Optimization of Breast Tomosynthesis Imaging Systems for Computer-Aided Detection

Abstract

The goal of this research is to develop methodology for optimizing acquisition parameters for digital tomosynthesis of the breast (DBT). Optimization is important to be able to study whether DBT can be used in place of screening mammography with better sensitivity and specificity. The research is composed of three parts: 1) to develop a computer model to simulate tomosynthesis, 2) to generate realistic breast and tumor models, and 3) to determine optimal acquisition parameters by using a genetic algorithm with CADe performance as an indicator of fitness. In this report, we summarize the research done for this project to date, focussing particularly on the development of an anthropomorphic software breast phantom and its validation. Lastly, we evaluate methods for measuring anatomic noise in projection imaging.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 01, 2011
Accession Number
ADA545786

Entities

People

  • Beverly Lau

Organizations

  • University of Chicago

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • Acquisition
  • Computer Simulations
  • Computers
  • Detection
  • Detectors
  • Diagnostic Imaging
  • Geometry
  • Health Services
  • Materials
  • Monte Carlo Method
  • Power Spectra
  • Quantum Noise
  • Sampling
  • Simulations
  • Statistical Analysis
  • Three Dimensional
  • Two Dimensional

Fields of Study

  • Medicine
  • Physics

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Life Cycle Cost Analysis
  • Medical Imaging.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms
  • Biotechnology
  • Biotechnology - Cancer Biotech