Virtual Library

Start Your Search

D. Vuong



Author of

  • +

    Poster Display session (Friday) (ID 65)

    • Event: ELCC 2018
    • Type: Poster Display session
    • Track:
    • Presentations: 1
    • Moderators:
    • Coordinates: 4/13/2018, 12:30 - 13:00, Hall 1
    • +

      76P - Robustness of radiomic features in [18F]-FDG PET/CT and [18F]-FDG PET/MR (ID 304)

      12:30 - 13:00  |  Presenting Author(s): D. Vuong

      • Abstract

      Background:
      Radiomics is a promising tool for identification of new prognostic biomarkers. However, image reconstruction settings may affect the absolute values of radiomic features, which reduces their value as reliable biomarkers. PET/MR is becoming more available and often replaces PET/CT. The aim of this study was to quantify to what extend [18F]-FDG PET/CT radiomics models can be transferred to [18F]-FDG PET/MR.

      Methods:
      Nine patients with non-small cell lung cancer underwent first an [18F]-FDG PET/MR scan followed by an [18F]-FDG PET/CT scan (SIGNA PET/MR and Discovery PET/CT 690, GE Healthcare) with a delay time of 38 min +/−5 min. Patients had one single FDG injection for both scans. The primary tumors were segmented independently on the PET scans from PET/CT and PET/MR with two semi-automated methods (gradient-based and threshold-based). Resampling was performed to the lowest resolution. In total, 1358 radiomic features were calculated, i.e. shape (18), intensity (17), texture (137), wavelets (1186). The intra-class correlation coefficient was used to compare the radiomic features in both image modalities. An ICC >0.9 was considered stable among both types of PET scans.

      Results:
      The median relative volume difference of the tumors segmented on PET/CT and PET/MR was 4.8% (range 0.4–39.9%) for the gradient-based and 18.0% (range 0.7–71.2%) for the threshold-based method. A larger number of radiomic features was stable using the gradient-based method compared to the threshold-based method, which concurs with the improved reproducibility of tumor volume using gradient-based method. More than 70.6% of shape and intensity features yielded an ICC >0.9 among both segmentation methods. However, only 51.5% of texture and 27.2% of wavelet features reached this criterion (for gradient-based and even less in threshold-based method). In the wavelet features analysis, more features were robust in smoothed images (low-pass filtering) in comparison to images with emphasized heterogeneity (high-pass filtering).

      Conclusions:
      Shape and intensity radiomic features were robust comparing the two types of [18F]-FDG PET scans (PET/CT and PET/MR). In contrast, texture and wavelet features showed reduced stability, which needs to be considered for their use in prognostic modelling.

      Clinical trial identification:


      Legal entity responsible for the study:
      Dr. Stephanie Tanadini-Lang

      Funding:
      Has not received any funding

      Disclosure:
      M. Guckenberger: Committee Member EORTC, ESTRO Board of Directors, Head of Working Group DEGRO. All other authors have declared no conflicts of interest.