Computer-Aided Detection of Mammographic Masses in Dense Breast Images

Abstract

This document describes the research tasks and educational activities in which the PI has been engaged during the second phase of this post-doctoral work. The PI has selected 300 dense breast masses for testing using an automated segmentation algorithm which combines region growing with cost function analysis. This method has been validated on all cases using overlap, accuracy, sensitivity, specificity, Dice Similarity Index, and kappa statistics by three expert radiologists. The method has also been compared to a second algorithm developed by a group at The Johns Hopkins University. The PI has engaged in a number of technical development activities, including attending meetings in her research area, engaging in oral presentations describing her path through graduate school and through her post-doctoral award, reviewing grants and journal submissions, learning proper interviewing techniques, and teaching CAD methods to wide audiences.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 2006
Accession Number
ADA459716

Entities

People

  • Lisa M. Kinnard

Organizations

  • Howard University

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Breast Cancer
  • Computational Science
  • Computer Science
  • Data Science
  • Databases
  • Electrical Engineering
  • Health Services
  • Image Processing
  • Image Segmentation
  • Information Processing
  • Information Science
  • Medical Personnel
  • Physicians
  • Statistical Analysis
  • Statistics
  • Two Dimensional

Readers

  • Instructional Design and Training Evaluation.
  • Oncology and Biomarker-Based Cancer Detection.
  • Research Science/Academic Research