.png){kind=icon}
返回
StRegA: Unsupervised anomaly detection in brain MRIs using a compact context-encoding variational autoencoder
.png){kind=icon}
OA
AI
DOI：10.1016/j.compbiomed.2022.106093.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Expert interpretation of anatomical images of the human brain is the central part of neuroradiology. Several machine learning-based techniques have been proposed to assist in the analysis process. However, the ML models typically need to be trained to perform a specific task, e.g., brain tumour segmentation or classification. Not only do the corresponding training data require laborious manual annotations, but a wide variety of abnormalities can be present in a human brain MRI - even more than one simultaneously, which renders a representation of all possible anomalies very challenging. Hence, a possible solution is an unsupervised anomaly detection (UAD) system that can learn a data distribution from an unlabelled dataset of healthy subjects and then be applied to detect out-of-distribution samples. Such a technique can then be used to detect anomalies - lesions or abnormalities, for example, brain tumours, without explicitly training the model for that specific pathology. Several Variational Autoencoder (VAE) based techniques have been proposed in the past for this task. Even though they perform very well on controlled artificially simulated anomalies, many of them perform poorly while detecting anomalies in clinical data. This research proposes a compact version of the context-encoding VAE (ceVAE) model, combined with pre and post-processing steps, creating a UAD pipeline (StRegA), which is more robust on clinical data and shows its applicability in detecting anomalies such as tumours in brain MRIs. The proposed pipeline achieved a Dice score of 0.642 +/- 0.101 while detecting tumours in T2w images of the BraTS dataset and 0.859 +/- 0.112 while detecting artificially induced anomalies, while the best performing baseline achieved 0.522 +/- 0.135 and 0.783 +/- 0.111, respectively.
Keyword:
Anomaly detection
Unsupervised learning
MRI
Brain tumour segmentation
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.3
论文数:
8.3K
被引数:
3.3W
机构
引用论文
Numerically optimized structures for dielectric asymmetric dual-grating laser accelerators介质非对称双光栅激光加速器的数值优化结构
PREAI
分享收藏分享收藏Video anomaly detection and localization via multivariate gaussian fully convolution adversarial autoencoder.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏The relationship between performance on the standardised field sobriety tests, driving performance and the level of Δ9-tetrahydrocannabinol (THC) in blood标准化现场清醒测试的性能，驾驶性能与血液中 Δ9-四氢大麻酚 (THC) 水平之间的关系
PREAI
分享收藏Unsupervised brain imaging 3D anomaly detection and segmentation with transformers基于transformers的无监督脑成像3D异常检测与分割MEDICAL IMAGE ANALYSIS
OAAI
MEDICAL IMAGE ANALYSISIF11.8
OAAI分享收藏
查看更多内容