Computer-Aided Mammography Using Automated Feature Extraction for the Detection and Diagnosis of Breast Cancer,
Abstract
The purpose of this project was to improve the diagnosis and treatment of breast cancer by reducing the cost and morbidity of unnecessary biopsies. Although mammography is very sensitive, there are a large number of false-positive biopsies. Of women with radio graphically- suspicious, nonpalpable lesions who are sent to biopsy, only 15 to 34% actually have a malignancy by histologic diagnosis 1,2. The cost of these unnecessary biopsies is a major obstacle to widespread acceptance of mammographic screening 3. It has been shown that surgeon's fees and biopsy costs account for over half the cost of detecting small breast cancers in a screening population 4. Preventing unnecessary biopsies is therefore one of the most important ways to improve the efficacy of mammographic screening. Many previous reports have discussed the need to reduce the number of benign biopsies 5, 6.
Document Details
- Document Type
- Technical Report
- Publication Date
- Oct 01, 1997
- Accession Number
- ADA341604
Entities
People
- Joseph Y. Lo
Organizations
- Duke University Hospital