Assessing the impact of CNN architectures for whole organ segmentation on predictive models of organ toxicity

ORAL

Abstract

Segmentation of disease and critical structures from medical images is a critical task that enables development of predictive models of treatment response and treatment-related toxicities. Convolutional neural networks (CNN) are often used for this task. However, the impact assessment of CNN segmentation model architectures on predictive models’ performance is incipient. Here, we perform such assessment on a 18F-FDG PET histogram metrics-based model for predicting organ inflammation.

Two CNN architectures (DeepMedic, nnUNet) were employed to segment bowel, lungs and thyroid on the CT scans of melanoma cancer patients; from which the PET signal indicative of organ inflammation was extracted. This signal was used to predict organ toxicity via classical statistical and machine learning models. Model performance was assessed using area under the receiver operating characteristic curve. Model’s sensitivity to CNN architecture was analyzed.

Dice similarity coefficient of organ segmentation was 0.96±0.06 (mean±sd) in bowel, 0.87±0.07 in lungs and 0.61±0.16 in thyroid accounting for differences in different CNN architectures. Different CNN architectures had no significant impact on prediction of organ toxicities (z-test, p>0.05).

Our findings suggest that PET-derived, segmentation-based organ toxicity biomarkers are robust against different CNN architectures.

*The authors acknowledge the financial support from the Slovenian Research Agency ARIS (research core funding P1-0389).

–

Presenters

  • Katja Strasek

    • Faculty of Mathematics and Physics, University of Ljubljana, Ljubljana, Slovenia

Authors

  • Katja Strasek

    • Faculty of Mathematics and Physics, University of Ljubljana, Ljubljana, Slovenia

  • Daniel Huff

    • Department of Medical Physics, University of Wisconsin - Madison

  • Nežka Hribernik

    • Department of Medical Oncology, Institute of Oncology Ljubljana, Ljubljana, Slovenia; Faculty of Medicine, University of Ljubljana, Ljubljana, Slovenia

  • Victor S Fernandes

    • University of Wisconsin - Madison
    • Department of Medical Physics, University of Wisconsin - Madison

  • Vincent T Ma

    • University of Wisconsin Carbone Cancer Center, Madison, WI; Department of Medicine, University of Wisconsin School of Medicine and Public Health, Madison, WI

  • Zan Klanecek

    • University of Ljubljana, Faculty of Mathematics and Physics
    • Faculty of Mathematics and Physics, University of Ljubljana, Ljubljana, Slovenia
    • University of Ljubljana, Faculty of Mathematics and Physics, Medical Physics, Ljubljana, Slovenia

  • Andrej Studen

    • Faculty of Mathematics and Physics, University of Ljubljana, Ljubljana, Slovenia; Experimental Particle Physics Department, Jožef Stefan Institute, Ljubljana, Slovenia
    • University of Ljubljana, Faculty of Mathematics and Physics, Medical Physics, Ljubljana, Slovenia and Jožef Stefan Institute, Ljubljana, Slovenia

  • Katarina Zevnik

    • Department of Nuclear Medicine, Institute of Oncology Ljubljana, Ljubljana, Slovenia

  • Martina Reberšek

    • Department of Medical Oncology, Institute of Oncology Ljubljana, Ljubljana, Slovenia; Faculty of Medicine, University of Ljubljana, Ljubljana, Slovenia

  • Robert Jeraj

    • University of Ljubljana, Faculty of Mathematics and Physics, Slovenia; Jožef Stefan Institute, Ljubljana, Slovenia; University of Wisconsin - Madison, USA
    • University of Ljubljana, Faculty of Mathematics and Physics, Slovenia and Jožef Stefan Institute, Slovenia and University of Wisconsin-Madison, Madison, U.S.A.