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

Combining Statistical and Geometric Features for Colonic Polyp Detection in CTC Based on Multiple Kernel Learning.

Shijun Wang1, Jianhua Yao, Nicholas Petrick

  • 1Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Building 10 Room 1C368X MSC 1182, Bethesda, MD 20892-1182.

International Journal of Computational Intelligence and Applications
|October 19, 2010
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Imaging Studies III: Gastrointestinal Motility Studies and Virtual Colonoscopy01:26

Imaging Studies III: Gastrointestinal Motility Studies and Virtual Colonoscopy

This lesson explores three gastrointestinal imaging techniques: radionuclide testing, colonic transit studies, and virtual colonoscopy.
Radionuclide Testing
Radionuclide testing is a sophisticated medical technique for assessing gastrointestinal motility. It focuses on gastric emptying and colonic transit time. Radioactive markers track the movement of food through the digestive system, providing insights into gastrointestinal disorders.
In gastric emptying studies, a meal's liquid and solid...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Methodological considerations for evaluating deep learning segmentation models in digital pathology whole-slide images.

Journal of medical imaging (Bellingham, Wash.)·2026
Same author

Physics-informed data augmentation to simulate low dose CT scans: Application to lung nodule detection.

Medical physics·2026
Same author

Detecting dataset bias in medical AI using a generalized and modality agnostic auditing approach.

NPJ digital medicine·2026
Same author

Digital decoding tissue microenvironment heterogeneity from spatial proteomics through graph-enhanced transfer learning.

Cell systems·2026
Same author

Oxygen-Vacancy-Engineered Y<sub>2</sub>O<sub>3</sub>/CeO<sub>2</sub> Nanobrush Superlattices via Laser Heteroepitaxy: Toward High-Performance Memristors.

Small methods·2026
Same author

Single-cell transcriptomics and machine learning identify RNF144B and C5AR1 as immune-related molecular signatures and therapeutic targets in myocardial infarction.

Genes & genomics·2026
See all related articles

New statistical shape features improve colon cancer detection using computed tomographic colonography (CTC). Combining these with traditional features and a novel kernel learning method enhances polyp identification accuracy in screening.

Area of Science:

  • Medical imaging analysis
  • Computer-aided diagnosis
  • Gastroenterology

Background:

  • Colon cancer is a leading cause of cancer deaths in the US.
  • Computed tomographic colonography (CTC) aids in colon cancer screening.
  • Accurate polyp detection is crucial for CTC effectiveness, requiring differentiation from false positives.

Purpose of the Study:

  • To introduce novel statistical curvature features (histograms of curvature features) for polyp candidate description.
  • To integrate these new features with traditional geometric features for improved polyp detection.
  • To employ multiple kernel learning with semi-definite programming for optimized classification.

Main Methods:

  • Extraction of traditional geometric features (Group A) and new statistical curvature features (Group B) from polyp candidates.

Related Experiment Videos

  • Application of multiple kernel learning based on semi-definite programming to combine heterogeneous feature sets.
  • Validation using a leave-one-patient-out test on a CTC dataset of 66 patients.

    • Main Results:

    • A support vector machine (SVM) utilizing combined features and the optimized kernel outperformed SVMs using individual feature sets.
    • Sensitivity improved from 0.77 (Group A) and 0.73 (Group B) to 0.83 at 5 false positives per scan.
    • The combined approach demonstrated statistically significant improvement (p ≤ 0.01).

    Conclusions:

    • Statistical curvature features complement traditional geometric features for polyp detection in CTC.
    • Multiple kernel learning effectively integrates diverse feature types for enhanced classification performance.
    • The proposed method shows significant potential for improving colon cancer screening accuracy via CTC.