Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoders

Chen, Xiaoran; Konukoğlu, Ender

doi:10.48550/arxiv.1806.04972

Cited by 54 publications

(74 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Quantile regression is a simple yet powerful method for estimating uncertainty both in supervised and unsupervised lesion detection. In the unsupervised framework we used the VAE, a popular model for unsupervised lesion detection (Chen and Konukoglu, 2018;Baur et al, 2018;Pawlowski et al, 2018). VAEs can be used to estimate reconstruction probability instead of reconstruction error for anomaly detection tasks.…”

Section: Discussionmentioning

confidence: 99%

Deep Quantile Regression for Uncertainty Estimation in Unsupervised and Supervised Lesion Detection

Akrami¹,

Joshi²,

Aydöre³

et al. 2021

Preprint

View full text Add to dashboard Cite

Despite impressive state-of-the-art performance on a wide variety of machine learning tasks in multiple applications, deep learning methods can produce over-confident predictions, particularly with limited training data. Therefore, quantifying uncertainty is particularly important in critical applications such as anomaly or lesion detection and clinical diagnosis, where a realistic assessment of uncertainty is essential in determining surgical margins, disease status and appropriate treatment. In this work, we focus on using quantile regression to estimate aleatoric uncertainty and use it for estimating uncertainty in both supervised and unsupervised lesion detection problems. In the unsupervised settings, we apply quantile regression to a lesion detection task using Variational AutoEncoder (VAE). The VAE models the output as a conditionally independent Gaussian characterized by means and variances for each output dimension. VAEs therefore enable using reconstruction probability instead of reconstruction error for anomaly detection. Unfortunately, joint optimization of both mean and variance in the VAE leads to the well-known problem of shrinkage or underestimation of variance. We describe an alternative VAE model, Quantile-Regression VAE (QR-VAE), that avoids this variance shrinkage problem by estimating conditional quantiles for the given input image. Using the estimated quantiles, we compute the conditional mean and variance for input images under the conditionally Gaussian model. We then compute reconstruction probability using this model as a principled approach to outlier or anomaly detection applications. In the supervised setting, we develop binary quantile regression (BQR) for the supervised lesion segmentation task. BQR segmentation can capture uncertainty in label boundaries. We show how quantile regression can be used to characterize expert disagreement in the location of lesion boundaries.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep Quantile Regression for Uncertainty Estimation in Unsupervised and Supervised Lesion Detection

Akrami¹,

Joshi²,

Aydöre³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Here, we briefly explain how our DCAE model can serve as a platform for anomaly detection. They trained a reproduction model with enormous data by updating the model weight parameters to minimize the loss function (see e.g., Chen et al 2018;Zimmerer et al 2018;Baur et al 2021). Therefore, the trained model learns the overall structure representation of the training data, but not the uncommon features existing in them.…”

Section: Model Descriptionmentioning

confidence: 99%

Where's Swimmy?: Mining unique color features buried in galaxies by deep anomaly detection using Subaru Hyper Suprime-Cam data

Tanaka,

Shimakawa,

Shimasaku

et al. 2021

Preprint

View full text Add to dashboard Cite

We present the Swimmy (Subaru WIde-field Machine-learning anoMalY) survey program, a deep-learning-based search for unique sources using multicolored (grizy) imaging data from the Hyper Suprime-Cam Subaru Strategic Program (HSC-SSP). This program aims to detect unexpected, novel, and rare populations and phenomena, by utilizing the deep imaging data acquired from the wide-field coverage of the HSC-SSP. This article, as the first paper in the Swimmy series, describes an anomaly detection technique to select unique populations as "outliers" from the data-set. The model was tested with known extreme emission-line galaxies (XELGs) and quasars, which consequently confirmed that the proposed method successfully selected 60∼70% of the quasars and 60% of the XELGs without labeled training data. In reference to the spectral information of local galaxies at z = 0.05-0.2 obtained from the Sloan Digital Sky Survey, we investigated the physical properties of the selected anomalies and compared them based on the significance of their outlier values. The results revealed that XELGs constitute notable fractions of the most anomalous galaxies, and certain galaxies manifest unique morphological features. In summary, deep anomaly detection is an effective tool that

show abstract

“…In comparison, a similar study conducted by [3] consisting of a multitude of algorithms including AnoVAEGAN [4] and f-AnoGANS, obtained a best mean score of 27.8% Dice after post-processing by f-AnoGANS. Before post-processing the best method was Constrained AutoEncoder [8] with a score of 9.7% Dice. An exhaustive list is presented in Table 1.…”

Section: Ms Lesion Segmentation (Ms-seg2015)mentioning

confidence: 99%

ASC-Net: Unsupervised Medical Anomaly Segmentation Using an Adversarial-based Selective Cutting Network

Dey¹,

Sun²,

Xu³

et al. 2021

Preprint

View full text Add to dashboard Cite

In this paper we consider the problem of unsupervised anomaly segmentation in medical images, which has attracted increasing attention in recent years due to the expensive pixel-level annotations from experts and the existence of a large amount of unannotated normal and abnormal image scans. We introduce a segmentation network that utilizes adversarial learning to partition an image into two cuts, with one of them falling into a reference distribution provided by the user. This Adversarial-based Selective Cutting network (ASC-Net) bridges the two domains of cluster-based deep segmentation and adversarialbased anomaly/novelty detection algorithms. Our ASC-Net learns from normal and abnormal medical scans to segment anomalies in medical scans without any masks for supervision. We evaluate this unsupervised anomly segmentation model on three public datasets, i.e., BraTS 2019 for brain tumor segmentation, LiTS for liver lesion segmentation, and MS-SEG 2015 for brain lesion segmentation, and also on a private dataset for brain tumor segmentation. Compared to existing methods, our model demonstrates tremendous performance gains in unsupervised anomaly segmentation tasks. Although there is still room to further improve performance compared to supervised learning algorithms, the promising experimental results and interesting observations shed light on building an unsupervised learning algorithm for medical anomaly identification using user-defined knowledge.

show abstract

Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoders

Cited by 54 publications

References 13 publications

Deep Quantile Regression for Uncertainty Estimation in Unsupervised and Supervised Lesion Detection

Deep Quantile Regression for Uncertainty Estimation in Unsupervised and Supervised Lesion Detection

Where's Swimmy?: Mining unique color features buried in galaxies by deep anomaly detection using Subaru Hyper Suprime-Cam data

ASC-Net: Unsupervised Medical Anomaly Segmentation Using an Adversarial-based Selective Cutting Network

Contact Info

Product

Resources

About