Quantification of pulmonary involvement in COVID-19 pneumonia by means of a cascade oftwo U-nets: training and assessment on multipledatasets using different annotation criteria.
Francesca LizziAbramo AgostiFrancesca BreroRaffaella Fiamma CabiniMaria Evelina FantacciSilvia FiginiAlessandro LascialfariFrancesco LaruinaPiernicola OlivaStefano PifferIan PostumaLisa RinaldiCinzia TalamontiAlessandra ReticoPublished in: CoRR (2021)
Keyphrases
- annotation effort
- supervised learning
- boosted classifiers
- training set
- active learning
- semantic annotation
- test set
- selection criteria
- multiple criteria
- evaluation criteria
- automatic segmentation
- data sets
- face detection
- online learning
- medical images
- training algorithm
- training phase
- image retrieval
- object recognition
- computer based training
- image segmentation
- metadata