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

Discriminating benign from malignant thyroid lesions using artificial intelligence and statistical selection of

Beatrix Cochand-Priollet1, Konstantinos Koutroumbas, Tatiana Mona Megalopoulou

  • 1Service Central d'Anatomie et de Cytologie Pathologiques, Hospital Lariboisiere, Paris, France.

Oncology Reports
|March 10, 2006
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

Rotational thromboelastometry analysis of recovered plasma stored for a long period of time.

Asian journal of transfusion science·2026
Same author

Dead-Space Microdomains as Explicit Barriers to Extracellular Drug Transport in Alzheimer's Disease.

Pharmaceutical research·2026
Same author

Cytopathology Terminology Systems: European Federation of Cytological Societies Survey on Practice in Europe.

Cytopathology : official journal of the British Society for Clinical Cytology·2026
Same author

Recent evidence on quality of life following total gastrectomy for gastric cancer: A scoping review.

Medicine international·2026
Same author

A rare coexistence: Ollier disease and primary hyperparathyroidism-mere coincidence or expanding the spectrum of Ollier disease?

JBMR plus·2026
Same author

[Case #6. Suspicious for a papillary carcinoma sub-type follicular variant. According to the 2023 Bethesda system: Suspicious for malignancy (category V)].

Annales de pathologie·2026

This study compared classifiers for distinguishing benign from malignant thyroid lesions using nuclear features from fine needle aspiration (FNA) cytology. Four key features effectively differentiated lesion types, showing promise for laboratory use.

Area of Science:

  • Cytopathology
  • Medical image analysis
  • Machine learning in diagnostics

Background:

  • Accurate differentiation of benign from malignant thyroid lesions is crucial for patient management.
  • Fine needle aspiration (FNA) cytology is a primary diagnostic tool, but interpretation can be challenging.
  • Automated image analysis offers potential to improve diagnostic accuracy and efficiency.

Purpose of the Study:

  • To compare the effectiveness of different classifiers in distinguishing benign from malignant thyroid lesions.
  • To identify key nuclear features for accurate lesion discrimination.
  • To evaluate the potential of an automated system in routine cytological analysis.

Main Methods:

  • Analysis of 25 nuclear features from May Grunvald-Giemsa stained FNA smears using a custom image analysis system.

Related Experiment Videos

  • Statistical pre-processing to identify the most discriminative features.
  • Training and testing of four different classifiers using selected nuclear features.
  • Classification performed at both nuclear and patient levels.

    • Main Results:

    • Statistical analysis identified 4 crucial nuclear features for discriminating benign from malignant thyroid lesions.
    • The developed technique demonstrated encouraging classification performance.
    • The system showed potential for assisting in daily cytological laboratory routines.

    Conclusions:

    • A subset of 4 nuclear features is highly effective for classifying thyroid lesions.
    • The automated image analysis approach shows promise as a supportive tool in cytopathology.
    • This technique could enhance the accuracy and efficiency of thyroid nodule diagnosis.