Accession Number : ADA325798

Title :   Computer Aided Breast Cancer Diagnosis.

Descriptive Note : Annual rept. 23 Sep 95-22 Sep 96,

Corporate Author : DUKE UNIV MEDICAL CENTER DURHAM NC

Personal Author(s) : Floyd, Carey E.

PDF Url : ADA325798

Report Date : OCT 1996

Pagination or Media Count : 35

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. Our total case database is over 500. We have investigated two alternative network architectures for predicting malignancy: a genetic algorithm approach, and an adaptive learning rule for the feed-forward network.

Descriptors :   *COMPUTER AIDED DIAGNOSIS, *BREAST CANCER, DATA BASES, ALGORITHMS, NETWORKS, ACCURACY, LONG RANGE(TIME), LONG RANGE(DISTANCE), HISTORY, GENETICS, MAMMOGRAPHY.

Subject Categories : Computer Systems
      Cybernetics
      Medicine and Medical Research

Distribution Statement : APPROVED FOR PUBLIC RELEASE