Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Study

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

doi:10.48550/arxiv.2004.03271

Cited by 9 publications

(14 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Eq. [4][5][6]: n is the number of voxels in the image, m is the dimensionality of the discriminator feature space, f (x) the activation on the intermediate layer of D and κ is a weighting parameter.…”

Section: Encoder Trainingmentioning

confidence: 99%

“…You et al [25] detect brain tumors using a Gaussian Mixture VAE with restoration of the latent space, while Pawlowski et al [18] use Bayesian Auto-encoders to detect traumatic brain injury lesions. In a very recent comparative study on brain AD, the performance of f-AnoGAN is remarkable in diverse datasets [4]. All of these 2D-based approaches have several drawbacks: i) they do not consider volumetric information and, consequently, they do not effectively handle the complex brain anatomy; ii) they have to consider the whole brain image since there is no prior information of the anomaly localization; iii) they require multiple models for evaluating an entire scan.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised 3D Brain Anomaly Detection

Viana

Rosa

Vyvere

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Anomaly detection (AD) is the identification of data samples that do not fit a learned data distribution. As such, AD systems can help physicians to determine the presence, severity, and extension of a pathology. Deep generative models, such as Generative Adversarial Networks (GANs), can be exploited to capture anatomical variability. Consequently, any outlier (i.e., sample falling outside of the learned distribution) can be detected as an abnormality in an unsupervised fashion. By using this method, we can not only detect expected or known lesions, but we can even unveil previously unrecognized biomarkers. To the best of our knowledge, this study exemplifies the first AD approach that can efficiently handle volumetric data and detect 3D brain anomalies in one single model. Our proposal is a volumetric and high-detail extension of the 2D f-AnoGAN model obtained by combining a state-of-the-art 3D GAN with refinement training steps. In experiments using non-contrast computed tomography images from traumatic brain injury (TBI) patients, the model detects and localizes TBI abnormalities with an area under the ROC curve of ∼75%. Moreover, we test the potential of the method for detecting other anomalies such as low quality images, preprocessing inaccuracies, artifacts, and even the presence of post-operative signs (such as a craniectomy or a brain shunt). The method has potential for rapidly labeling abnormalities in massive imaging datasets, as well as identifying new biomarkers.

show abstract

Section: Encoder Trainingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Unsupervised 3D Brain Anomaly Detection

Viana

Rosa

Vyvere

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Unsupervised learning methods are not included in this survey since an excellent comprehensive survey of these is already provided by Baur et al [8]. As a general note, supervised methods tend to perform better than unsupervised methods for MS lesion segmentation, given the difficulty of the task ( [14,17]).…”

Section: Introductionmentioning

confidence: 99%

Multiple Sclerosis Lesion Segmentation -- A Survey of Supervised CNN-Based Methods

Zhang

Oguz

2020

Preprint

View full text Add to dashboard Cite

Lesion segmentation is a core task for quantitative analysis of MRI scans of Multiple Sclerosis patients. The recent success of deep learning techniques in a variety of medical image analysis applications has renewed community interest in this challenging problem and led to a burst of activity for new algorithm development. In this survey, we investigate the supervised CNN-based methods for MS lesion segmentation. We decouple these reviewed works into their algorithmic components and discuss each separately. For methods that provide evaluations on public benchmark datasets, we report comparisons between their results.

show abstract

“…In other words, most of the scans during the screening are from normal subjects, and only a few subjects are the abnormal with a large intraclass variation. To address these issues, recently, unsupervised deep anomaly detection methods [2][3][4][5][6][7][8][9] have been introduced based on autoencoder-based reconstruction methods [10] or variational autoencoders (VAE) [11]. These methods train a model on large-sized normal scans and detect abnormal scans by calculating reconstruction error because abnormal scans are out-of-distribution, making the model have difficulties reconstructing abnormal areas.…”

Section: Introductionmentioning

confidence: 99%

Self-Supervised Out-of-Distribution Detection in Brain CT Scans

Ravi¹,

Kim²,

Eisawy³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Medical imaging data suffers from the limited availability of annotation because annotating 3D medical data is a time-consuming and expensive task. Moreover, even if the annotation is available, supervised learning-based approaches suffer highly imbalanced data. Most of the scans during the screening are from normal subjects, but there are also large variations in abnormal cases. To address these issues, recently, unsupervised deep anomaly detection methods that train the model on large-sized normal scans and detect abnormal scans by calculating reconstruction error have been reported. In this paper, we propose a novel self-supervised learning technique for anomaly detection. Our architecture largely consists of two parts: 1) Reconstruction and 2) predicting geometric transformations. By training the network to predict geometric transformations, the model could learn better image features and distribution of normal scans. In the test time, the geometric transformation predictor can assign the anomaly score by calculating the error between geometric transformation and prediction. Moreover, we further use self-supervised learning with context restoration for pretraining our model. By comparative experiments on clinical brain CT scans, the effectiveness of the proposed method has been verified.

show abstract

Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Study

Cited by 9 publications

References 0 publications

Unsupervised 3D Brain Anomaly Detection

Unsupervised 3D Brain Anomaly Detection

Multiple Sclerosis Lesion Segmentation -- A Survey of Supervised CNN-Based Methods

Self-Supervised Out-of-Distribution Detection in Brain CT Scans

Contact Info

Product

Resources

About