Program Information
Harmonization of Radiomic Features On Planning CT and On-Board CBCT
R Geng1*, K Lafata2 , Y Zhang3 , F Yin4 , (1) Duke University, Durham, NC, (2) Duke University, Durham, NC, (3) Duke University Medical Center, Durham, NC, (4) Duke University Medical Center, Durham, NC
Presentations
TH-AB-201-6 (Thursday, August 3, 2017) 7:30 AM - 9:30 AM Room: 201
Purpose: To investigate methodology for harmonization of radiomic features between planning CT and on-board CBCT and establish a workflow to harmonize images taken from different scanning protocols and over the course of radiotherapy treatments using normalization.
Methods: All CBCT images acquired over the course of lung SBRT for each patient were registered with corresponding planning CT. A volume-of-interest (VOI) in a homogeneous soft-tissue region that would not change over the course of radiotherapy was selected on the planning CT. The VOI was applied to all CBCT images of the same patient taken at different days. The first CBCT was normalized to the planning CT using the ratio of their respective mean VOI pixel values. Subsequent CBCT images were normalized using the ratio of that CBCT’s mean VOI pixel value to the first CBCT’s mean VOI pixel value. Forty-three features characterizing image intensity and morphology in fine and coarse textures were extracted from the planning CT, original CBCT images, and normalized CBCT images. T-test on extracted features from CBCT images with and without normalization indicates the effect of normalization on the distribution of various features. Mutual information between the planning CT and the first CBCT with and without normalization was calculated to assess the effectiveness of normalization on harmonizing radiomic features.
Results: T-test on planning CT and CBCT images of 5 patients indicates that normalization generated statistically significant change of distribution in 36 out of 43 features (p<0.05). Patients with low mutual information between planning CT and the first CBCT before normalization have increased mutual information after normalization. Those with high mutual information before have decreased mutual information after.
Conclusion: Normalization can harmonize radiomic features on both planning CT and on-board CBCT. Further research is expected to examine whether normalization can improve the correlation between feature distribution and cumulative therapeutic dose.
Contact Email: