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

Cosine histogram analysis for spectral image data classification.

Jing Zhang1, Anne O'Connor, John F Turner

  • 1Department of Chemistry, Cleveland State University, Cleveland, Ohio 44115, USA.

Applied Spectroscopy
|December 21, 2004
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

Education programmes on performance-based assessment for allied health and nursing clinical educators: A scoping review protocol.

HRB open research·2025
Same author

Performance of comprehensive first trimester fetal anatomy assessment.

Prenatal diagnosis·2023
Same author

The Invisible Voice.

Academic emergency medicine : official journal of the Society for Academic Emergency Medicine·2022
Same author

Assessing the relationship between psychosocial risk and pregnancy outcomes using the perinatal integrated psychosocial assessment (PIPA) tool.

Birth (Berkeley, Calif.)·2022
Same author

Impact of role conflicts and self-efficacy on academic performance of graduate-entry healthcare students: A lagged study.

Nursing & health sciences·2022
Same author

A feedback journey: employing a constructivist approach to the development of feedback literacy among health professional learners.

BMC medical education·2021

This study introduces cosine histogram analysis (CHA) to differentiate abnormal cervical cells from normal ones using spectral data. CHA analyzes cosine correlation scores to provide a likelihood of abnormality for each pixel, improving diagnostic accuracy.

Area of Science:

  • Biomedical optics
  • Computational pathology
  • Digital image analysis

Background:

  • Multivariate strategies for sample composition analysis often rely on subtle spectral shape differences.
  • Distinguishing between normal and abnormal biological tissues using spectral data can be challenging due to overlapping spectral variations.
  • Existing methods struggle with the complexity of spectral shapes within a single sample class and similarities between different classes.

Purpose of the Study:

  • To develop a novel method for differentiating abnormal cervical cells from normal cells using spectral image analysis.
  • To introduce cosine histogram analysis (CHA) as a quantitative tool for assessing cellular abnormality.
  • To enhance the accuracy of qualitative estimates of sample composition in cytopathology.

Main Methods:

Related Experiment Videos

  • Statistical analysis of cosine correlation scores derived from multispectral visible absorption images of stained cervical Papanicolaou samples.
  • Application of cosine histogram analysis (CHA) to frequency distribution of spectral cosine correlation scores from cell nuclei.
  • Pixel-level analysis to determine the percent likelihood of abnormality.

Main Results:

  • Abnormal cells can be effectively differentiated from the background of normal cells based on spectral analysis.
  • Cosine histogram analysis (CHA) demonstrates utility in distinguishing cellular abnormalities.
  • The method provides a quantitative measure (percent likelihood of abnormality) for each pixel.

Conclusions:

  • Cosine histogram analysis (CHA) offers a robust method for identifying abnormal cells in cervical Papanicolaou samples.
  • This approach overcomes limitations of conventional multivariate strategies by analyzing spectral correlation scores.
  • CHA provides a novel, pixel-level assessment of abnormality, advancing digital pathology techniques.