Login / Signup

Comparison of automated full-body bone metastases delineation methods and their corresponding predictive power.

Brayden SchottAmy J WeismanTimothy G PerkAlison R RothGlenn LiuRobert Jeraj
Published in: Physics in medicine and biology (2022)
This work showed that CNN-based (nnUNet) methods are superior to the non-CNN methods for mCRPC disease delineation in full-body 18F-NaF PET/CT. The CNN-based methods, however, do not hold greater prognostic power for predicting clinical outcome. This merits more investigation on the optimal selection of delineation methods for specific clinical tasks.
Keyphrases
  • pet ct
  • convolutional neural network
  • machine learning
  • deep learning
  • high throughput