Assessment of an Optical Flow Field-Based Polyp Detector for CT Colonography

Abstract

Most current computer-aided detection (CAD) algorithms for the fully automatic detection of colonic polyps from 3D CT data suffer from high false positive rates. We developed and evaluated a post-processing algorithm to decrease the false positive rate of such a method. Our method attempts to model the way a radiologist recognizes a polyp while scrolling a cross-sectional plane through 3D CT data by quantifying the change in location of the edges in 2D plane. It uses a classifier for identification base on the Mahalanobis distance. The new method increase the ROC curve area from 0.89 to 0.98 (an increase from 34.5% to 85.0% in specificity for 100% sensitivity) in a population of 8 patients.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 25, 2001
Accession Number
ADA411867

Entities

People

  • B. Acar
  • C. F. Beaulieu
  • C. Tomasi
  • D. S. Paik
  • S. B. Goekturk

Organizations

  • Stanford University

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Classification
  • Computations
  • Data Science
  • Data Sets
  • Detection
  • Detectors
  • Flow
  • Flow Fields
  • Machine Learning
  • Military Research
  • Sensitivity
  • Test Sets
  • Training
  • Universities
  • X-Ray Computed Tomography

Fields of Study

  • Physics

Readers

  • Computer Vision.
  • Image Processing and Computer Vision.
  • Oncology and Biomarker-Based Cancer Detection.

Technology Areas

  • AI & ML