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

Shape filtering for false positive reduction at computed tomography colonography.

Abhilash A Miranda1, Tarik A Chowdhury, Ovidiu Ghita

  • 1Vision Systems Group, Dublin City University, Ireland. abhilash@eeng.dcu.ie

Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|March 16, 2007
PubMed
Summary

This study introduces a shape-filtering method to reduce false positives in computer-aided detection (CAD) of colorectal polyps during CT colonography. The efficient technique achieves 100% sensitivity for polyps over 10 mm with a low false positive rate.

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

Loss of normal facial asymmetry in schizophrenia and bipolar disorder: Implications for development of brain asymmetry in psychotic illness.

Psychiatry research·2024
Same author

Refining the resolution of craniofacial dysmorphology in bipolar disorder as an index of brain dysmorphogenesis.

Psychiatry research·2020
Same author

The definitions of three-dimensional landmarks on the human face: an interdisciplinary view.

Journal of anatomy·2015
Same author

Evaluation of Yogurt Microstructure Using Confocal Laser Scanning Microscopy and Image Analysis.

Journal of food science·2015
Same author

3-D Facial Landmark Localization With Asymmetry Patterns and Shape Regression from Incomplete Local Features.

IEEE transactions on cybernetics·2014
Same author

Automatic segmentation of mitochondria in EM data using pairwise affinity factorization and graph-based contour searching.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2014

Area of Science:

  • Medical Imaging
  • Computer-Aided Detection
  • Gastroenterology

Background:

  • Colorectal cancer screening relies on accurate polyp detection.
  • Computer-Aided Detection in Computed Tomography Colonography (CAD-CTC) aims to improve accuracy.
  • Reducing false positives (FP) is crucial for clinical utility.

Purpose of the Study:

  • To develop a shape-filtering technique for reducing false positives in CAD-CTC.
  • To enhance the reliability of automatic polyp detection.
  • To improve the efficiency and robustness of polyp identification.

Main Methods:

  • Treating polyp detection as a shape-filtering task.
  • Extracting candidate surfaces and analyzing shape distribution functions in the Fourier domain.

Related Experiment Videos

  • Classifying candidate surfaces using spectral data for polyp vs. non-polyp identification.

    • Main Results:

    • The developed shape filtering scheme is computationally efficient, taking approximately 2 seconds per dataset.
    • Achieved 100% sensitivity for polyps greater than 10 mm.
    • Demonstrated a robust overall false positive rate of 5.44 per dataset on standard and low-dose CT data.

    Conclusions:

    • Shape filtering in the Fourier domain is an effective method for reducing false positives in CAD-CTC.
    • The proposed method offers a computationally efficient and robust solution for polyp detection.
    • This technique can improve the clinical applicability of CT colonography for colorectal cancer screening.