Xiaolei Qu1, Chao-Jen Lai2, Yuncheng Zhong2, Ying Yi2, Chris C Shaw3. 1. Graduate School of Engineering, The University of Tokyo, Tokyo, Japan. 2. Department of Imaging Physics, The University of Texas M. D. Anderson Cancer Center, Houston, TX, USA. 3. Department of Imaging Physics, The University of Texas M. D. Anderson Cancer Center, Houston, TX, USA. csdirl@gmail.com.
Abstract
PURPOSE: Cone-beam breast computed tomography (CBBCT), a promising breast cancer diagnostic technique, has been under investigation for the past decade. However, owing to scattered radiation and beam hardening, CT numbers are not uniform on CBBCT images. This is known as cupping artifact, and it presents an obstacle for threshold-based volume segmentation. In this study, we proposed a general post-reconstruction method for cupping artifact correction. METHODS: There were four steps in the proposed method. First, three types of local region histogram peaks were calculated: adipose peaks with low CT numbers, glandular peaks with high CT numbers, and unidentified peaks. Second, a linear discriminant analysis classifier, which was trained by identified adipose and glandular peaks, was employed to identify the unidentified peaks as adipose or glandular peaks. Third, adipose background signal profile was fitted according to the adipose peaks using the least squares method. Finally, the adipose background signal profile was subtracted from original image to obtain cupping corrected image RESULTS: In experimental study, standard deviation of adipose tissue CT numbers was obviously reduced and the CT numbers were more uniform after cupping correction by proposed method; in simulation study, root-mean-square errors were significantly reduced for both symmetric and asymmetric cupping artifacts, indicating that the proposed method was effective to both artifacts. CONCLUSIONS: A general method without a circularly symmetric assumption was proposed to correct cupping artifacts in CBBCT images for breast. It may be properly applied to images of real patient breasts with natural pendent geometry.
PURPOSE: Cone-beam breast computed tomography (CBBCT), a promising breast cancer diagnostic technique, has been under investigation for the past decade. However, owing to scattered radiation and beam hardening, CT numbers are not uniform on CBBCT images. This is known as cupping artifact, and it presents an obstacle for threshold-based volume segmentation. In this study, we proposed a general post-reconstruction method for cupping artifact correction. METHODS: There were four steps in the proposed method. First, three types of local region histogram peaks were calculated: adipose peaks with low CT numbers, glandular peaks with high CT numbers, and unidentified peaks. Second, a linear discriminant analysis classifier, which was trained by identified adipose and glandular peaks, was employed to identify the unidentified peaks as adipose or glandular peaks. Third, adipose background signal profile was fitted according to the adipose peaks using the least squares method. Finally, the adipose background signal profile was subtracted from original image to obtain cupping corrected image RESULTS: In experimental study, standard deviation of adipose tissue CT numbers was obviously reduced and the CT numbers were more uniform after cupping correction by proposed method; in simulation study, root-mean-square errors were significantly reduced for both symmetric and asymmetric cupping artifacts, indicating that the proposed method was effective to both artifacts. CONCLUSIONS: A general method without a circularly symmetric assumption was proposed to correct cupping artifacts in CBBCT images for breast. It may be properly applied to images of real patient breasts with natural pendent geometry.
Entities:
Keywords:
Background fitting; CT number uniformity; Cone-beam breast CT; Cupping artifact correction