Xiaoyong Wang1, Jeon-Hor Chen2, Yen-Hsiu Liao3, Peter T. Fwu1, Muqing Lin1, Min-Ying Su1
1Center for Functional Onco-Imaging, Department of Radiological Sciences, University of California, Irvine, CA, United States; 2Center for Functional Onco-Imaging, Department of Radiological Sciences, University of California Irvine, Irvine, CA, United States; 3Department of Radiology, China Medical University Hospital, Taichung, Taiwan
We reported a breast density segmentation method for low dose chest CT, which is widely used for lung cancer screening. The method was based on algorithms used for MRI segmentation (FCM clustering and region growing & fitting). Fifteen healthy subjects who received both CT for lung cancer screening and MRI for breast cancer screening were analyzed. The breast volume, fibroglandular tissue volume, and percent density measured on CT and MRI were highly correlated, with r > 0.98. The results show that it is feasible to segment breast density based on chest CT to yield consistent measurements compared to MRI.