Automated Analysis and Display of Temporal Sequences of Mammograms

Abstract

Although screening for breast %cancer has been effective in detecting cancers, it is not clear that the diagnostic information present in sequences of screening exams is currently being utilized. This project has integrated several novel technologies into a system for providing mammographers with information about changing tissue patterns derived from temporal sequences of images. Our hypotheses are: 1) Sequences of screening mammograms contain information about tissue changes that is not otherwise being exploited in the diagnosis of breast cancer; and, 2) Changing tissue patterns can automatically be identified, and correlated with diagnostic questions. To date, the tasks described in the statement of work have been completed, but unexpected issues arising from that work are being addressed in a 1-year extension of the project. This involves defining additional time- dependent features, and having the system subjectively evaluated by radiologists.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 2005
Accession Number
ADA443778

Entities

People

  • Walter F. Good

Organizations

  • University of Pittsburgh

Tags

Communities of Interest

  • Engineered Resilient Systems
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Accuracy
  • Algorithms
  • Biomedical Research
  • Breast Cancer
  • Cancer
  • Coordinate Systems
  • Data Analysis
  • Detection
  • Health Care
  • Medical Personnel
  • Neoplasms
  • Neural Networks
  • Physicians
  • Sequences
  • Software Development
  • Standards
  • Test And Evaluation

Fields of Study

  • Medicine
  • Physics

Readers

  • Oncology and Biomarker-Based Cancer Detection.
  • Systems Analysis and Design