Overcoming the "catastrophic forgetting" effect in transfer learning to achieve vendor independent performance for the COVID-19 pneumonia classification task using chest x-ray radiographs.
Ran ZhangGuang-Hong ChenPublished in: Medical Imaging: Computer-Aided Diagnosis (2021)
Keyphrases
- x ray
- transfer learning
- x ray images
- text classification
- machine learning
- knowledge transfer
- intraoperative
- medical imaging
- cross domain learning
- digital x ray images
- three dimensional
- tomographic images
- projection images
- machine learning algorithms
- cross domain
- electron microscopy
- training set
- low dose
- labeled data
- ct scans
- support vector
- chest radiographs
- decision trees
- active learning
- supervised learning
- lung nodules
- semi supervised learning
- support vector machine
- feature selection
- multi task
- feature extraction
- data sets
- imaging modalities
- domain specific
- text mining
- collaborative filtering
- image registration
- data mining