q-Space Novelty Detection with Variational Autoencoders

Васильев, А. Э.; Golkov, Vladimir; Meissner, Marc; Lipp, Ilona; Sgarlata, Eleonora; Tomassini, Valentina; Jones, Derek K.; Cremers, Daniel

doi:10.48550/arxiv.1806.02997

Cited by 6 publications

(6 citation statements)

References 6 publications

(7 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[7] [20] [21] [18] Generative models have also been sparsely applied to medical imaging of MS. Looking at disease detection, in one paper, the authors trained a VAE only on the data of healthy patients, with the idea that abnormal samples, in their case images with MS lesions, would also have an abnormal latent space code [24]. They found their approach successful, but this approach is not disease specific, and a brain image with a stroke lesion or other irregularity would also be detected as abnormal.…”

Section: Related Workmentioning

confidence: 99%

Latent Space Analysis of VAE and Intro-VAE applied to 3-dimensional MR Brain Volumes of Multiple Sclerosis, Leukoencephalopathy, and Healthy Patients

Christopher¹,

Federau²

2021

Preprint

View full text Add to dashboard Cite

Multiple Sclerosis (MS) and microvascular leukoencephalopathy are two distinct neurological conditions, the first caused by focal autoimmune inflammation in the central nervous system, the second caused by chronic white matter damage from atherosclerotic microvascular disease. Both conditions lead to signal anomalies on Fluid Attenuated Inversion Recovery (FLAIR) magnetic resonance (MR) images, which can be distinguished by an expert neuroradiologist, but which can look very similar to the untrained eye as well as in the early stage of both diseases. In this paper, we attempt to train a 3-dimensional deep neural network to learn the specific features of both diseases in an unsupervised manner. For this manner, in a first step we train a generative neural network to create artificial MR images of both conditions with approximate explicit density, using a mixed dataset of multiple sclerosis, leukoencephalopathy and healthy patients containing in total 5404 volumes of 3096 patients. In a second step, we distinguish features between the different diseases in the latent space of this network, and use them to classify new data.

show abstract

Section: Related Workmentioning

confidence: 99%

Latent Space Analysis of VAE and Intro-VAE applied to 3-dimensional MR Brain Volumes of Multiple Sclerosis, Leukoencephalopathy, and Healthy Patients

Christopher¹,

Federau²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…This approach is also used in the deep learning community by using an autoencoder for dimensionality reduction (Sakurada & Yairi, 2014;Zhou & Paffenroth, 2017;Zong et al 2018). Variants of the autoencoder such as the variational autoencoder have also proven to be successful in detecting outliers (An & Cho, 2015;Vasilev et al 2018).…”

Section: Related Literaturementioning

confidence: 99%

Self‐supervised learning for outlier detection

Diers

Pigorsch

2021

Stat

View full text Add to dashboard Cite

The identification of outliers is mainly based on unannotated data and therefore constitutes an unsupervised problem. The lack of a label leads to numerous challenges that do not occur or only occur to a lesser extent when using annotated data and supervised methods. In this paper, we focus on two of these challenges: the selection of hyperparameters and the selection of informative features. To this end, we propose a method to transform the unsupervised problem of outlier detection into a supervised problem. Benchmarking our approach against common outlier detection methods shows clear advantages of our method when many irrelevant features are present. Furthermore, the proposed approach also scores very well in the selection of hyperparameters, i.e., compared to methods with randomly selected hyperparameters.

show abstract

“…Hybrid approaches also exist, where anomaly scores are generated by combining measures proposed on the embeddings with reconstruction errors [19]- [21], enhancing model performance at cost of further increased complexity.…”

Section: A Learning Ad From Scratchmentioning

confidence: 99%

Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detection

Rippel¹,

Mertens²,

Merhof³

2020

Preprint

View full text Add to dashboard Cite

Anomaly Detection (AD) in images is a fundamental computer vision problem and refers to identifying images and/or image substructures that deviate significantly from the norm. Popular AD algorithms commonly try to learn a model of normality from scratch using task specific datasets, but are limited to semi-supervised approaches employing mostly normal data due to the inaccessibility of anomalies on a large scale combined with the ambiguous nature of anomaly appearance.We follow an alternative approach and demonstrate that deep feature representations learned by discriminative models on large natural image datasets are well suited to describe normality and detect even subtle anomalies. Our model of normality is established by fitting a multivariate Gaussian to deep feature representations of classification networks trained on ImageNet using normal data only in a transfer learning setting. By subsequently applying the Mahalanobis distance as the anomaly score we outperform the current state of the art on the public MVTec AD dataset, achieving an Area Under the Receiver Operating Characteristic curve of 95.8 ± 1.2% (mean ± SEM) over all 15 classes. We further investigate why the learned representations are discriminative to the AD task using Principal Component Analysis. We find that the principal components containing little variance in normal data are the ones crucial for discriminating between normal and anomalous instances. This gives a possible explanation to the often sub-par performance of AD approaches trained from scratch using normal data only. By selectively fitting a multivariate Gaussian to these most relevant components only we are able to further reduce model complexity while retaining AD performance. We also investigate setting the working point by selecting acceptable False Positive Rate thresholds based on the multivariate Gaussian assumption.

show abstract

q-Space Novelty Detection with Variational Autoencoders

Cited by 6 publications

References 6 publications

Latent Space Analysis of VAE and Intro-VAE applied to 3-dimensional MR Brain Volumes of Multiple Sclerosis, Leukoencephalopathy, and Healthy Patients

Latent Space Analysis of VAE and Intro-VAE applied to 3-dimensional MR Brain Volumes of Multiple Sclerosis, Leukoencephalopathy, and Healthy Patients

Self‐supervised learning for outlier detection

Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detection

Contact Info

Product

Resources

About