Automated Method for Analysis of Mammographic Breast Density - A Technique for Breast Cancer Risk Estimation

Abstract

The goal of this proposed project is to develop an automated technique to assist radiologists in estimating mammographic breast density. During the project years, we developed an automated mammographic density segmentation system, referred to as Mammographic Density ESTimator (MDEST), for both DMs and DFMs. Our studies showed that the automated MDEST system can provide percent dense area estimates that are highly correlated with radiologists interactive thresholding results and the percent volumetric fibroglandular tissue estimates from MR breast images. The quantitative estimates are superior to the radiologists qualitative BI-RADS density assessment. The MDEST system can provide a consistent and reproducible estimation of percent dense area on routine clinical mammograms. This will facilitate studies of various factors associated with breast cancer risk and mammographic sensitivity, and monitoring the effects of interventional or preventive strategies. The image analysis tool will therefore contribute to the understanding of the relationship of density to breast cancer risk, detection, prognosis, and to the prevention and treatment of breast cancers.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 2006
Accession Number
ADA463240

Entities

People

  • Heang-Ping Chan

Organizations

  • University of Michigan

Tags

Communities of Interest

  • Engineered Resilient Systems

DTIC Thesaurus Topics

  • Algorithms
  • Breast Cancer
  • Computer Programs
  • Computer Vision
  • Computers
  • Databases
  • Detection
  • Electronic Mail
  • Estimators
  • Graphical User Interface
  • Image Processing
  • Information Science
  • Institutional Review Board
  • Medical Personnel
  • Three Dimensional
  • Two Dimensional
  • X Rays

Fields of Study

  • Medicine
  • Physics

Readers

  • Oncology and Biomarker-Based Cancer Detection.