Generalizability issues with deep learning models in medicine and their potential solutions: illustrated with Cone-Beam Computed Tomography (CBCT) to Computed Tomography (CT) image conversion.
Xiao LiangDan NguyenSteve B. JiangPublished in: CoRR (2020)
Keyphrases
- computed tomography
- ct images
- cone beam ct
- cone beam
- medical images
- ct scans
- cone beam computed tomography
- medical imaging
- radiation therapy
- ct data
- image reconstruction
- three dimensional
- computer tomography
- region of interest
- loss function
- x ray
- anatomical structures
- treatment planning
- machine learning
- image processing
- imaging modalities
- radon transform
- projection images
- feature selection