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

Image mining for investigative pathology using optimized feature extraction and data fusion.

Wenjin Chen1, Peter Meer, Bogdan Georgescu

  • 1Center for Biomedical Imaging & Informatics, Room R203, 675 Hoes Lane, Piscataway, NJ 08854, USA. wjc@pleiad.umdnj.edu

Computer Methods and Programs in Biomedicine
|May 24, 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

Organ masks applied in feature space improve weakly supervised scan-level CT classification.

Scientific reports·2026
Same author

Predictors of Pathological Complete Response and Patient-Reported Outcomes During Neoadjuvant Chemotherapy in Early Breast Cancer: A Single-Center Retrospective Cohort Study.

Cureus·2026
Same author

PatchCLIP enables region specific contrastive health record and image joint training with patch embedding loss.

Scientific reports·2026
Same author

Fairness aware subset selection for advancing equity in skin cancer detection.

Journal of the American Medical Informatics Association : JAMIA·2026
Same author

Deep learning-based pulmonary nodule risk assessment outperforms established malignancy risk scores in lung cancer screening.

Radiology advances·2026
Same author

The Performance of Protein Meal from <i>Hermetia illucens</i> Larvae in Hetero-Clarias Hybrid Farming.

Insects·2025

This study introduces an intelligent archiving system to improve diagnostic accuracy in pathology. The system enhances classification reliability for diseases like lymphomas and leukemia using texture descriptors and density estimation.

Area of Science:

  • Digital Pathology
  • Computational Pathology
  • Medical Informatics

Background:

  • Pathology diagnoses face complexity due to lack of definitive criteria, leading to disparities between expert and non-expert assessments.
  • Previous work developed an Image Guided Decision Support (IGDS) system for discriminating between malignant lymphomas and leukemia.
  • A need exists for automated systems to manage and analyze histological data for improved diagnostic accuracy.

Purpose of the Study:

  • To develop and evaluate a web-based intelligent archiving subsystem for automated cell detection, imaging, and indexing into ground-truth databases.
  • To enhance the reliability and performance of diagnostic classification systems in pathology.
  • To reduce the dimensionality of feature spaces in image analysis for pathology.

Main Methods:

Related Experiment Videos

  • Development of a web-based intelligent archiving subsystem.
  • Implementation of automated cell detection, imaging, and indexing into distributed databases.
  • Utilization of robust texture descriptors and density estimation-based fusion for classification.

Main Results:

  • The intelligent archiving subsystem automatically detects, images, and indexes new cells into ground-truth databases.
  • Significant improvements in reliability and performance of classification were achieved.
  • Dimensionality of the feature space was reduced through the applied methods.

Conclusions:

  • The developed web-based intelligent archiving subsystem enhances diagnostic decision support in pathology.
  • The integration of texture descriptors and density estimation-based fusion significantly improves classification accuracy.
  • This approach offers a scalable solution for building and utilizing ground-truth databases in digital pathology.