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

A geometric model for 3-D confocal image analysis.

A Sarti1, C Ortiz de Solórzano, S Lockett

  • 1Lawrence Berkeley National Laboratory, University of California, Berkeley, CA 94720, USA. asarti@math.lbl.gov

IEEE Transactions on Bio-Medical Engineering
|December 28, 2000
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

In silico evaluation of the potential of very high energy electrons delivered in both conventional and FLASH regimes for the SBRT treatment of pancreatic cancer: A report of three case studies.

Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)·2025
Same author

Erratum: Lymphopenia-induced lymphoproliferation drives activation of naive T cells and expansion of regulatory populations.

iScience·2025
Same author

Observation of Exotic J/ψϕ Resonant Structure in Diffractive Processes in Proton-Proton Collisions.

Physical review letters·2025
Same author

Observation of New Charmonium or Charmoniumlike States in B^{+}→D^{*±}D^{∓}K^{+} Decays.

Physical review letters·2024
Same author

Modification of χ_{c1}(3872) and ψ(2S) Production in pPb Collisions at sqrt[s_{NN}]=8.16  TeV.

Physical review letters·2024
Same author

Amplitude Analysis of the B^{0}→K^{*0}μ^{+}μ^{-} Decay.

Physical review letters·2024

This study introduces partial-differential-equation-based filtering to improve nuclear shape analysis in computer-aided cytology. The novel filtering strategy enhances edge fidelity and accuracy in segmenting and classifying cell nuclei from microscopy images.

Area of Science:

  • Medical image analysis
  • Computational pathology
  • Biomedical imaging

Background:

  • Accurate nuclear shape extraction is crucial for quantitative analysis in cytology.
  • Confocal microscopy images present challenges for precise nuclear segmentation.
  • Existing methods may struggle with edge fidelity and surface accuracy.

Purpose of the Study:

  • To develop and evaluate a partial-differential-equation-based filtering strategy for computer-aided cytology.
  • To enhance the accuracy of nuclear shape extraction and classification from microscopy images.
  • To improve both intranuclear and internuclear analyses through refined nuclear surface definition.

Main Methods:

  • Utilized geometry-driven, edge-preserving image smoothing as a preprocessing step before nuclear segmentation.

Related Experiment Videos

  • Applied the same filtering mechanism with adjusted initial conditions for sub-pixel nuclear surface smoothing.
  • Employed the filter as a post-processing tool to correct segmentation misinterpretations of nuclear surfaces.

    • Main Results:

    • The proposed geometry-driven filter demonstrated superior edge fidelity compared to other widely-used filters.
    • Achieved sub-pixel accuracy in smoothing nuclear surfaces.
    • The pre- and post-filtering approach significantly improved the definition of nuclear surfaces.

    Conclusions:

    • Partial-differential-equation-based filtering is an effective strategy for enhancing nuclear segmentation in computer-aided cytology.
    • The filtering approach provides substantial and measurable improvements in nuclear surface definition.
    • This method complements existing segmentation strategies, leading to more accurate quantitative analyses.