Robust Detection of Masses in Digitized Mammograms
Abstract
This project is to develop a robust computer aided diagnosis (CAD) system for mass detection with high sensitivity and specificity in digitized mammograms. The research in the year of non-cost extension is on data collection, evaluation of clinical significance of CAD system, and the final documentation and manuscript reports. By reviewing more than 1553 cases, a total of 100 consecutive cancer cases were collected. A ground truth file was generated by an experienced radiologist. To evaluate the clinical significance of the CAD system in early cancer detection, a testing of the CAD system on independent consecutive cancer cases was performed, in which the detection FROC curves and months of early detection at different false-positive rates were obtained.
Document Details
- Document Type
- Technical Report
- Publication Date
- May 01, 2005
- Accession Number
- ADA437880
Entities
People
- Lihua Li
Organizations
- University of South Florida