Meeting Banner
Abstract #4941

Development of Robust Texture Parameters for Characterizing Normal Breast Parenchymal Patterns

Yang Zhang1, Jeon-Hor Chen1,2, Siwa Chan3, Dah-Cherng Yeh4, and Min-Ying Su1

1Tu & Yuen Center for Functional Onco-Imaging, University of California, Irvine, Irvine, CA, United States, 2E-Da Hospital and I-Shou University, 3Tzu-Chi General Hospital, Taichung, Taiwan, 4Taichung Veterans General Hospital, Taichung, Taiwan

The non-fat-sat T1-weighted breast MRI of 57 normal healthy women were analyzed. In order to test the robustness of parameters we compared the texture analyzed from the ROI’s of different sizes as the largest cuboid that can fit within the breast and cover 30%, 40%, and 50% of fibroglandular tissue slices. 21 texture features were selected as robust features that were not greatly affected by the cuboid ROI size. The concordance correlation coefficient of the percent density between bilateral breasts was very high, 0.98. Of all texture parameters, “Information Measure for Correlation (IMC)” and “Contrast” show the highest ccc, 0.90-0.98.

This abstract and the presentation materials are available to members only; a login is required.

Join Here