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

Robust pulmonary nodule segmentation in CT: improving performance for juxtapleural cases.

K Okada1, V Ramesh, A Krishnan

  • 1Real-Time Vision and Modeling Dept., Siemens Corporate Research, Princeton, USA.

Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|May 12, 2006
PubMed
Summary

Two new methods improve pulmonary nodule segmentation in CT scans, especially for challenging wall-attached nodules. These techniques achieve a 95% correct segmentation rate, enhancing diagnostic accuracy.

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

Exosomal-complement system activation in preeclampsia.

The journal of obstetrics and gynaecology research·2025
Same author

Early Intervention in Post-operative Infectious Spondylodiscitis: Outcome of Aggressive Transforaminal Lumbar Interbody Fusion.

Malaysian orthopaedic journal·2024
Same author

Patient costs for drug-resistant TB diagnosis and pre-treatment evaluation in North India.

Public health action·2024
Same author

Comparative assessment of immunogenicity of recombinant insulin Aspart from BioGenomics and its originator NovoRapid® in adult patients with type 2 diabetes mellitus.

Journal of endocrinological investigation·2023
Same author

Cryogenic vacuum valve with actuation times down to 50 ms.

The Review of scientific instruments·2023
Same author

Observation of Single-Top-Quark Production in Association with a Photon Using the ATLAS Detector.

Physical review letters·2023

Area of Science:

  • Medical Imaging
  • Computer-Aided Diagnosis
  • Pulmonology

Background:

  • Accurate segmentation of pulmonary nodules in CT images is crucial for early lung cancer detection.
  • Juxtapleural or wall-attached nodules present significant segmentation challenges due to their proximity to the lung wall.
  • Existing methods often struggle with localizing and segmenting these specific nodule types effectively.

Purpose of the Study:

  • To develop and evaluate novel semi-automatic methods for robust pulmonary nodule segmentation in CT images.
  • To specifically address the segmentation difficulties of juxtapleural nodules using local information.
  • To improve the accuracy and reliability of pulmonary nodule detection and segmentation in clinical practice.

Main Methods:

  • Proposed two novel segmentation methods as extensions of the robust Gaussian fitting approach.

Related Experiment Videos

  • Method 1: 3D morphological opening with an anisotropic structuring element.
  • Method 2: Extended mean shift with a Gaussian repelling prior, utilizing only local image information.

    • Main Results:

    • Both proposed methods demonstrated improved performance compared to the baseline robust Gaussian fitting.
    • An 8% increase in segmentation accuracy was observed across the clinical high-resolution CT dataset.
    • Achieved a high correct segmentation rate of 95% for pulmonary nodules.

    Conclusions:

    • The novel segmentation methods offer a robust solution for pulmonary nodule detection, particularly for challenging juxtapleural cases.
    • These techniques enhance the accuracy of nodule segmentation without requiring global lung segmentation.
    • The improved segmentation accuracy contributes to more reliable computer-aided diagnosis for lung cancer screening.