Cross-Visit Tumor Sub-segmentation and Registration with Outlier Rejection for Dynamic Contrast-Enhanced MRI Time Series Data
Clinical trials of anti-angiogenic and vascular-disrupting agents often use biomarkers derived from DCE-MRI, typically reporting whole-tumor summary statistics and so overlooking spatial parameter variations caused by tissue heterogeneity. We present a data-driven segmentation method comprising tracer-kinetic model-driven registration for motion correction, conversion from MR signal intensity to contrast agent concentration for cross-visit normalization, iterative principal components analysis for imputation of missing data and dimensionality reduction, and statistical outlier detection using the minimum covariance determinant to obtain a robust Mahalanobis distance. After applying these techniques we cluster in the principal components space using k-means. We present results from a clinical trial of a VEGF inhibitor, using time-series data selected because of problems due to motion and outlier time series. We obtained spatially-contiguous clusters that map to regions with distinct microvascular characteristics. This methodology has the potential to uncover localized effects in trials using DCE-MRI-based biomarkers
DCE-MRI PCA k-means tracer kinetic modeling image registration imputation outlier detection minimum covariance determinant
G.A.Buonaccorsi C.J.Rose J.P.B.O’Connor C.Roberts Y.Watson A.Jackson G.C.Jayson G.J.M.Parker
Imaging Science and Biomedical Engineering, School of Cancer and Imaging Sciences,University of Manc CRUK Dept of Medical Oncology, Christie Hospital, Manchester, United Kingdom The University of Manch Imaging Science and Biomedical Engineering, School of Cancer and Imaging Sciences, University of Man
国际会议
北京
英文
121–128
2010-09-01（万方平台首次上网日期，不代表论文的发表时间）