Share Email Print
cover

Proceedings Paper

Computerized image analysis: estimation of breast density on mammograms
Author(s): Chuan Zhou; Heang-Ping Chan; Nicholas Petrick; Berkman Sahiner; Mark A. Helvie; Marilyn A. Roubidoux; Lubomir M. Hadjiiski; Mitchell M. Goodsitt
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

An automated image analysis tool is being developed for estimation of mammographic breast density, which may be useful for risk estimation or for monitoring breast density change in a prevention or intervention program. A mammogram is digitized using a laser scanner and the resolution is reduced to a pixel size of 0.8 mm X 0.8 mm. Breast density analysis is performed in three stages. First, the breast region is segmented from the surrounding background by an automated breast boundary-tracking algorithm. Second, an adaptive dynamic range compression technique is applied to the breast image to reduce the range of the gray level distribution in the low frequency background and to enhance the differences in the characteristic features of the gray level histogram for breasts of different densities. Third, rule-based classification is used to classify the breast images into several classes according to the characteristic features of their gray level histogram. For each image, a gray level threshold is automatically determined to segment the dense tissue from the breast region. The area of segmented dense tissue as a percentage of the breast area is then estimated. In this preliminary study, we analyzed the interobserver variation of breast density estimation by two experienced radiologists using BI-RADS lexicon. The radiologists' visually estimated percent breast densities were compared with the computer's calculation. The results demonstrate the feasibility of estimating mammographic breast density using computer vision techniques and its potential to improve the accuracy and reproducibility in comparison with the subjective visual assessment by radiologists.

Paper Details

Date Published: 6 June 2000
PDF: 10 pages
Proc. SPIE 3979, Medical Imaging 2000: Image Processing, (6 June 2000); doi: 10.1117/12.387676
Show Author Affiliations
Chuan Zhou, Univ. of Michigan (United States)
Heang-Ping Chan, Univ. of Michigan (United States)
Nicholas Petrick, Univ. of Michigan (United States)
Berkman Sahiner, Univ. of Michigan (United States)
Mark A. Helvie, Univ. of Michigan (United States)
Marilyn A. Roubidoux, Univ. of Michigan (United States)
Lubomir M. Hadjiiski, Univ. of Michigan (United States)
Mitchell M. Goodsitt, Univ. of Michigan (United States)


Published in SPIE Proceedings Vol. 3979:
Medical Imaging 2000: Image Processing
Kenneth M. Hanson, Editor(s)

© SPIE. Terms of Use
Back to Top