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

Retina lesion and microaneurysm segmentation using morphological reconstruction methods with ground-truth data.

Thomas P Karnowski1, V Govindasamy, Kenneth W Tobin

  • 1Oak Ridge National Laboratory, Oak Ridge, TN 37831, USA. karnowskitp@ornl.gov

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
|January 24, 2009
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

Prominin-1 and Retinal Degenerative Disorders: Expanding the Biology from Photoreceptors to the Retinal Pigment Epithelium.

Biomolecules·2026
Same author

Prominin-1 Regulates Retinal Pigment Epithelium Homeostasis: Transcriptomic Insights into Degenerative Mechanisms.

International journal of molecular sciences·2025
Same author

Durotaxis is a driver and potential therapeutic target in lung fibrosis and metastatic pancreatic cancer.

Nature cell biology·2025
Same author

Exometabolome of Pantoea targets pathogen associated scytalone dehydratase and XopQ for suppression of foliar blast and bacterial blight in rice.

International journal of biological macromolecules·2025
Same author

A Novel Combination Therapy Approach Targeting STAT3 and Autophagy in Glioblastoma.

Autophagy reports·2025
Same author

Prominin-1 Knockdown Causes RPE Degeneration in a Mouse Model.

Cells·2024

This study presents an improved lesion segmentation method using morphological reconstruction, achieving 90% accuracy in distinguishing true lesions from noise in medical images.

Area of Science:

  • Medical Imaging
  • Image Segmentation
  • Computational Pathology

Background:

  • Lesion segmentation is crucial for disease diagnosis and monitoring.
  • Existing methods may struggle with dark lesions or over-segmentation.
  • Accurate segmentation requires robust algorithms adaptable to various lesion types.

Purpose of the Study:

  • To adapt morphological reconstruction for segmenting dark lesions.
  • To improve lesion segmentation accuracy using ground-truth data.
  • To develop post-processing filters for enhanced lesion identification.

Main Methods:

  • Adapted morphological reconstruction techniques for lesion segmentation.
  • Incorporated vasculature segmentation for improved accuracy.
  • Utilized ground-truth data to determine optimal segmentation scales.

Related Experiment Videos

  • Developed post-processing filters to mitigate over-segmentation and false positives.

    • Main Results:

    • Achieved 90% sensitivity and specificity in classifying segmented blobs.
    • Successfully segmented dark lesions within medical imagery.
    • Validated the method on datasets comprising 86 and 1296 images.

    Conclusions:

    • The adapted morphological reconstruction method effectively segments dark lesions.
    • Post-processing filters significantly improve the accuracy of lesion identification.
    • The approach demonstrates high performance in distinguishing true lesions from artifacts.