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 two expert radiologists. Two experiments have been performed, where the segmentation algorithm was tested on non-processed and background trend corrected images. The PI has attended oncology seminars, attended one scientific meeting, made two oral presentations, made one poster presentation, and her publication completed during the last phase of the award was selected for publication in a virtual biophysics journal during this time.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 2005
Accession Number
ADA437718

Entities

People

  • Lisa M. Kinnard

Organizations

  • Howard University

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Accuracy
  • Algorithms
  • Biophysics
  • Computer Vision
  • Computers
  • Data Science
  • Databases
  • Detection
  • Diagnostic Imaging
  • Image Processing
  • Image Segmentation
  • Information Processing
  • Information Science
  • Physicians
  • Probability
  • Sensitivity
  • Statistics

Fields of Study

  • Physics

Readers

  • Academic Conference Management
  • Oncology and Biomarker-Based Cancer Detection.
  • Regression Analysis.

Technology Areas

  • Biotechnology