Evaluation of Recurrence Risk in Irreversible Electroporation-Treated Pancreatic Adenocarcinoma Patients Using Radiomics Signatures

TL;DR

This study shows that radiomics signatures from CT scans can predict recurrence risk in pancreatic cancer patients treated with irreversible electroporation.

Contribution

The novel use of radiomics signatures from pre-treatment CT scans to predict outcomes in IRE-treated pancreatic cancer patients.

Findings

Radiomics features from pre-treatment CT scans significantly predicted time to recurrence with hazard ratios up to 3.13.

Composite radiomics features derived from intensity and filter groups showed strong associations with survival differences.

Gray-level co-occurrence matrix features indicated a 6.6-month median survival difference between risk groups.

Abstract

To investigate if radiomics signatures generated from longitudinal CT scans could predict IRE treatment effectiveness and outcomes in patients with locally advanced pancreatic cancer (LAPC).  A cohort of 50 (60% male, mean [SD] age 60.7 [8.7] years) LAPC patients treated with IRE were retrospectively selected. Preoperative and 12-week follow-up CT were reviewed by two radiologists for tumor segmentation. Statistically significant separation between high and low patient TTR risk groups was observed in: Gray-level co-occurrence matrix (HR = 2.65, p < 0.01, median survival difference = 6.6 mo); composite radiomics features derived from the following feature groups: all radiomics features (HR = 2.27, p = 0.01, median survival difference = 6.4 mo), intensity features (HR = 3.13, p < 0.01, median survival difference = 14.0 mo), and filter features (HR = 2.27, p = 0.01, median survival difference = 6.4 mo).  Pre-treatment radiomics signatures were significantly associated with LAPC patient outcomes. The observed correlations used pre-treatment CT scans, implying that the features are predicting individual risk of disease recurrence.

Purpose: To investigate if radiomics signatures generated from longitudinal CT scans could predict IRE treatment effectiveness and outcomes in patients with locally advanced pancreatic cancer (LAPC). Methods: A cohort of 50 (60% male, mean [SD] age 60.7 [8.7] years) LAPC patients treated with IRE were retrospectively selected. Preoperative and 12-week follow-up CT scans were reviewed by two radiologists for tumor segmentation. A total of 2078 features were extracted: shape (n = 16), texture (n = 68), filter (n = 1892), intensity (n = 18), and local texture (n = 84). Principal component analysis (PCA) was applied to develop composite radiomics features. Composite signatures and clinically relevant radiomics features were correlated with time to recurrence (TTR), time to local recurrence (TTLR), time to distant recurrence (TTDR), recurrence-free survival (RFS) and overall survival (OS). Risk stratification performance was evaluated using hazard ratios (HRs), and significance was evaluated using the log-rank test. Results: Statistically significant separation between high and low patient TTR risk groups was observed in the following: gray-level co-occurrence matrix (HR = 2.65, p < 0.01, median survival difference = 6.6 mo); composite radiomics features derived from the following feature groups: all radiomics features (HR = 2.27, p = 0.01, median survival difference = 6.4 mo), intensity features (HR = 3.13, p < 0.01, median survival difference = 14.0 mo), and filter features (HR = 2.27, p = 0.01, median survival difference = 6.4 mo). Conclusions: Pre-treatment radiomics signatures were significantly associated with LAPC patient outcomes. The observed correlations used pre-treatment CT scans, implying that the features predict the individual risk of disease recurrence.

Figures