B Riley*, C Wang, Z Yang, Y Mowery, D Brizel, F Yin, K Lafata, Duke University Medical Center, Durham, NC

• 
  B Riley

TH-B-202-1 (Thursday, 7/14/2022) 8:30 AM - 9:30 AM [Eastern Time (GMT-4)]

Room 202

Purpose: Characterize the effect of PET image discretization on radiomic features of patients undergoing definitive radiotherapy for oropharyngeal cancer (OPC).

Methods: 71 patients were enrolled in a prospective clinical trial to receive definitive radiotherapy (70Gy) for OPC. 8F-FDG PET/CT images were acquired both prior to treatment and two weeks into treatment (i.e., after 20 Gy). All patients were scanned on the same departmental Siemens Biograph mCT PET-CT scanner. The gross tumor volume at the primary tumor site was manually segmented on CT then transferred to PET, from which 74 quantitative radiomic features were extracted. Feature values at monotonically increasing bin numbers (32, 64, 128, 256) and bin sizes (0.1, 0.5, 1.0, 5.0) were measured to gauge the sensitivity of features to two discretization techniques: Fixed Bin Number and Fixed Bin Size. Paired t-tests of individual features. A discretization invariance score (DIS) was defined as an aggregation of each unique probability of rejecting the null hypothesis that any two discretization techniques produce the same feature value. To evaluate the generalization of these characteristics during treatment, DIS values were compared between pre- and intra-treatment imaging.

Results: 50% of radiomic features were robust (DIS>0.7) to changes in bin number, compared to 66% of features when varying bin size. Regardless of discretization technique, grey level variance (DIS=0.0) and high grey level size emphasis (DIS=0.21) were most sensitive to binning perturbations, while skewness (DIS=1.0) and kurtosis (DIS=1.0) were invariant. Ranked DIS measurements were comparable between pre-treatment and intra-treatment imaging, suggesting that feature sensitivity is invariant to changes in the absolute feature value over time.

Conclusion: Individual features demonstrated a non-linear response to systematic changes in discretization parameters, captured by our DIS metric. DIS values can be used to optimize downstream radiomic biomarkers, where the prognostic value of individual features may depend on feature-specific discretization.

Funding Support, Disclosures, and Conflict of Interest: DOD\CDMRP W81XWH2110248

Keywords

PET, Feature Extraction, Texture Analysis

Taxonomy

IM/TH- Image Analysis (Single Modality or Multi-Modality): Imaging biomarkers and radiomics

Contact Email