Feature selection methodology for longitudinal cone-beam CT radiomics.
Janita E van TimmerenRalph T H LeijenaarWouter van ElmptBart ReymenPhilippe LambinPublished in: Acta oncologica (Stockholm, Sweden) (2017)
This study describes a feature selection methodology for longitudinal radiomics that is able to select reproducible delta radiomics features that are informative due to their change during treatment, which can potentially be used for treatment decisions concerning adaptive radiotherapy. Nonetheless, the prognostic value of the selected delta radiomic features should be investigated in future studies.
Keyphrases
- contrast enhanced
- lymph node metastasis
- cone beam
- machine learning
- deep learning
- early stage
- magnetic resonance imaging
- computed tomography
- cross sectional
- radiation therapy
- magnetic resonance
- current status
- radiation induced
- locally advanced
- atomic force microscopy
- combination therapy
- case control
- high speed
- smoking cessation