Automatic segmentation of cerebral white matter hyperintensities using only 3D FLAIR images.
TL;DR: This work proposes an automatic lesion segmentation method that uses only three-dimensional fluid-attenuation inversion recovery (FLAIR) images and uses a modified context-sensitive Gaussian mixture model to determine voxel class probabilities, followed by correction of FLAIR artifacts.
About: This article is published in Magnetic Resonance Imaging.The article was published on 2013-09-01. It has received 52 citations till now. The article focuses on the topics: Segmentation & Cognitive decline.
Citations
More filters
TL;DR: The findings suggest that BIANCA, which will be freely available as part of the FSL package, is a reliable method for automated WMH segmentation in large cross-sectional cohort studies.
303 citations
Additional excerpts
...…0.45 0.62 0.65 (Ji et al., 2013) S FLAIR WM disease / 0.87 (Yoo et al., 2014) S FLAIR Longitudinal study ageing and dementia 0.98 0.76 0.59 0.73 0.85 (Simões et al., 2013) S FLAIR HC, MCI / 0.68 0.51 0.70 (Herskovits et al., 2008) S T1, T2, spin-density, FLAIR Diabetes (ACCORD-MIND study) / 0.60…...
[...]
TL;DR: This paper applies and compares the proposed architectures for segmentation of white matter hyperintensities in brain MR images on a large dataset and observes that the CNNs that incorporate location information substantially outperform a conventional segmentation method with handcrafted features as well asCNNs that do not integrate location information.
Abstract: The anatomical location of imaging features is of crucial importance for accurate diagnosis in many medical tasks. Convolutional neural networks (CNN) have had huge successes in computer vision, but they lack the natural ability to incorporate the anatomical location in their decision making process, hindering success in some medical image analysis tasks. In this paper, to integrate the anatomical location information into the network, we propose several deep CNN architectures that consider multi-scale patches or take explicit location features while training. We apply and compare the proposed architectures for segmentation of white matter hyperintensities in brain MR images on a large dataset. As a result, we observe that the CNNs that incorporate location information substantially outperform a conventional segmentation method with handcrafted features as well as CNNs that do not integrate location information. On a test set of 50 scans, the best configuration of our networks obtained a Dice score of 0.792, compared to 0.805 for an independent human observer. Performance levels of the machine and the independent human observer were not statistically significantly different (p-value = 0.06).
212 citations
TL;DR: The effectiveness and generalization capability of the proposed system show its potential for real‐world clinical practice and are the highest achieved in the challenge, suggesting the proposed method is the state‐of‐the‐art.
175 citations
TL;DR: A comprehensive literature review of U-shaped networks applied to medical image segmentation tasks, focusing on the architectures, extended mechanisms and application areas in these studies.
146 citations
TL;DR: This work proposes a hierarchical fully unsupervised model selection framework for neuroimaging data which enables the distinction between different types of abnormal image patterns without pathological a priori knowledge and demonstrates the ability to detect abnormal intensity clusters.
Abstract: In neuroimaging studies, pathologies can present themselves as abnormal intensity patterns. Thus, solutions for detecting abnormal intensities are currently under investigation. As each patient is unique, an unbiased and biologically plausible model of pathological data would have to be able to adapt to the subject's individual presentation. Such a model would provide the means for a better understanding of the underlying biological processes and improve one's ability to define pathologically meaningful imaging biomarkers. With this aim in mind, this work proposes a hierarchical fully unsupervised model selection framework for neuroimaging data which enables the distinction between different types of abnormal image patterns without pathological a priori knowledge. Its application on simulated and clinical data demonstrated the ability to detect abnormal intensity clusters, resulting in a competitive to improved behavior in white matter lesion segmentation when compared to three other freely-available automated methods.
142 citations
Cites background or methods from "Automatic segmentation of cerebral ..."
...This solution is subject to some difficulties related to both the choice of an appropriate population to build the statistical atlases and the choice of a suitable coordinate mapping [25]....
[...]
...Finally, some methods avoid problems related to the registration of multiple acquisition sequences by using one unique acquisition sequence [25], [26]....
[...]
References
More filters
49,597 citations
TL;DR: An automated method for segmenting magnetic resonance head images into brain and non‐brain has been developed and described and examples of results and the results of extensive quantitative testing against “gold‐standard” hand segmentations, and two other popular automated methods.
Abstract: An automated method for segmenting magnetic resonance head images into brain and non-brain has been developed. It is very robust and accurate and has been tested on thousands of data sets from a wide variety of scanners and taken with a wide variety of MR sequences. The method, Brain Extraction Tool (BET), uses a deformable model that evolves to fit the brain's surface by the application of a set of locally adaptive model forces. The method is very fast and requires no preregistration or other pre-processing before being applied. We describe the new method and give examples of results and the results of extensive quantitative testing against "gold-standard" hand segmentations, and two other popular automated methods.
9,887 citations
"Automatic segmentation of cerebral ..." refers methods in this paper
...uk/fsl/bet2/) [31]; - bias field correction using FAST (FMRIB's automated segmentation tool, http://fsl....
[...]
TL;DR: The authors propose a novel hidden Markov random field (HMRF) model, which is a stochastic process generated by a MRF whose state sequence cannot be observed directly but which can be indirectly estimated through observations.
Abstract: The finite mixture (FM) model is the most commonly used model for statistical segmentation of brain magnetic resonance (MR) images because of its simple mathematical form and the piecewise constant nature of ideal brain MR images. However, being a histogram-based model, the FM has an intrinsic limitation-no spatial information is taken into account. This causes the FM model to work only on well-defined images with low levels of noise; unfortunately, this is often not the the case due to artifacts such as partial volume effect and bias field distortion. Under these conditions, FM model-based methods produce unreliable results. Here, the authors propose a novel hidden Markov random field (HMRF) model, which is a stochastic process generated by a MRF whose state sequence cannot be observed directly but which can be indirectly estimated through observations. Mathematically, it can be shown that the FM model is a degenerate version of the HMRF model. The advantage of the HMRF model derives from the way in which the spatial information is encoded through the mutual influences of neighboring sites. Although MRF modeling has been employed in MR image segmentation by other researchers, most reported methods are limited to using MRF as a general prior in an FM model-based approach. To fit the HMRF model, an EM algorithm is used. The authors show that by incorporating both the HMRF model and the EM algorithm into a HMRF-EM framework, an accurate and robust segmentation can be achieved. More importantly, the HMRF-EM framework can easily be combined with other techniques. As an example, the authors show how the bias field correction algorithm of Guillemaud and Brady (1997) can be incorporated into this framework to achieve a three-dimensional fully automated approach for brain MR image segmentation.
6,335 citations
TL;DR: The novelty of the approach is that it does not use a model selection criterion to choose one among a set of preestimated candidate models; instead, it seamlessly integrate estimation and model selection in a single algorithm.
Abstract: This paper proposes an unsupervised algorithm for learning a finite mixture model from multivariate data. The adjective "unsupervised" is justified by two properties of the algorithm: 1) it is capable of selecting the number of components and 2) unlike the standard expectation-maximization (EM) algorithm, it does not require careful initialization. The proposed method also avoids another drawback of EM for mixture fitting: the possibility of convergence toward a singular estimate at the boundary of the parameter space. The novelty of our approach is that we do not use a model selection criterion to choose one among a set of preestimated candidate models; instead, we seamlessly integrate estimation and model selection in a single algorithm. Our technique can be applied to any type of parametric mixture model for which it is possible to write an EM algorithm; in this paper, we illustrate it with experiments involving Gaussian mixtures. These experiments testify for the good performance of our approach.
2,182 citations
"Automatic segmentation of cerebral ..." refers background in this paper
...Converging to local minima is a wellknown limitation of the EM method [37]....
[...]
TL;DR: White matter hyperintensities indicate an increased risk of cerebrovascular events when identified as part of diagnostic investigations, and support their use as an intermediate marker in a research setting.
Abstract: Objectives To review the evidence for an association of white matter hyperintensities with risk of stroke, cognitive decline, dementia, and death.
Design Systematic review and meta-analysis.
Data sources PubMed from 1966 to 23 November 2009.
Study selection Prospective longitudinal studies that used magnetic resonance imaging and assessed the impact of white matter hyperintensities on risk of incident stroke, cognitive decline, dementia, and death, and, for the meta-analysis, studies that provided risk estimates for a categorical measure of white matter hyperintensities, assessing the impact of these lesions on risk of stroke, dementia, and death.
Data extraction Population studied, duration of follow-up, method used to measure white matter hyperintensities, definition of the outcome, and measure of the association of white matter hyperintensities with the outcome.
Data synthesis 46 longitudinal studies evaluated the association of white matter hyperintensities with risk of stroke (n=12), cognitive decline (n=19), dementia (n=17), and death (n=10). 22 studies could be included in a meta-analysis (nine of stroke, nine of dementia, eight of death). White matter hyperintensities were associated with an increased risk of stroke (hazard ratio 3.3, 95% confidence interval 2.6 to 4.4), dementia (1.9, 1.3 to 2.8), and death (2.0, 1.6 to 2.7). An association of white matter hyperintensities with a faster decline in global cognitive performance, executive function, and processing speed was also suggested.
Conclusion White matter hyperintensities predict an increased risk of stroke, dementia, and death. Therefore white matter hyperintensities indicate an increased risk of cerebrovascular events when identified as part of diagnostic investigations, and support their use as an intermediate marker in a research setting. Their discovery should prompt detailed screening for risk factors of stroke and dementia.
1,842 citations
"Automatic segmentation of cerebral ..." refers background in this paper
...They occur often in the elderly [2–5] and have been shown to predict an increased risk of stroke, cognitive decline and death [6]....
[...]