Breast cancer risk prediction via area and volumetric estimates of breast density

Authors:
Brad M. Keller;Emily F. Conant;Huen Oh;Despina Kontos
Affiliations:
Department of Radiology, University of Pennsylvania, Philadelphia, PA;Department of Radiology, University of Pennsylvania, Philadelphia, PA;Department of Radiology, University of Pennsylvania, Philadelphia, PA;Department of Radiology, University of Pennsylvania, Philadelphia, PA
Venue:
IWDM'12 Proceedings of the 11th international conference on Breast Imaging
Year:
2012

Citing 3
Cited 2

Image Processing, Analysis, and Machine Vision

Image Processing, Analysis, and Machine Vision
Adaptive multi-cluster fuzzy C-means segmentation of breast parenchymal tissue in digital mammography

MICCAI'11 Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention - Volume Part III
A comparative study of volumetric and area-based breast density estimation in digital mammography: results from a screening population

IWDM'10 Proceedings of the 10th international conference on Digital Mammography

Constructing and applying higher order textons: Estimating breast cancer risk

Pattern Recognition
Texture and region dependent breast cancer risk assessment from screening mammograms

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

We performed a study to assess the potential value of absolute and relative measures of area and volumetric breast density in predicting breast cancer risk. A case-control study was performed. The raw mediolateral-oblique (MLO) view digital mammography (DM) images of 106 women with unilateral breast cancer and 318 age-matched controls were retrospectively analyzed. The unaffected breast of the cancer cases was used as a surrogate of higher cancer risk. For each image, area and volumetric breast density measures were estimated using fully-automated software. The performance of the density metrics to distinguish between cancer cases and controls was assessed using linear discriminant and ROC curve analysis. Absolute measures of dense tissue content had stronger discriminatory capacity (AUCs=0.65-0.67) than percent density (AUCs=0.57). Shape-location features also showed modest discriminatory power (AUC=0.56-0.65). A combined area-volumetric model was able to outperform (AUC=0.70) any single-feature model. Absolute measures of fibroglandular tissue content were seen to be more discriminative than percent density estimates, indicating that total fibroglandular tissue content may be more reflective of cancer risk than relative measures of density. Our results suggest that area and volumetric breast density measures could be complementary in breast cancer risk assessment.