Autoencoders for unsupervised anomaly segmentation in brain MR images: A comparative study

Baur, Christoph; Denner, Stefan; Wiestler, Benedikt; Navab, Nassir; Albarqouni, Shadi

doi:10.1016/j.media.2020.101952

Cited by 228 publications

(239 citation statements)

References 25 publications

Supporting

Mentioning

212

Contrasting

Unclassified

Order By: Relevance

“…Anomalies are then localized by comparing original images to restorations. Restoration-based approaches seem to overall outperform reconstruction-based ones [2].…”

Section: Introductionmentioning

confidence: 96%

“…Second, they are specific to the abnormalities annotated in the datasets, and therefore are unable to generalize to other pathologies. Unsupervised anomaly detection methods, on the other hand, aim to overcome these constraints by not relying on annotated datasets [2]. Instead, they focus on learning the underlying distribution of normal images and then identifying as anomalies the images that do not conform to the learnt distribution.…”

Section: Introductionmentioning

confidence: 99%

“…Recently, methods based on Variational Auto-Encoders (VAEs) have been proposed to identify and localize anomalies in medical images [2,3,4]. VAEs are generative models trained by minimizing a loss function composed of a reconstruction term (measuring the distance between original images and reconstructions) and a Kullback-Leibler (KL) divergence term (measuring the distance between the latent distribution and a prior, generally assumed to be Gaussian).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Anomaly Detection Through Latent Space Restoration Using Vector Quantized Variational Autoencoders

Marimont

Tarroni

2021

2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)

View full text Add to dashboard Cite

We propose an out-of-distribution detection method that combines density and restoration-based approaches using Vector-Quantized Variational Auto-Encoders (VQ-VAEs). The VQ-VAE model learns to encode images in a categorical latent space. The prior distribution of latent codes is then modelled using an Auto-Regressive (AR) model. We found that the prior probability estimated by the AR model can be useful for unsupervised anomaly detection and enables the estimation of both sample and pixel-wise anomaly scores. The sample-wise score is defined as the negative loglikelihood of the latent variables above a threshold selecting highly unlikely codes. Additionally, out-of-distribution images are restored into in-distribution images by replacing unlikely latent codes with samples from the prior model and decoding to pixel space. The average L1 distance between generated restorations and original image is used as pixelwise anomaly score. We tested our approach on the MOOD challenge datasets, and report higher accuracies compared to a standard reconstruction-based approach with VAEs.

show abstract

“…Anomalies are then localized by comparing original images to restorations. Restoration-based approaches seem to overall outperform reconstruction-based ones [2].…”

Section: Introductionmentioning

confidence: 96%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Anomaly Detection Through Latent Space Restoration Using Vector Quantized Variational Autoencoders

Marimont

Tarroni

2021

2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)

View full text Add to dashboard Cite

show abstract

“…Note that supervised methods only generalize well to cases that are sufficiently represented in the training data. However, diverse and large annotated data sets are costly to obtain, and often only a few limited cases are available for rare diseases [4].…”

Section: Introductionmentioning

confidence: 99%

Three-dimensional deep learning with spatial erasing for unsupervised anomaly segmentation in brain MRI

et al. 2021

View full text Add to dashboard Cite

Purpose Brain Magnetic Resonance Images (MRIs) are essential for the diagnosis of neurological diseases. Recently, deep learning methods for unsupervised anomaly detection (UAD) have been proposed for the analysis of brain MRI. These methods rely on healthy brain MRIs and eliminate the requirement of pixel-wise annotated data compared to supervised deep learning. While a wide range of methods for UAD have been proposed, these methods are mostly 2D and only learn from MRI slices, disregarding that brain lesions are inherently 3D and the spatial context of MRI volumes remains unexploited. Methods We investigate whether using increased spatial context by using MRI volumes combined with spatial erasing leads to improved unsupervised anomaly segmentation performance compared to learning from slices. We evaluate and compare 2D variational autoencoder (VAE) to their 3D counterpart, propose 3D input erasing, and systemically study the impact of the data set size on the performance. Results Using two publicly available segmentation data sets for evaluation, 3D VAEs outperform their 2D counterpart, highlighting the advantage of volumetric context. Also, our 3D erasing methods allow for further performance improvements. Our best performing 3D VAE with input erasing leads to an average DICE score of 31.40% compared to 25.76% for the 2D VAE. Conclusions We propose 3D deep learning methods for UAD in brain MRI combined with 3D erasing and demonstrate that 3D methods clearly outperform their 2D counterpart for anomaly segmentation. Also, our spatial erasing method allows for further performance improvements and reduces the requirement for large data sets.

show abstract

“…Here we considered two of these. A deep convolutional neural network and an autoencoder (Baur et al, 2020 ). In addition, because it was possible that these two types would do better at replicating specific aspects of the overall solution, we also evaluated a superposition of the two.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Approaches to Surrogates for Solving the Diffusion Equation for Mechanistic Real-World Simulations

et al. 2021

View full text Add to dashboard Cite

In many mechanistic medical, biological, physical, and engineered spatiotemporal dynamic models the numerical solution of partial differential equations (PDEs), especially for diffusion, fluid flow and mechanical relaxation, can make simulations impractically slow. Biological models of tissues and organs often require the simultaneous calculation of the spatial variation of concentration of dozens of diffusing chemical species. One clinical example where rapid calculation of a diffusing field is of use is the estimation of oxygen gradients in the retina, based on imaging of the retinal vasculature, to guide surgical interventions in diabetic retinopathy. Furthermore, the ability to predict blood perfusion and oxygenation may one day guide clinical interventions in diverse settings, i.e., from stent placement in treating heart disease to BOLD fMRI interpretation in evaluating cognitive function (Xie et al., 2019; Lee et al., 2020). Since the quasi-steady-state solutions required for fast-diffusing chemical species like oxygen are particularly computationally costly, we consider the use of a neural network to provide an approximate solution to the steady-state diffusion equation. Machine learning surrogates, neural networks trained to provide approximate solutions to such complicated numerical problems, can often provide speed-ups of several orders of magnitude compared to direct calculation. Surrogates of PDEs could enable use of larger and more detailed models than are possible with direct calculation and can make including such simulations in real-time or near-real time workflows practical. Creating a surrogate requires running the direct calculation tens of thousands of times to generate training data and then training the neural network, both of which are computationally expensive. Often the practical applications of such models require thousands to millions of replica simulations, for example for parameter identification and uncertainty quantification, each of which gains speed from surrogate use and rapidly recovers the up-front costs of surrogate generation. We use a Convolutional Neural Network to approximate the stationary solution to the diffusion equation in the case of two equal-diameter, circular, constant-value sources located at random positions in a two-dimensional square domain with absorbing boundary conditions. Such a configuration caricatures the chemical concentration field of a fast-diffusing species like oxygen in a tissue with two parallel blood vessels in a cross section perpendicular to the two blood vessels. To improve convergence during training, we apply a training approach that uses roll-back to reject stochastic changes to the network that increase the loss function. The trained neural network approximation is about 1000 times faster than the direct calculation for individual replicas. Because different applications will have different criteria for acceptable approximation accuracy, we discuss a variety of loss functions and accuracy estimators that can help select the best network for a particular application. We briefly discuss some of the issues we encountered with overfitting, mismapping of the field values and the geometrical conditions that lead to large absolute and relative errors in the approximate solution.

show abstract

Autoencoders for unsupervised anomaly segmentation in brain MR images: A comparative study

Cited by 228 publications

References 25 publications

Anomaly Detection Through Latent Space Restoration Using Vector Quantized Variational Autoencoders

Anomaly Detection Through Latent Space Restoration Using Vector Quantized Variational Autoencoders

Three-dimensional deep learning with spatial erasing for unsupervised anomaly segmentation in brain MRI

Deep Learning Approaches to Surrogates for Solving the Diffusion Equation for Mechanistic Real-World Simulations

Contact Info

Product

Resources

About