Tumor Detection in Digital Mammograms
Lists
Only you see this
Abstract
A novel approach for detecting microcalcifications in digital mammograms is proposed. The noisy and impulsive nature of normal breast tissue in mammograms leads to high false-positive rates, thereby impairing detection performance. The authors address this issue by first observing that the distribution of pixel values is heavy-tailed. A statistical-physical noise model, based on the generalized central limit theorem and simple models for X-ray attenuation, distribution of breast tissue, and the digitization process, is presented to explain the presence of outliers. The authors use this model to derive an optimal statistical test to detect breast abnormalities in symmetric alpha-stable (S/spl alpha/S) noise. The resulting algorithm yields a constant false-alarm rate (CFAR) S/spl alpha/S microcalcification detector that is robust in impulsive noise environments. Experimental results on mammogram images from the Digital Database for Screening Mammography (DDSM) are provided to demonstrate the usefulness of the proposed approach.
BibTeX
@inproceedings{banerjee2000tumor,
author = {Amit Banerjee and Rama Chellappa},
title = {{Tumor Detection in Digital Mammograms}},
booktitle = {ICIP},
year = {2000},
doi = {10.1109/icip.2000.899426},
}Loading related content...