检索结果-内蒙古大学图书馆

advances in Computing, Communication and Applied Informatics (ACCAI), international conference on

作者： V Malathy Niladri Maiti Nithin Kumar d. Lavanya S. Aswath Shaik Balkhis Banu Department of ECE School of Engineering SR University Warangal Telangana India School Of Dentistry Central Asian University Tashkent Uzbekistan CSE (AIML) Sri Venkateswara College of Engineering Tirupati Tirupati Andhra Pradesh Electronics and Communication Engineering Veltech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu Department of Physiotherapy Fatima college of health sciences Al Ain UAE

ISBN: (数字)9798350389449

ISBN: (纸本)9798350389456

Picture segmentation is an essential instrument in medical diagnostics, as it enables the precise identification and examination of anatomical characteristics and pathological regions. Modern picture segmentation algorithms have been considerably improved in comparison to their predecessors as a result of recent developments in deep learning. This paper offers a succinct overview of the most recent developments in medical diagnostic image segmentation, which have been facilitated by the application of deep learning algorithms. U-Nets, CNNs, and FCNs are deep learning architectures that are frequently implemented in medical imaging. The precision and efficacy of automated image analysis have been improved by integrating these models into medical diagnostics. Furthermore, we investigate the challenges that arise when applying deep learning models to healthcare, including the necessity for a more comprehensive comprehension of the models and the restricted availability of data.

关键词： deep learning Image segmentation Pathology Image analysis Computational modeling Instruments Neural networks

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Multiplication: Implementing Vedic Sutra Principles in Multiplier design

Revolutionizing Multiplication: Implementing Vedic Sutra Pri...

引用

recent advances in Science and Engineering Technology (ICRASET), international conference on

作者： Kiran Puttegowda Saritha Shetty K Prabhavathi G R Yathiraj P Chandra Shekar d S Sunil Kumar Department of Electronics and Communication Engineering Vidyavardhaka College of Engineering Mysuru Karnataka India Department of MCA NMAM Institute of Technology (Nitte Deemed to be University) Nitte Karnataka India Department of Electronics and Communication Engineering BGS Institute of Technology Adichunchanagiri University BG Nagara Mandya INDIA Department of CSE Coorg Institute of Technology Ponnampet Karnataka India Department of Electronics and communication Engineering ATME College of Engineering Mysuru Karnataka India Anatta Innovations Bangalore Karnataka India

ISBN: (数字)9798350388602

ISBN: (纸本)9798350388619

Ancient Indian Mathematics, known as Vedic Mathematics, draws from 16 principles found in ancient Indian scriptures (Vedas). Among these principles, Urdhva Tiryakbhyam, Ekanyunena Purvena, and Ekadhikena Purvena stand out for their relevance in modern computation. In recent decades, there has been significant interest in developing fast multiplier circuits, with Vedic multipliers gaining favor due to their efficiency in terms of speed, space utilization, and power consumption. This study examines the performance of these sutras, particularly in the context of $\mathbf{1 6}$-bit operations, using Verilog programming language for implementation and Vivado 2017.1 for synthesis and testing. Through simulations and analysis, the aim is to identify optimal outcomes in terms of area, speed, and power efficiency, contributing to advancements in digital signal systems and processor design.

关键词： Power demand Computer architecture Very large scale integration Mathematical models delays Cryptography Hardware design languages Integrated circuit modeling Optimization Testing

来源：评论

学校读者我要写书评

暂无评论

3d Bone Shape Reconstruction from 2d X-ray Images Using MEd Generative Adversarial Network

3D Bone Shape Reconstruction from 2D X-ray Images Using MED ...

引用

Advanced Information and Communication Technology (ICAICT), international conference on

作者： Kazi Sohan Mohammad Abu Yousuf Institute of Information Technology Jahangirnagar University Dhaka Bangladesh

ISBN: (数字)9780738123233

ISBN: (纸本)9781665422406

Three-dimensional (3d) objects are always better than two-dimensional (2d) images for visualization. Very delicate information can be detected in 3d objects compared to 2d objects. The human brain can easily infer 3d information by observing 2d objects. But retrieving 3d information from a 2d object is very challenging for machines. For this reason, 3d shape reconstruction is one of the most researched topics in computer vision, deep learning, and medical science. 3d bone shapes are needed for pre-operative surgery planning and visualization. But the conventional methods of generating high-quality 3d bone-shape from 2d images are very time-consuming. This paper proposes a framework of Generative Adversarial Network Medical Generative Adversarial Network (MEd-GAN) to generate high-quality 3d bone-shape from 2d images. It generates 3d bone-shape using recent advances in convolution networks and generative adversarial networks. X-ray images are fed to the convolution network which is then converted to a d-dimensional vector by the convolution network. d-dimensional vector is fed to the GAN to reconstruct 3d bone shape.

关键词： Solid modeling Three-dimensional displays Shape Two dimensional displays Generative adversarial networks Bones X-ray imaging

来源：评论

学校读者我要写书评

暂无评论

Adaptation and applications of a realistic digital phantom based on patient lung tumor trajectories

引用

PHYSICS IN MEdICINE ANd BIOLOGY 2012年第11期57卷 3597-3608页

作者： Mishra, Pankaj St James, Sara Segars, W. Paul Berbeco, Ross I. Lewis, John H. Brigham & Womens Hosp Dana Farber Canc Inst Boston MA 02115 USA Harvard Univ Sch Med Boston MA USA Duke Univ Dept Radiol Durham NC 27710 USA

digital phantoms continue to play a significant role in modeling and characterizing medical imaging. The currently available XCAT phantom incorporates both the flexibility of mathematical phantoms and the realistic nature of voxelized phantoms. This phantom generates images based on a regular breathing pattern and can include arbitrary lung tumor trajectories. In this work, we present an algorithm that modifies the current XCAT phantom to generate 4d imaging data based on irregular breathing. First, a parameter is added to the existing XCAT phantom to include any arbitrary tumor motion. This modification introduces the desired tumor motion but, comes at the cost of decoupled diaphragm, chest wall and lung motion. To remedy this problem diaphragm and chest wall motion is first modified based on initial tumor location and then input to the XCAT phantom. This generates a phantom with synchronized respiratory motion. Mapping of tumor motion trajectories to diaphragm and chest wall motion is done by adaptively calculating a scale factor based on tumor to lung contour distance. The distance is calculated by projecting the initial tumor location to lung edge contours characterized by quadratic polynomials. data from ten patients were used to evaluate the accuracy between actual independent tumor location and the location obtained from the modified XCAT phantom. The RMSE and standard deviations for ten patients in x, y, and z directions are: (0.29 +/- 0.04, 0.54 +/- 0.17, and 0.39 +/- 0.06) mm. To demonstrate the utility of the phantom, we use the new phantom to simulate a 4dCT acquisition as well as a recently published method for phase sorting. The modified XCAT phantom can be used to generate more realistic imaging data for enhanced testing of algorithms for CT reconstruction, tumor tracking, and dose reconstruction.

关键词： Medical physics Biological physics

来源：评论

学校读者我要写书评

暂无评论

Novel 3d Reconstruction modeling Contributes to development of Orthopaedic Surgical Interventions

Novel 3D Reconstruction Modeling Contributes to Development ...

引用

The 4th international conference on Bioinformatics and Biomedical Engineering(第四届IEEE生物信息与生物医学工程国际会议 iCBBE 2010)

作者： Xing Ma Xiaoming Wu Yaoping Wu Jian Liu Long Sun Department of Orthopaedics First Affiliated Hospital of Medical School Xi’an Jiaotong University Xi’ Department of Orthopaedics First Affiliated Hospital of Medical School Xi'an Jiaotong University Xi' Department of Biomedical Engineering Xi'an 710032 P.R.China Department of Orthopaedics Xijing Hospital Fourth Military Medical University Xi'an 710032 P.R.Ch

Radiology plays important roles in orthopaedicsurgery. Although various conventional radiological assessmentsincluding digital X-rays, magnetic resonance imaging (MRI),computerized tomography (CT) and the three-dimensional (3d)CT reconstruction images have been widely developed andutilized for preoperative assessment and planning, there arelimitations. For example, despite the advances in 3d digitalreconstruction images, the 3d structure, anatomy and damagedsituation are still being inspected in a separate and flat manner(i.e. paper, film, etc.). Therefore the requirement of real 3dmodels for bone and joint has emerged clinically. In the presentstudy, a CAd based 3d visualization system and a rapidprototyping (RP) technique were used to fabricate 3d physicalmodels of highly difficult fractures and severe deformities inskeleton including severe pelvic/acetabular fractures,comminuted proximal humeral fractures, talar/ankle jointfractures, scoliolosis and progressive deformities in *** and benefits of the biomedical visualization-basedorthopaedic surgical strategies were elucidated.

关键词： Orthopedic surgery Image reconstruction Computed tomography Magnetic resonance imaging Joints Visualization Radiology X-rays Anatomy Bones

来源：评论

学校读者我要写书评

暂无评论

distributed simulator design by using of SimNetwork to overcome speed limit on GenSim

Distributed simulator design by using of SimNetwork to overc...

引用

international conference on recent advances in Space Technologies (RAST)

作者： Cheol H. Koo Hoon H. Lee Yee J. Cheon Satellite Flight Software Department Korea AeroSpace Research Institute Daejeon South Korea Satellite Control System Department Korea AeroSpace Research Institute Daejeon South Korea

GenSim(Generic Simulator) is a simulator infrastructure which is on engineering development level and will be used at software validation and verification of satellite flight software. GenSim is able to run software simulator models which follow ESA SMP/SMI standard. But also GenSim has to handle HILS with real I/O card, e.g. MIL-STd-1553B card or RS-422 digital I/O board to communicate with real spacecraft equipments. So GenSim has various shapes according to the usage and may take some limitation of speed to run it as realtime. To overcome this limitation, GenSim is designed to cooperate with remote GenSim which is separated by physically but connected by ethernet connection. In this case, GenSim is split with two or more simulator parts and there are some communication and synchronization mechanisms which are needed to maintain connection between the separated simulator parts. Some parts may take a role of simulator controller and other parts may take a role of external I/O simulator for interfacing with real spacecraft components. Smooth running and timing margin would benefit most from spatial separation of GenSim. Of course complexity of simulation model development will be decreased since a huge model can be decomposed by dividing it with several distributed models. distributed configuration of GenSim would make it easier when GenSim link with specialized simulator or system, e.g. camera simulator or 3d motion display system. A network is established to connect them with minimizing system complexity came from introducing system validation or mission validation requirement. SimNetwork is name of protocol which is invented to solve the interconnection methodology among distributed GenSims or between GenSim and the specialized simulators. SimNetwork is based on the ethernet TCP/IP stack and has simple protocol for control and data exchange between simulators which are connected via SimNetwork. A connection between simulators would be managed dynamically, so no s

关键词： Servers Computational modeling Military standards Adaptation models Protocols Satellites Kernel

来源：评论

学校读者我要写书评

暂无评论

detail Preserving depth Estimation from a Single Image Using Attention Guided Networks

Detail Preserving Depth Estimation from a Single Image Using...

引用

international conference on 3d imaging, modeling, Processing, Visualization and Transmission (3dIMPVT)

作者： Zhixiang Hao Yu Li Shaodi You Feng Lu State key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Advanced Digital Sciences Center Singapore Australian National University Beijing Advanced Innovation Center for Big Data-Based Precision Medicine Beihang University Beijing China

Convolutional Neural Networks have demonstrated superior performance on single image depth estimation in recent years. These works usually use stacked spatial pooling or strided convolution to get high-level information which are common practices in classification task. However, depth estimation is a dense prediction problem and low-resolution feature maps usually generate blurred depth map which is undesirable in application. In order to produce high quality depth map, say clean and accurate, we propose a network consists of a dense Feature Extractor (dFE) and a depth Map Generator (dMG). The dFE combines ResNet and dilated convolutions. It extracts multi-scale information from input image while keeping the feature maps dense. As for dMG, we use attention mechanism to fuse multi-scale features produced in dFE. Our Network is trained end-to-end and does not need any post-processing. Hence, it runs fast and can predict depth map in about 15 fps. Experiment results show that our method is competitive with the state-of-the-art in quantitative evaluation, but can preserve better structural details of the scene depth.

关键词： Feature extraction Convolution Estimation Fuses Semantics Three-dimensional displays Task analysis

来源：评论

学校读者我要写书评

暂无评论

advances in Calibration and data-Processing for a clinical semi-monolithic dOI-capable PET detector reaching sub-200 ps Timing Resolution

Advances in Calibration and Data-Processing for a clinical s...

引用

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： F. Mueller Y. Kuhl S. Naunheim M. Bovelett T.-M. Mai d. Schug V. Schulz Department of Physics of Molecular Imaging Systems Institute for Experimental Molecular Imaging RWTH Aachen University Aachen North Rhine-Westphalia Germany Hyperion Hybrid Imaging System Aachen North Rhine-Westphalia Germany

Total- and Whole-Body-PET scanners utilize numerous detectors introducing further challenges besides spatial, energy, and time resolution, such as fast calibration and cost-efficiency. Semi-monolithic detectors (called slabs) combine the advantages of pixelated and monolithic scintillators, providing intrinsic depth-of-interaction (dOI) capabilities, high density of optical photons as well as reduced dead time at a competitive cost compared to classical segmented arrays. Here, we present recent advances made in the different aspects of detector calibration and data processing. An array of 8 monolithic LYSO slabs of dimensions 3.9 x 32 x 19 mm 3 was coupled to a 64-channel photosensor array based on digital SiPMs (dPC 3200-22-44). Positioning calibration was performed using the supervised ML algorithm gradient tree boosting (GTB) and a fan beam collimator with multiple simultaneous irradiations allowing for fast calibration routines. The timing calibration includes an analytical correction of the detector time skews following GTB-based improvements. We achieved a spatial resolution in terms of mean absolute error (MAE) of 1.22 mm in planar and 1.86 mm in dOI direction, a coincidence resolution time (CRT) of 186 ps, and an energy resolution of 11.3%. The performance is better than or comparable to currently established clinical detectors following a segmented design concept. We put a special focus on the easy and fast applicability of the calibration methods to demonstrate a pathway for the broad translation of slab-based detectors into clinical PET systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

OctField: hierarchical implicit functions for 3d modeling 21

OctField: hierarchical implicit functions for 3D modeling

引用

Proceedings of the 35th international conference on Neural Information Processing Systems

作者： Jia-Heng Tang Weikai Chen Jie Yang Bo Wang Songrun Liu Bo Yang Lin Gao Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences Tencent Games Digital Content Technology Center

ISBN: (纸本)9781713845393

recent advances in localized implicit functions have enabled neural implicit representation to be scalable to large scenes. However, the regular subdivision of 3d space employed by these approaches fails to take into account the sparsity of the surface occupancy and the varying granularities of geometric details. As a result, its memory footprint grows cubically with the input volume, leading to a prohibitive computational cost even at a moderately dense decomposition. In this work, we present a learnable hierarchical implicit representation for 3d surfaces, coded OctField, that allows high-precision encoding of intricate surfaces with low memory and computational budget. The key to our approach is an adaptive decomposition of 3d scenes that only distributes local implicit functions around the surface of interest. We achieve this goal by introducing a hierarchical octree structure to adaptively subdivide the 3d space according to the surface occupancy and the richness of part geometry. As octree is discrete and non-differentiable, we further propose a novel hierarchical network that models the subdivision of octree cells as a probabilistic process and recursively encodes and decodes both octree structure and surface geometry in a differentiable manner. We demonstrate the value of OctField for a range of shape modeling and reconstruction tasks, showing superiority over alternative approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Microfluidic Biosensor for Bioengineering: High-frequency Equivalent-Circuit modeling of Interdigital Capacitor

Microfluidic Biosensor for Bioengineering: High-frequency Eq...

引用

international conference on Telecommunications in Modern Satellite, Cable and Broadcasting Service (TELSIKS)

作者： Giovanni Crupi Xiue Bao Paweł Barmuta Ilja Ocket dominique M. M.-P. Schreurs Bart Nauwelaers Department of Biomedical and Dental Sciences and Morphofunctional Imaging University of Messina Messina Italy Electronic Engineering Department KU Leuven Leuven Belgium

ISBN: (数字)9781728108780

ISBN: (纸本)9781728108797

Microwave biosensing is a rapidly growing field of bioengineering. The progress in micro- and nanotechnologies and the recent advances in microwave dielectric spectroscopy have allowed a rapid development in the miniaturization of high-frequency biosensors. There has therefore been intensive research during the last few years on investigating miniature microwave biosensors for liquid characterization. To contribute to the advancement of this challenging and stimulating field of research, the present contribution is devoted to the analysis of a microfluidic sensor based on a one-port coplanar interdigital capacitor (IdC). The high-frequency performance of the studied sensor is achieved by using the 3d finite-element method (FEM) by Ansoft's high frequency structure simulator (HFSS). The simulations are used for extracting and validating an equivalent-circuit model that can be further exploited for complex permittivity extraction of the material under test.

关键词： Biosensors Microfluidics Capacitors Fingers Microwave circuits Permittivity

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：