Filters








4,901 Hits in 5.6 sec

Invasive Compute Balancing for Applications with Shared and Hybrid Parallelization

Martin Schreiber, Christoph Riesinger, Tobias Neckel, Hans-Joachim Bungartz, Alexander Breuer
2014 International journal of parallel programming  
Achieving high scalability with dynamically adaptive algorithms in high-performance computing (HPC) is a non-trivial task.  ...  The invasive paradigm using compute migration represents an efficient alternative to classical data migration approaches for such algorithms in HPC.  ...  Acknowledgements This work was supported by the German Research Foundation (DFG) as part of the Transregional Collaborative Research Centre "Invasive Computing" (SFB/TR 89).  ... 
doi:10.1007/s10766-014-0336-3 fatcat:3epov6cgnzeetpkhtyazctlrzy

Deep Learning Fast Screening Approach on Cytological Whole Slides for Thyroid Cancer Diagnosis

Yi-Jia Lin, Tai-Kuang Chao, Muhammad-Adil Khalil, Yu-Ching Lee, Ding-Zhi Hong, Jia-Jhen Wu, Ching-Wei Wang
2021 Cancers  
In clinical practice, visual inspection of cytopathological slides is an essential initial method used by the pathologist to diagnose PTC.  ...  Manual visual assessment of the whole slide images is difficult, time consuming, and subjective, with a high inter-observer variability, which can sometimes lead to suboptimal patient management due to  ...  Thyroid fine needle aspiration (FNA) is an important, safe tool for diagnosing PTC with an accuracy of approximately 94%, and a high degree of sensitivity, specificity [4, 5] .  ... 
doi:10.3390/cancers13153891 fatcat:s2b4of4nwzc23lrvnevzecluyi

Biomechanical rupture risk assessment of abdominal aortic aneurysms using clinical data: A patient-specific, probabilistic framework and comparative case-control study

Lukas Bruder, Jaroslav Pelisek, Hans-Henning Eckstein, Michael W. Gee, Janet Powell
2020 PLoS ONE  
For the efficient evaluation of this index, a flexible Kriging-based surrogate model with an active training process is proposed.  ...  Our novel framework builds upon a comprehensive database of tensile test results that were carried out on 305 AAA tissue samples from 139 patients, as well as corresponding non-invasively and clinically  ...  a prospective new patient with non-invasive properties ξ.  ... 
doi:10.1371/journal.pone.0242097 pmid:33211767 pmcid:PMC7676745 fatcat:q23hemzq2nfilbej7hohgmlxk4

The role of the image phase in cardiac strain imaging

M. Alessandrini, A. Basarab, M. De Craene, M. Sermesant, H. Liebgott, O. Bernard, J. D'hooge
2015 2015 23rd European Signal Processing Conference (EUSIPCO)  
cardiac deformation imaging, which includes a motion estimation framework based on the conservation of the image phase over time and an open pipeline to benchmark algorithms for cardiac strain imaging  ...  The paper also shows an original evaluation of the proposed motion estimation technique based on the new benchmarking pipeline.  ...  INTRODUCTION Evolving medical imaging technologies such as ultrasound (US) and magnetic resonance imaging (MRI) allow visualizing the cardiac muscle non-invasively with increasingly high spatial and temporal  ... 
doi:10.1109/eusipco.2015.7362894 dblp:conf/eusipco/AlessandriniBCS15 fatcat:oqwrr4v4qvbbxf2ouzksdmm7ta

Run-Time Interoperability Between Neuronal Network Simulators Based on the MUSIC Framework

Mikael Djurfeldt, Johannes Hjorth, Jochen M. Eppler, Niraj Dudani, Moritz Helias, Tobias C. Potjans, Upinder S. Bhalla, Markus Diesmann, Jeanette Hellgren Kotaleski, Örjan Ekeberg
2010 Neuroinformatics  
Benchmarks show that the MUSIC pilot implementation provides efficient data transfer in a cluster computer with good scaling.  ...  An event is a pair of an index identifier, either a shared global index or a local index, and a doubleprecision floating point time-stamp.  ...  While both solutions are non-exclusive in the sense that they could potentially co-exist with each other and/or other communication frameworks, MUSIC does not require the re-organization of an existing  ... 
doi:10.1007/s12021-010-9064-z pmid:20195795 pmcid:PMC2846392 fatcat:pdr32zf6pbhvppia4ia5wyknaq

A Multi-objective Invasive Weed Optimization Method for Segmentation of Distress Images

Eslam Mohammed Abdelkader, Osama Moselhi, Mohamed Marzouk, Tarek Zayed
2020 Intelligent Automation and Soft Computing  
Thus, the subjectivity associated with the visual inspectionbased methods requires the development of an automated method for the detection of cracks.  ...  CONVENTIONAL IMAGE SEGMENTATION METHODS THIS section provides an overview of some of the conventional image segmentation methods that the proposed method is compared with, in order to demonstrate the capabilities  ... 
doi:10.32604/iasc.2020.010100 fatcat:esmpqozgfrbr5kykqakqarlsbe

Multi-view 3D skin feature recognition and localization for patient tracking in spinal surgery applications

Francesca Manni, Marco Mamprin, Ronald Holthuizen, Caifeng Shan, Gustav Burström, Adrian Elmi-Terander, Erik Edström, Svitlana Zinger, Peter H. N. de With
2021 BioMedical Engineering OnLine  
The localization accuracy was compared to a system with conventional markers, serving as a ground truth. An average accuracy of 0.627 and 0.622 mm was achieved for MSER and SURF, respectively.  ...  In the future, the framework may be further improved by exploiting extended feature processing using modern optical imaging techniques for clinical applications where patient tracking is crucial.  ...  In this feasibility study, the triangulation error was used as evaluation metric to obtain an index of the triangulation accuracy, and then, the 3D point locations were used to perform a benchmark against  ... 
doi:10.1186/s12938-020-00843-7 pmid:33413426 fatcat:kjigz3zinbctjg2zpkacu4e7zu

Locally Sparse Neural Networks for Tabular Biomedical Data [article]

Junchen Yang, Ofir Lindenbaum, Yuval Kluger
2022 arXiv   pre-print
Furthermore, the proposed framework dramatically outperforms existing schemes when evaluating its interpretability capabilities.  ...  Tabular datasets with low-sample-size or many variables are prevalent in biomedicine.  ...  As visually indicated by this figure, LLSPIN, Real-X, and L2X tend to select pixels with non-zero values that cover "unique" patterns in the digits.  ... 
arXiv:2106.06468v2 fatcat:psertidh55ajvly7k5lgsthtsq

The Java Image Science Toolkit (JIST) for Rapid Prototyping and Publishing of Neuroimaging Software

Blake C. Lucas, John A. Bogovic, Aaron Carass, Pierre-Louis Bazin, Jerry L. Prince, Dzung L. Pham, Bennett A. Landman
2010 Neuroinformatics  
Non-invasive neuroimaging techniques enable extraordinarily sensitive and specific in vivo study of the structure, functional response and connectivity of biological mechanisms.  ...  Java-based rapid prototyping with this system is an efficient and practical approach to evaluate new algorithms since the proposed system ensures that rapidly constructed prototypes are actually fully-functional  ...  With these capabilities, JIST provides an open-source, platform-independent framework to rapidly develop image analysis tools and distribute them to the scientific community.  ... 
doi:10.1007/s12021-009-9061-2 pmid:20077162 pmcid:PMC2860951 fatcat:i3jilk4wjfdn7nr4t3uospc3u4

Livestock Monitoring with Transformer [article]

Bhavesh Tangirala, Ishan Bhandari, Daniel Laszlo, Deepak K. Gupta, Rajat M. Thomas, Devanshu Arya
2021 arXiv   pre-print
For benchmarking, we present Pigtrace, a carefully curated dataset comprising video sequences with instance level bounding box, segmentation, tracking and activity classification of pigs in real indoor  ...  We present starformer, the first end-to-end multiple-object livestock monitoring framework that learns instance-level embeddings for grouped pigs through the use of transformer architecture.  ...  Stationary RGB cameras, already available in most modern farms, facilitate implementation that is cost effective, non-invasive, and scalable.  ... 
arXiv:2111.00801v2 fatcat:lnen6f2ulzckbafjaxfrg674fq

Implicit active constraints for concentric tube robots based on analysis of the safe and dexterous workspace

Konrad Leibrandt, Christos Bergeles, Guang-Zhong Yang
2017 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)  
Under this guidance scheme, the user can make informed decisions and maintain full control of the path planning and manipulation processes, with intuitive visual feedback on when the robot's limitations  ...  Furthermore, the operator is often presented with guidance paths which have to be followed approximately.  ...  With the TIA approach the heterogeneous approach shows an increased performance of 54 %. The two top benchmarks depicted in Table III report results of a non-fully utilized GPU.  ... 
doi:10.1109/iros.2017.8202157 dblp:conf/iros/LeibrandtBY17 fatcat:z76fw7nu5ffhpjkij3noi4ksqu

Joint reconstruction of compressively sensed ultrasound RF echoes by exploiting temporal correlations

George Tzagkarakis, Alin Achim, Panagiotis Tsakalides, Jean-Luc Starck
2013 2013 IEEE 10th International Symposium on Biomedical Imaging  
Our experimental evaluation reveals an improved performance, both visually and in terms of quality metrics, such as the SSIM and PSNR, when such correlations are extracted during the joint reconstruction  ...  of RF echoes, compared with previous methods based on the separate recovery of each RF echo.  ...  Specifically, ultrasound imaging systems are non-invasive, versatile, they do not use ionizing radiation, and they can be embedded in relatively low-cost portable devices, which operate in real time.  ... 
doi:10.1109/isbi.2013.6556554 dblp:conf/isbi/TzagkarakisATS13 fatcat:mooauaq3k5edva6jgvb5lpcp7y

Hadoop++

Jens Dittrich, Jorge-Arnulfo Quiané-Ruiz, Alekh Jindal, Yagiz Kargin, Vinay Setty, Jörg Schad
2010 Proceedings of the VLDB Endowment  
Our experiments show the superiority of Hadoop++ over both Hadoop and HadoopDB for tasks related to indexing and join processing.  ...  Hence, the performance of Hadoop -an open-source implementation of MapReduce -often does not match the one of a well-configured parallel DBMS.  ...  Non-Invasive: We do not change the existing Hadoop framework. Our index structure is implemented by providing the right UDFs. (3.)  ... 
doi:10.14778/1920841.1920908 fatcat:gldzhlwrmfen3kaqsdmwhlon7e

OptMark: A Toolkit for Benchmarking Query Optimizers [article]

Zhan Li, Olga Papaemmanouil, Mitch Cherniack
2016 arXiv   pre-print
OptMark includes also a generic benchmarking toolkit that is minimum invasive to the DBMS that wishes to use it.  ...  Indeed, existing performance benchmarks for database engines (like TPC benchmarks) produce a performance assessment of the query runtime system rather than its query optimizer.  ...  It could be extended to any schema and query set, but we want to focus on queries that stress the performance of an optimizer. Typically, these are queries with non-trivia number of joins.  ... 
arXiv:1608.02611v1 fatcat:hvrianwhrvfxrcse2hcrlkswvq

Deep Cross-Subject Mapping of Neural Activity [article]

Marko Angjelichinoski, Bijan Pesaran, Vahid Tarokh
2022 arXiv   pre-print
We verify our approach on an experimental data set in which two macaque monkeys perform memory-guided visual saccades to one of eight target locations.  ...  We cast the problem of neural activity mapping in a probabilistic framework where we adopt deep generative modelling.  ...  acquiring training data in non-invasive setups is relatively straight-forward procedure even with human subjects.  ... 
arXiv:2007.06407v3 fatcat:yxl2tksa55gvjhlmzl5l6sudfu
« Previous Showing results 1 — 15 out of 4,901 results