Semi-supervised VAE-GAN for Out-of-Sample Detection Applied to MRI Quality Control
| Autor: | John H. Gilmore, Veronica Murphy, Steven M. Pizer, Martin Styner, Weili Lin, Juan Prieto, Ashley Rumple, Joseph Blocher, Mark Foster, Jed T. Elison, Jessica B. Girault, Mahmoud Mostapha |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Artificial neural network
business.industry Computer science Deep learning Parameterized complexity Pattern recognition 010501 environmental sciences 01 natural sciences Autoencoder 03 medical and health sciences 0302 clinical medicine Discriminative model Anomaly detection Artificial intelligence Invariant (mathematics) business 030217 neurology & neurosurgery 0105 earth and related environmental sciences |
| Zdroj: | Lecture Notes in Computer Science ISBN: 9783030322472 MICCAI (3) |
| DOI: | 10.1007/978-3-030-32248-9_15 |
| Popis: | Discriminative deep learning models have shown remarkable success in many medical image analysis applications. However, their success is limited in problems that involve learning from imbalanced and heterogeneous datasets. Generative models parameterized using deep learning models can resolve this problem by characterizing the distribution of well-represented classes, a step enabling the identification of samples that were improbably generated from that distribution. This paper proposes a semi-supervised out-of-sample detection framework based on a 3D variational autoencoder-based generative adversarial network (VAE-GAN). The proposed framework relies on a high-level similarity metric and invariant representations learned by a semi-supervised discriminator to evaluate the generated images. The encoded latent representations were constrained according to user-defined properties through a jointly trained predictor network. Anomaly samples are detected using learned similarity scores and/or scores from an online one-class neural network. The high performance of the proposed methods is confirmed via a novel application to the automatic quality control of structural MR images. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|