Accession Number:

ADA346548

Title:

Computer Aided Breast Cancer Diagnosis.

Descriptive Note:

Annual rept. 23 Sep 96-22 Sep 97

Corporate Author:

DUKE UNIV MEDICAL CENTER DURHAM NC

Personal Author(s):

Report Date:

1997-09-01

Pagination or Media Count:

12.0

Abstract:

The long range goal of this project is to improve the accuracy and consistency of breast cancer diagnosis by developing a Computer Aided Diagnosis CAD system for early prediction of breast cancer from the patients mammographic findings and medical history. In the third year of this project, we have acquired 200 new cases bring our total case database to over 700. We have further investigated an alternative network architecture for predicting malignancy 1 a genetic algorithm. A user interface was further developed for more efficient data entry and error checking was employed. The existing mammography data entry database was evaluated for use in the prediction system. These developments were targeted at the first specific aim of the grant 2 develop an artificial neural network to predict biopsy outcome from mammographic and history findings. In the fourth year, we will focus on the second specific aim and 3 evaluate the improvement in radiologists diagnostic performance when the computer diagnostic aid is provided. This implementation of an accurate CAD system will improve sensitivity, specificity, and consistency of breast cancer diagnosis and will provide a significant improvement in long term outcome for breast cancer patients.

Subject Categories:

  • Medicine and Medical Research
  • Medical Facilities, Equipment and Supplies
  • Computer Programming and Software

Distribution Statement:

APPROVED FOR PUBLIC RELEASE