei Haifeng Dai School of Automotive Studies Tongji University Shanghai China

ISBN: (数字)9798331529277

ISBN: (纸本)9798331529307

Reliability and safety are two key concerns for proton exchange membrane fuel cell (PEMFC) vehicles, but the potential consequences caused by sensor failures pose significant threats to these aspects, especially in commercial vehicles that are more cost-sensitive. This article introduces a novel sensor fault diagnosis approach for PEMFCs based on a data-driven method. The method employs multi-signal data-image conversion and reconstruction to cope with situations where sensor data are highly coupled and difficult for dimensional reduction. Transfer learning (TL) is also implemented, using pre-trained Inception v1 as the knowledge for TL in sensor fault diagnosis, based on the dataset collected from real road operations of commercial fuel cell tractors. The proposed TL-Inception identifies six fault types with an accuracy rate of up to 98.29%, outperforming other common methods, particularly in missed diagnosis, indicating its high sensitivity. Moreover, the method demonstrates sensitivity to fault characteristics in discrete and continuous sliding time windows and shows the potential for multi-fault diagnosis and time-varying response capability.

关键词： Fault diagnosis Protons Sensitivity Roads Transfer learning Fuel cells Transportation Electrification Fuel cell vehicles Safety

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：