Accession Number:

ADA455785

Title:

Computer Analysis and Detection of Missed Cancer in Screening Mammogram

Descriptive Note:

Annual summary rept. 24 Mar 2005-23 Mar 2006

Corporate Author:

H LEE MOFFITT CANCER CENTER AND RESEARCH INST TAMPA FL

Personal Author(s):

• Li, Lihua

Report Date:

2006-04-01

Pagination or Media Count:

10.0

Abstract:

This project is to explore an innovative CAD strategy for improving early detection of breast cancer in screening mammograms by focusing on computerized analysis and detection of cancers missed by radiologists. The research in the second year is on i continuation of missed cancer analysis with a focus on density analysis and its effect on CAD detection ii new CAD system design. The achievements include 1 A comprehensive analysis was taken on the effect of breast density on cancer detection. The accomplishments include breast dense tissue segmentation, correlation analysis of mammogram density features between missed and detected stages, statistical testing of density difference between normal and cancerous mammograms, baseline study of the effect of density on CAD detection performance using existing algorithm. 2 A new CAD system was designed based on the existing second-generation CAD algorithm and the missed cancer analysis. Due to the effective modification strategies taken in the new system, detection performance was improved for mammograms at both detected and missed stages. However, with the focus on missed cancer analysis and detection, a bigger improvement was obtained in detecting missed cases even though the general detection performance is still lower than that at detected stage.

Descriptors:

• *COMPUTER AIDED DIAGNOSIS
• *BREAST CANCER
• *MAMMOGRAPHY
• DETECTION
• MAMMARY GLANDS
• CANCER SCREENING

Subject Categories:

• Medicine and Medical Research
• Medical Facilities, Equipment and Supplies
• Computer Programming and Software

Distribution Statement:

APPROVED FOR PUBLIC RELEASE