X2CT-FLOW: Reconstruction of multiple volumetric chest computed tomography images with different likelihoods from a uni- or biplanar chest X-ray image using a flow-based generative model.
Hisaichi ShibataShouhei HanaokaYukihiro NomuraTakahiro NakaoTomomi TakenagaNaoto HayashiOsamu AbePublished in: CoRR (2021)
Keyphrases
- x ray images
- generative model
- x ray
- medical images
- tomographic images
- three dimensional
- computer tomography
- computed tomography images
- computed tomography
- probabilistic model
- automatic segmentation
- medical imaging
- posterior probability
- ct scans
- lung nodules
- bayesian framework
- prior knowledge
- em algorithm
- low dose
- image reconstruction
- flow field
- likelihood function
- discriminative models
- abdominal organs
- intraoperative
- ct images
- semi supervised
- latent dirichlet allocation
- clinical applications
- topic models
- d objects
- active learning
- high resolution
- training data