Database-Aided Diagnosis in Digital Mammography
Abstract
The purpose of this project is to refine a 'visual neural network', coupled to a mamnographic database, and evaluate the ability of the resulting system to help radiologists reduce the number of benign biopsies in mammographic screening without increasing the number of missed cancers. We refer to this as a 'mapped database diagnostic system'. The unique features of this system are (a) its exploitation of a clinically proved database of mammograms for enhanced diagnosis, (b) automatic selection of highly discriminating mammographic features, and (c) a two-dimensional 'relational map' for enhanced browsing through the mammographic database. Years 1 and 2 of this project will be devoted primarily to retrospective studies, Years 3 and 4 primarily to clinical studies. In Year 2, reported here, we acquired a database of biopsy-proven mammographic cases from UCLA and the King Drew Medical Center. In addition we developed new algorithms and software for classifying masses, we constructed and tested a new content-based image search engine for database-aided diagnosis and teleradiology, we constructed a radiologist-friendly interface for interacting with our database-aided diagnostic system, and we initiated the construction and testing of a telemammography system linking the Humphrey Comprehensive Health Center to our database-aided diagnostic system at the King/Drew Medical Center.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jul 01, 2001
- Accession Number
- ADA400561
Entities
People
- Jack Sklansky
Organizations
- Charles R. Drew University of Medicine and Science