Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Pressure-induced softening of locust bean gum hydrogels: A counterintuitive alternative to freeze-thaw stiffening.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Impact of Concurrent Graft-versus-Host Disease on Long-Term Survival in Critically Ill Patients Following Allogeneic Hematopoietic Stem Cell Transplantation for Hematological Malignancies.

Transplantation and cellular therapy·2026
Same author

Enhancing minority class recovery in high resolution land cover mapping with dynamic imbalance aware oversampling.

Scientific reports·2026
Same author

Haploidentical allogeneic haematopoietic stem cell transplantation for paroxysmal nocturnal haemoglobinuria: a retrospective analysis.

Annals of hematology·2026
Same author

Association of <i>katG</i>, <i>inhA,</i> and <i>AhpC</i> Mutations with Isoniazid Resistance of <i>Mycobacterium tuberculosis</i> in Pulmonary Tuberculosis Patients from Nanjing, China.

Microbial drug resistance (Larchmont, N.Y.)·2026
Same author

Machine Learning Models Used to Predict Abdominal Aortic Aneurysm Growth and Rupture: A Systematic Review and Critical Appraisal.

Annals of vascular surgery·2026

Related Experiment Video

Updated: Apr 7, 2026

Databases to Efficiently Manage Medium Sized, Low Velocity, Multidimensional Data in Tissue Engineering
09:43

Databases to Efficiently Manage Medium Sized, Low Velocity, Multidimensional Data in Tissue Engineering

Published on: November 22, 2019

6.9K

Region Templates: Data Representation and Management for High-Throughput Image Analysis.

George Teodoro1, Tony Pan2, Tahsin Kurc3

  • 1Department of Computer Science, University of Brasília, Brasília, DF, Brazil.

Parallel Computing
|July 4, 2015
PubMed
Summary

A new region template abstraction efficiently manages large, high-resolution image datasets on hybrid computing clusters. This framework optimizes data processing and transfer, achieving high performance for scientific imaging applications.

Keywords:
GPGPUHeterogeneous EnvironmentsImageStorage and I/O

More Related Videos

Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis
07:59

Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis

Published on: October 28, 2022

3.7K
Three and Four-Dimensional Visualization and Analysis Approaches to Study Vertebrate Axial Elongation and Segmentation
12:59

Three and Four-Dimensional Visualization and Analysis Approaches to Study Vertebrate Axial Elongation and Segmentation

Published on: February 28, 2021

4.3K

Related Experiment Videos

Last Updated: Apr 7, 2026

Databases to Efficiently Manage Medium Sized, Low Velocity, Multidimensional Data in Tissue Engineering
09:43

Databases to Efficiently Manage Medium Sized, Low Velocity, Multidimensional Data in Tissue Engineering

Published on: November 22, 2019

6.9K
Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis
07:59

Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis

Published on: October 28, 2022

3.7K
Three and Four-Dimensional Visualization and Analysis Approaches to Study Vertebrate Axial Elongation and Segmentation
12:59

Three and Four-Dimensional Visualization and Analysis Approaches to Study Vertebrate Axial Elongation and Segmentation

Published on: February 28, 2021

4.3K

Area of Science:

  • Computer Science
  • Image Processing
  • High-Performance Computing

Background:

  • Analyzing large, high-resolution image datasets requires efficient storage, management, and processing.
  • Hybrid computing clusters (CPUs and GPUs) offer computational power but pose data transfer challenges.

Purpose of the Study:

  • To introduce a region template abstraction and framework for efficient data handling in large-scale image analysis.
  • To optimize data processing and transfer on hybrid computing nodes.
  • To enable high-throughput analysis of complex imaging datasets.

Main Methods:

  • Developed a region template abstraction for generic data structures within spatial-temporal bounding boxes.
  • Implemented a hierarchical dataflow representation for applications coordinated by a runtime system.
  • Incorporated performance-aware scheduling and CPU-GPU data transfer optimizations for hybrid machines.

Main Results:

  • The region template abstraction introduced negligible overhead (approx. 3%) with good scalability and high data transfer rates.
  • Optimizations for asynchronous data transfers and computation yielded a 1.13x performance gain.
  • Achieved a processing rate of 11,730 4K×4K tiles per minute on a 100-node hybrid cluster.

Conclusions:

  • The region template abstraction provides a unified interface for efficient data management and processing of large image datasets on hybrid clusters.
  • The framework significantly enhances performance and scalability for scientific imaging applications.
  • Enables high-throughput analysis crucial for studies involving massive datasets.