Model and Expansion Based Methods of Detection of Small Masses in Radiographs of Dense Breasts

Abstract

Our goal is to identify representations to assist in the detection masses in dense mammograms having a diameter less than 1 Cm. The central idea of this project is to detect subtle masses by tuning the central frequency and width of a basis function used in an overcomplete expansion. By modeling the shape of a mass through this flexibility we hope to detect small and subtle masses in dense breasts and improve the chances of early detection in screening mammography. During this final year of the project we implemented a level-set method of segmentation that made use of a local homogeneity operator for the detection of subtle masses in digital mammography. These methods are currently integrated into our previously described multi-scale expansion framework and will be tested using an existing public database of mammograms with ground truth of known disease.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 2003
Accession Number
ADA425569

Entities

People

  • Andrew F. Laine

Organizations

  • Columbia University

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Algorithms
  • Biomedical Research
  • Computer Programming
  • Computers
  • Data Mining
  • Databases
  • Detection
  • Frequency
  • Graphical User Interface
  • Image Processing
  • Image Reconstruction
  • Information Processing
  • Information Science
  • Operating Systems
  • Statistical Algorithms
  • Two Dimensional
  • User Interface

Fields of Study

  • Medicine
  • Physics

Readers

  • Calculus or Mathematical Analysis
  • Computational Fluid Dynamics (CFD)
  • Oncology and Biomarker-Based Cancer Detection.