Login / Signup

Radiomics for glioblastoma survival analysis in pre-operative MRI: exploring feature robustness, class boundaries, and machine learning techniques.

Yannick SuterUrspeter KnechtMariana AlãoWaldo ValenzuelaEkkehard HewerPhilippe SchuchtRoland WiestMauricio Reyes
Published in: Cancer imaging : the official publication of the International Cancer Imaging Society (2020)
Our experiments show that it is possible to attain improved levels of robustness and accuracy when models need to be applied to unseen multi-center data. The performance on multi-center data of models trained on single-center data can be increased by using robust features and introducing prior knowledge. For successful model robustification, tailoring perturbations for robustness testing to the target dataset is key.
Keyphrases
  • machine learning
  • big data
  • electronic health record
  • contrast enhanced
  • artificial intelligence
  • deep learning
  • squamous cell carcinoma
  • computed tomography
  • magnetic resonance
  • resistance training