Medical Applications with Disentanglements
Description
The 8 full papers presented in this book together with one short paper were carefully reviewed and cover generative adversarial networks (GAN), variational autoencoders (VAE) and normalizing-flow architectures as well as a wide range of medical applications, like brain age prediction, skull reconstruction and unsupervised pathology disentanglement.
More details
Other editions
Additional editions
Content
Applying Disentanglement in the Medical Domain: An Introduction.- HSIC-InfoGAN: Learning Unsupervised Disentangled Representations by Maximising Approximated Mutual Information.- Implicit Embeddings via GAN Inversion for High Resolution Chest Radiographs.- Disentangled Representation Learning for Privacy-Preserving Case-Based Explanations.- Instance-Specific Augmentation of Brain MRIs with Variational Autoencoder.- Low-rank and Sparse Metamorphic Autoencoders for Unsupervised Pathology Disentanglement.- Training ß-VAE by Aggregating a Learned Gaussian Posterior with a Decoupled Decoder.- Disentangling Factors of Morpholigical Variation in an Invertible Brain Aging Model.- A study of representational properties of unsupervised anomaly detection in brain MRI.