ASC-Net: Adversarial-Based Selective Network for Unsupervised Anomaly Segmentation

Dey, Raunak; Hong, Yi

doi:10.1007/978-3-030-87240-3_23

“…Moreover, the lack of added representational capacity upon adding new layers raises some further questions regarding what are optimal architectures for hierarchical GPs, what inductive biases do they need or how to properly initialize them to facilitate adequate training. Additionally, our comparison with respect to reconstruction based approaches towards OOD detection was not complete as it did not include a comprehensive list of recent models (Dey and Hong, 2021;Pinaya et al, 2021;Schlegl et al, 2019;Baur et al, 2018). However, comparing our proposed model with reconstruction based approaches was not our intended goal for this paper, the main aim being to compare with models which can provide accurate predictive results alongside OOD detection capabilities at the same time.…”

Section: Discussionmentioning

confidence: 99%

Distributional Gaussian Processes Layers for Out-of-Distribution Detection

Popescu

¹

,

Sharp

²

,

Cole

³

et al. 2022

Melba

0

View full text Add to dashboard Cite

Machine learning models deployed on medical imaging tasks must be equipped with out-of-distribution detection capabilities in order to avoid erroneous predictions. It is unsure whether out-of-distribution detection models reliant on deep neural networks are suitable for detecting domain shifts in medical imaging. Gaussian Processes can reliably separate in-distribution data points from out-of-distribution data points via their mathematical construction. Hence, we propose a parameter efficient Bayesian layer for hierarchical convolutional Gaussian Processes that incorporates Gaussian Processes operating in Wasserstein-2 space to reliably propagate uncertainty. This directly replaces convolving Gaussian Processes with a distance-preserving affine operator on distributions. Our experiments on brain tissue-segmentation show that the resulting architecture approaches the performance of well-established deterministic segmentation algorithms (U-Net), which has not been achieved with previous hierarchical Gaussian Processes. Moreover, by applying the same segmentation model to out-of-distribution data (i.e., images with pathology such as brain tumors), we show that our uncertainty estimates result in out-of-distribution detection that outperforms the capabilities of previous Bayesian networks and reconstruction-based approaches that learn normative distributions.

show abstract

“…Moreover, the lack of added representational capacity upon adding new layers raises some further questions regarding what are optimal architectures for hierarchical GPs, what inductive biases do they need or how to properly initialize them to facilitate adequate training. Additionally, our comparison with respect to reconstruction based approaches towards OOD detection was not complete as it did not include a comprehensive list of recent models (Dey and Hong, 2021;Pinaya et al, 2021;Schlegl et al, 2019;Baur et al, 2018). However, comparing our proposed model with reconstruction based approaches was not our intended goal for this paper, the main aim being to compare with models which can provide accurate predictive results alongside OOD detection capabilities at the same time.…”

Section: Discussionmentioning

confidence: 99%

Untitled

2022

Melba

0

View full text Add to dashboard Cite

Machine learning models deployed on medical imaging tasks must be equipped with out-of-distribution detection capabilities in order to avoid erroneous predictions. It is unsure whether out-of-distribution detection models reliant on deep neural networks are suitable for detecting domain shifts in medical imaging. Gaussian Processes can reliably separate in-distribution data points from out-of-distribution data points via their mathematical construction. Hence, we propose a parameter efficient Bayesian layer for hierarchical convolutional Gaussian Processes that incorporates Gaussian Processes operating in Wasserstein-2 space to reliably propagate uncertainty. This directly replaces convolving Gaussian Processes with a distance-preserving affine operator on distributions. Our experiments on brain tissue-segmentation show that the resulting architecture approaches the performance of well-established deterministic segmentation algorithms (U-Net), which has not been achieved with previous hierarchical Gaussian Processes. Moreover, by applying the same segmentation model to out-of-distribution data (i.e., images with pathology such as brain tumors), we show that our uncertainty estimates result in out-of-distribution detection that outperforms the capabilities of previous Bayesian networks and reconstruction-based approaches that learn normative distributions. To facilitate future work our code is publicly available 1 .

show abstract

“…The sliced-based techniques [20], [21] extract slices from the 3D neuroimaging brain scan by projecting the sagittal, coronal, and axial to the 2D image slices. Indeed, because non-affected regions and normal slices must be chosen as the reference distribution, they cannot account for the disease and may be considered an anomaly [22]. Furthermore, choosing separate 2D slices may neglect the spatial dependencies of voxels in adjacent slices due to inter/intra anatomical variances in the brain images [14].…”

Section: Literature Reviewmentioning

confidence: 99%

A Multi-Stream Convolutional Neural Network for Classification of Progressive MCI in Alzheimer’s Disease Using Structural MRI Images

Ashtari-Majlan

¹

,

Seifi

²

,

Dehshibi

³

2022

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Early diagnosis of Alzheimer's disease and its prodromal stage, also known as mild cognitive impairment (MCI), is critical since some patients with progressive MCI will develop the disease. We propose a multi-stream deep convolutional neural network fed with patch-based imaging data to classify stable MCI and progressive MCI. First, we compare MRI images of Alzheimer's disease with cognitively normal subjects to identify distinct anatomical landmarks using a multivariate statistical test. These landmarks are then used to extract patches that are fed into the proposed multi-stream convolutional neural network to classify MRI images. Next, we train the architecture in a separate scenario using samples from Alzheimer's disease images, which are anatomically similar to the progressive MCI ones and cognitively normal images to compensate for the lack of progressive MCI training data. Finally, we transfer the trained model weights to the proposed architecture in order to fine-tune the model using progressive MCI and stable MCI data. Experimental results on the ADNI-1 dataset indicate that our method outperforms existing methods for MCI classification, with an F1-score of 85.96%.

show abstract

ASC-Net: Adversarial-Based Selective Network for Unsupervised Anomaly Segmentation

Cited by 17 publications

References 20 publications

Distributional Gaussian Processes Layers for Out-of-Distribution Detection

Distributional Gaussian Processes Layers for Out-of-Distribution Detection

Untitled

A Multi-Stream Convolutional Neural Network for Classification of Progressive MCI in Alzheimer’s Disease Using Structural MRI Images

Contact Info

Product

Resources

About