A Novel Fuzzy Topological Approach to the Detection of Mammographic Lesions and Qualifications of Parenchymal Density
Abstract
This research focuses on mammographic image processing for the purpose of density quantification, lesion detection and classification. The approaches proposed are different from those taken in the literature in two respects: (1) They emphasize on identifying the dense regions and analyzing their parenchymal architecture. (2) They use a novel fuzzy connectedness method of object definition and image segmentation. During this report period, the following have been accomplished. The development of a novel method of defining the "hanging togetherness" of dense regions via scale-based affinity and connectedness. An interactive method of lesion segmentation using live wire. An automatic, validated method of mammographic density quantification and the development of a host of intensity-based parameters that are more accurate than the measure of the area of dense regions. A novel method of detecting architectural distortions without explicitly delineating lesions (the method being tested for its effectiveness in predicting the on- set of lesions).
Document Details
- Document Type
- Technical Report
- Publication Date
- Aug 01, 1999
- Accession Number
- ADA382475
Entities
People
- Jayaram K. Udupa
Organizations
- University of Pennsylvania