This poster is published under an
open license. Please read the
disclaimer for further details.
Keywords:
Oncology, Neuroradiology brain, Contrast agents, CT, Computer Applications-Detection, diagnosis, Contrast agent-intravenous, Radiation therapy / Oncology, Cancer
Authors:
T. S. Koh, C. H. Thng, P. T. H. Teo, D. Cheong, K. Lim, J. B. K. Khoo, T. Lim; Singapore/SG
DOI:
10.1594/ecr2015/C-0038
Methods and materials
Automatic classification of voxel-level enhancement patterns was performed using a combined principal component analysis (PCA) and Kmeans clustering method.
PCA was used as a dimension reduction step to determine the appropriate number of distinct enhancement types (clusters) within the DCE CT dataset.
Kmeans clustering is subsequently employed to classify the enhancement curve in each voxel into one of the clusters (3).
To demonstrate clinical feasibility,
the automatic classification method was used to analyse a patient study case with serial brain DCE CT scans performed before,
0,
6 and 16 weeks after whole brain radiotherapy,
to monitor tumour response to radiotherapy.
DCE CT was performed using a slip ring,
helical CT scanner (HiSpeed; GE Medical Systems) with the dynamic CT images obtained on a single section at the level of the largest tumor diameter identified on non-contrast CT scans.
A reduced-scan protocol (4) was implemented whereby 30 contrast-enhanced images were acquired at increasing time intervals of 1,
2,
4 and 8 s for acquisitions 1-10,
11-20,
21-25 and 26-30,
respectively; with the intravenous injection of 50 ml of non-ionic iodinated contrast medium (Omnipaque 300 mgI/ml) at a rate of 4 mL/s using an automatic injector.
Parameters for the CT scans were 80 kVp,
190 mAs,
512×512 matrix,
20-22 cm field of view and at 5 mm collimations.