Conference proceeding
Near-automatic quantification of breast tissue glandularity via digitized mammograms
Proceedings of SPIE, Vol.3661(1), pp.266-276
Medical Imaging 1999: Image Processing
05/21/1999
DOI: 10.1117/12.348581
Abstract
Studies reported in the literature indicate that breast cancer risk is associated with mammographic densities. Although, an objective, repeatable quantitative measure of risk derived from mammographic densities will be of great use in recommending alternative screening paradigms and/or preventive measures, image processing efforts toward this goal seem to very sparse in the literature, and automatic and efficient methods do not seem to exist. In this paper, we describe and validate an automatic and reproducible method to segment glandular tissue regions from fat within breasts from digitized mammograms using scale-based fuzzy connectivity methods. Different measures for characterizing density are computed from the segmented regions and their accuracies in terms of their linear correlation across two different projections (CC and MLO) are studied. It is shown that quantization of glandularity taking into account the original intensities is more accurate than just considering the segmented areas. This makes the quantification less dependent on the shape of the glandular regions and the angle of projection. A simple phantom experiment is done that supports this observation.
Details
- Title: Subtitle
- Near-automatic quantification of breast tissue glandularity via digitized mammograms
- Creators
- Punam K Saha - Univ. of Pennsylvania (USA)Jayaram K Udupa - Univ. of Pennsylvania (USA)Emily F Conant - Univ. of Pennsylvania (USA)Dev P Chakraborty - Univ. of Pennsylvania (USA)
- Resource Type
- Conference proceeding
- Publication Details
- Proceedings of SPIE, Vol.3661(1), pp.266-276
- Conference
- Medical Imaging 1999: Image Processing
- DOI
- 10.1117/12.348581
- ISSN
- 0277-786X
- Language
- English
- Date published
- 05/21/1999
- Academic Unit
- Electrical and Computer Engineering; Radiology
- Record Identifier
- 9984051504302771
Metrics
12 Record Views