Better Than Ground-truth? Beyond Supervised Learning for Photoacoustic Imaging Reconstruction.
Hengrong LanChangchun YangFeng GaoFei GaoPublished in: CoRR (2020)
Keyphrases
- ground truth
- supervised learning
- high resolution
- diffusion weighted mri
- unsupervised learning
- positron emission tomography
- ground truth data
- high quality
- reinforcement learning
- image reconstruction
- imaging systems
- image processing
- digital holography
- limited angle
- image analysis
- poisson noise
- learning tasks
- three dimensional
- scan data
- semi supervised
- training data
- single photon emission computed tomography
- manually labeled
- multislice
- medical imaging
- tomographic reconstruction
- gold standard
- active learning
- high resolution images
- supervised machine learning
- machine learning
- class labels
- distortion correction
- low resolution
- computer vision
- learning algorithm
- reconstruction process
- synthetic aperture
- labeled data
- diffusion mri
- training set
- image segmentation