Digital Mammography: Development of an Advanced Computer-Aided Diagnosis System for Breast Cancer Detection
Abstract
The goal of the project is to develop computer-aided diagnosis (CAD) methods and systems for mammography using advanced computer vision techniques and image information fusion from multiple mammograms to improve lesion detection and characterization. When fully developed the CAD system can assist radiologists in mammographic interpretation. During this project year we have performed the following tasks: (1) collected databases of digital mammograms (DMs) and digitized film mammograms (DFMs) for development of the CAD systems (2) compared the performance of the microcalcification detection system on DMs and DFMs (3) developed two-view information fusion techniques for the mass detection system (4) developed bilateral analysis technique for the mass detection system and (5) evaluated the effects of reconstruction image quality on mass detection for digital tomosynthesis mammography (DTM) which is a promising new imaging modality for improving breast cancer detection. In summary we have investigated a number of areas in CAD of mammographic lesions and evaluated new techniques for both DMs and DFMs. We have found that our new computer-vision techniques and multiple-image analysis approach can improve the performance of the CAD systems. We have also explored CAD methods for DTM and evaluated their dependence on reconstruction techniques. We will continue the development of the CAD systems for mammography in the coming years.
Document Details
- Document Type
- Technical Report
- Publication Date
- May 01, 2006
- Accession Number
- ADA459130
Entities
People
- Heang-Ping Chan
Organizations
- University of Michigan