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 Experiment Videos

Fast automated cell phenotype image classification.

Nicholas A Hamilton1, Radosav S Pantelic, Kelly Hanson

  • 1ARC Centre in Bioinformatics, University of Queensland, Brisbane, Queensland 4072, Australia. n.hamilton@imb.uq.edu.au

BMC Bioinformatics
|March 31, 2007
PubMed
Summary
This summary is machine-generated.

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

Disruption of Retriever Function Impacts Retrograde Trafficking From Endosomes.

Cell biology international·2025
Same author

Pediatric Trauma Care Standardization: A Statewide Survey of Trauma Providers and Program Managers.

The Journal of surgical research·2023
Same author

Impact of institutional prophylaxis guidelines on rates of pediatric venous thromboembolism following trauma-A multicenter study from the pediatric trauma society research committee.

The journal of trauma and acute care surgery·2023
Same author

Sugar transporter Slc37a2 regulates bone metabolism in mice via a tubular lysosomal network in osteoclasts.

Nature communications·2023
Same author

Multifaceted Roles of Retromer in EGFR Trafficking and Signaling Activation.

Cells·2022
Same author

Venous thromboembolic screening in pediatric trauma: A prospective cohort study of risk-stratified ultrasonography.

The journal of trauma and acute care surgery·2022
Same journal

OpenIMC: an open-source platform for analyzing single-cell and spatial proteomics by imaging mass cytometry.

BMC bioinformatics·2026
Same journal

NAP: an open source pipeline for cross-domain microbiome profiling using Nanopore sequencing-derived amplicon data.

BMC bioinformatics·2026
Same journal

SurvGME: an R package for survival analysis with graphical and measurement error models.

BMC bioinformatics·2026
Same journal

SimMapNet: a Bayesian framework for gene regulatory network inference using gene ontology similarities as external hint.

BMC bioinformatics·2026
Same journal

Dual channel drug-drug interactions extraction based on cross attention.

BMC bioinformatics·2026
Same journal

FeSseqdb: a curated sequence-level database and interpretable machine learning framework for identifying iron-sulfur proteins.

BMC bioinformatics·2026
See all related articles

New threshold adjacency statistics rapidly and accurately classify protein sub-cellular localization images. This computational method enhances high-throughput analysis without cell cropping, advancing biological research.

Area of Science:

  • Computational biology
  • Cellular imaging
  • Bioinformatics

Background:

  • The genomic revolution necessitates high-throughput analysis of protein function.
  • Automated fluorescent microscopy generates large-scale sub-cellular localization images.
  • Existing image statistics methods are slow and require cell cropping, limiting throughput.

Purpose of the Study:

  • Introduce novel threshold adjacency statistics for automated sub-cellular image classification.
  • Develop a computational technique to efficiently quantify and classify protein localization.
  • Overcome limitations of existing methods in speed and cell selection.

Main Methods:

  • Developed threshold adjacency statistics by analyzing pixel adjacency after image thresholding.

Related Experiment Videos

  • Applied these statistics to classify sub-cellular localization in two distinct image datasets (endogenous and transfected proteins).
  • Utilized support vector machines for classification and compared performance with existing measures.

    • Main Results:

    • Achieved high classification accuracies: 94.4% (endogenous) and 86.6% (transfected).
    • Threshold adjacency statistics are an order of magnitude faster than commonly used measures.
    • Combined with Haralick measures, accuracies reached 98.2% (endogenous) and 93.2% (transfected).

    Conclusions:

    • Threshold adjacency statistics offer a fast and accurate method for computational image analysis.
    • Eliminates the need for cell cropping, enabling large-scale, high-throughput applications.
    • Has potential to significantly advance the scale and scope of sub-cellular image analysis.