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

Automatic selection of parameters for vessel/neurite segmentation algorithms.

Muhammad-Amri Abdul-Karim1, Badrinath Roysam, Natalie M Dowell-Mesfin

  • 1Rensselaer Polytechnic Institute, Troy, NY 12180, USA. abdulm@ecse.rpi.edu

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|September 30, 2005
PubMed
Summary

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

The Influence of Age on the Pharmacokinetics of Enrofloxacin and Ciprofloxacin in Calves.

Veterinary sciences·2026
Same author

Detecting amyloid-β pathology in subjective cognitive decline using plasma and CSF biomarkers.

EBioMedicine·2026
Same author

Pharmacokinetics and Bioavailability of Tolfenamic Acid in Calves: First Evaluation of Subcutaneous Administration.

Veterinary medicine and science·2026
Same author

Weak-to-strong generalization enables fully automated training of multi-head mask-RCNN model for segmenting densely overlapping cell nuclei in multiplex whole-slice brain images.

Frontiers in bioinformatics·2026
Same author

Pharmacokinetic Profiles of Enrofloxacin and Its Metabolite Ciprofloxacin Administered by Different Doses in Calves.

Journal of veterinary pharmacology and therapeutics·2026
Same author

Computational delineation and cellular profiling of murine cortical cell layers using multiplex immunofluorescence imaging.

Journal of neuroscience methods·2026

This study introduces an automated method for optimizing image segmentation parameters, improving accuracy and accessibility for users without technical expertise. The novel approach enhances morphometric analysis in biological imaging.

Area of Science:

  • Neuroscience
  • Biomedical Imaging
  • Computational Biology

Background:

  • Accurate segmentation of neural structures and blood vessels is crucial for quantitative morphometric analysis in neuroscience and biomedical research.
  • Manual or semi-automated parameter selection for segmentation algorithms is often subjective, time-consuming, and requires specialized expertise, limiting reproducibility and broad application.
  • Existing automated methods may lack robustness or user-friendliness, hindering widespread adoption in diverse research settings.

Purpose of the Study:

  • To develop and validate an automated, objective method for selecting optimal parameter settings for vessel/neurite segmentation algorithms.
  • To enhance the accuracy and applicability of segmentation algorithms for non-expert users.
  • To improve the efficiency and reduce the technical burden associated with image analysis in biological research.

Related Experiment Videos

Main Methods:

  • Implementation of an automated parameter selection method based on the minimum description length (MDL) principle and a recursive random search algorithm.
  • The method balances image-content coverage with conciseness to objectively determine optimal algorithm parameters.
  • Application of the method to segment 223 images of human retinas and cultured neurons from multiple sources, optimizing an eight-parameter segmentation algorithm.

Main Results:

  • Significant improvements in segmentation quality (4.7%-21%) compared to default settings were achieved after 1000 iterations, with most gains realized within the first 44 iterations.
  • Statistical analysis confirmed the significant improvement in segmentation quality (p < 0.0005).
  • A strong positive correlation (p = 0.78) was observed between improvements in description length and agreement with ground truth data.

Conclusions:

  • The automated parameter selection method objectively optimizes vessel/neurite segmentation algorithms, enhancing morphometric accuracy and broadening algorithm applicability.
  • The approach simplifies user interaction, reduces the need for technical expertise, and is adaptable to different image datasets and computational environments.
  • This method offers a modular, extensible, and parallelizable solution for robust biological image analysis, improving efficiency and reliability.