Enhanced roughness index for breast cancer benign/malignant measurement using Gaussian mixture model

Authors:
Zhe Li;Wei Wang;Sung Shin;Hyung D. Choi
Affiliations:
South Dakota State University, Brookings, SD;South Dakota State University, Brookings, SD;South Dakota State University, Brookings, SD;Telecommunications Research Institute (ETRI), DaeJeon, South Korea
Venue:
Proceedings of the 2013 Research in Adaptive and Convergent Systems
Year:
2013

Citing 2
Cited 0

A clustering technique for digital communications channel equalization using radial basis function networks

IEEE Transactions on Neural Networks
A new histogram-based breast cancer image classifier using Gaussian mixture model

Proceedings of the 2012 ACM Research in Applied Computation Symposium

Quantified Score

Hi-index	0.00

Visualization

Abstract

Morphologic appearance plays a substantial role in presenting mass lesion in breast imaging. In this paper, we propose an innovative shape irregularity measurement based on roughness index - Enhance Roughness Index (ERI). This new irregularity measurement is taken as an input to Gaussian Mixture Model (GMM) classifier. By analyzing the similarity through comparing GMM parameters for the input breast tumor image and training benign/malignant cases, a breast tumor image can be efficiently classified into benign or malignant case. This tumor ERI shape irregularity measurement is an effective and critical factor as a benign/malignant classifier for diagnosing breast cancer. The extensive experiments show this shape irregularity measurement can obtain decent performance in the breast tumor image classification.