Machine learning helps identifying volume-confounding effects in radiomics.

Journal: Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)
PMID: 32088562

Abstract

Highlighting the risk of biases in radiomics-based models will help improve their quality and increase usage as decision support systems in the clinic. In this study we use machine learning-based methods to identify the presence of volume-confounding effects in radiomics features. Methods 841 radiomics features were extracted from two retrospective publicly available datasets of lung and head neck cancers using open source software. Unsupervised hierarchical clustering and principal component analysis (PCA) identified relations between radiomics and clinical outcomes (overall survival). Bootstrapping techniques with logistic regression verified features' prognostic power and robustness. Results Over 80% of the features had large pairwise correlations. Nearly 30% of the features presented strong correlations with tumor volume. Using volume-independent features for clustering and PCA did not allow risk stratification of patients. Clinical predictors outperformed radiomics features in bootstrapping and logistic regression. Conclusions The adoption of safeguards in radiomics is imperative to improve the quality of radiomics studies. We proposed machine learning (ML) - based methods for robust radiomics signatures development.

Authors

  • Alberto Traverso
    Maastricht University Medical Centre, Netherlands.
  • Michal Kazmierski
    Princess Margaret Cancer Centre, University Health Network, Canada, Toronto, ON, Canada.
  • Ivan Zhovannik
    Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre+, Maastricht, The Netherlands; Department of Radiation Oncology, Radboudumc, Nijmegen, The Netherlands.
  • Mattea Welch
    Princess Margaret Cancer Centre, University Health Network, Canada, Toronto, ON, Canada.
  • Leonard Wee
    Maastricht University Medical Centre, Netherlands.
  • David Jaffray
    Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, Canada.
  • Andre Dekker
    Department of Radiation Oncology (MAASTRO Clinic), Dr. Tanslaan 12, Maastricht, The Netherlands.
  • Andrew Hope
    Radiation Oncology, Princess Margaret Hospital Cancer Centre, Toronto, Ontario, Canada.

Keywords

External Resources

Popular Topics
Recent Journals