Interpretable explanations of black box classifiers applied on medical images by meaningful perturbations using variational autoencoders.
Hristina UzunovaJan EhrhardtTimo KeppHeinz HandelsPublished in: Medical Imaging: Image Processing (2019)
Keyphrases
- medical images
- black box
- medical image analysis
- medical imaging
- medical image segmentation
- magnetic resonance imaging
- anatomical structures
- magnetic resonance images
- medical data
- mr images
- medical diagnosis
- white box
- imaging modalities
- image intensity
- black boxes
- magnetic resonance
- brain images
- ct images
- deformable models
- clinical practice
- region of interest
- x ray images
- computed tomography
- medical image retrieval
- computer aided diagnosis
- biomedical images
- segmentation of medical images
- image processing
- three dimensional
- test cases
- denoising
- computer tomography
- training data
- integration testing
- feature selection
- open source
- image data
- training set
- white box testing