Development of a Computer-Aided Diagnosis System for Early Detection of Masses Using Retrospectively Detected Cancers on Prior Mammograms
Abstract
The goal of this project is to develop a computer-aided diagnosis (CAD) system for mass detection using advanced computer vision techniques that will be trained with retrospectively detected cancers on prior mammograms. The new CAD system will be combined with our existing CAD system. When fully developed, the new dual CAD system should increase the sensitivity of detecting cancers at the early stage without compromising the sensitivity for other cancers. During this project year, we have performed the following tasks: (1) continue to collect the data sets of digitized film mammograms with multiple examinations, (2) investigate the performance of a regularized discriminant analysis (RDA) classifier in combination with a feature selection method for classification of masses and normal tissues on mammograms, (3) develop a two-view information fusion method to improve the performance of our CAD system, and (4) continue to develop a fusion scheme for combining two CAD systems to improve detection of early stage breast cancer. In summary, we have investigated a number of areas in CAD of mammographic masses and evaluated the new techniques for mass detection on mammograms. We have made progress in three of the tasks proposed in the project. We have found that our new computer-vision techniques can improve the performance of the CAD systems. We will continue the development of the CAD system in the coming years.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 01, 2006
- Accession Number
- ADA458398
Entities
People
- Jun Wei
Organizations
- University of Michigan