Automatic segmentation of cerebral white matter hyperintensities using only 3D FLAIR images

Simões, Rita; Mönninghoff, Christoph; Dlugaj, Martha; Weimar, Christian; Wanke, Isabel; Walsum, Anne‐Marie van Cappellen van; Slump, Cornelis H.

doi:10.1016/j.mri.2012.12.004

Cited by 52 publications

(40 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Simões and colleagues (2013) modeled the histogram of FLAIR intensities employing a Gaussian mixture model with three components: CSF, normal brain tissue, WMH. The traditional Expectation-Maximization algorithm was slightly modified by introducing a context-sensitive penalty term (Tang et al 2009): this way, at each iteration of the algorithm, the probability that a voxel belongs to a certain class depends not only on the voxel’s intensity, but also on its neighbors’ current class probabilities.…”

Section: Algorithms For Wmh Segmentationmentioning

confidence: 99%

“…Both Simoes and colleagues (2013) and Ong and colleagues (2012), by using a supervised and an unsupervised approach respectively, applied their method to the dataset used in the Medical Image Computing and Computer Aided Intervention Society’s MS Lesion Segmentation Challenge 2008 (Styner et al 2008), consisting of 23 FLAIR images acquired at the Children’s Hospital Boston and at the University of North Carolina. The challenge contemplated the evaluation of performances through four different metrics: relative absolute volume difference, average symmetric surface distance, true positive rate and false positive rate.…”

Section: Application In the Segmentation Of Ms Lesionsmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Detection of White Matter Hyperintensities in Healthy Aging and Pathology Using Magnetic Resonance Imaging: A Review

et al. 2015

View full text Add to dashboard Cite

White matter hyperintensities (WMH) are commonly seen in the brain of healthy elderly subjects and patients with several neurological and vascular disorders. A truly reliable and fully automated method for quantitative assessment of WMH on magnetic resonance imaging (MRI) has not yet been identified. In this paper, we review and compare the large number of automated approaches proposed for segmentation of WMH in the elderly and in patients with vascular risk factors. We conclude that, in order to avoid artifacts and exclude the several sources of bias that may influence the analysis, an optimal method should comprise a careful preprocessing of the images, be based on multimodal, complementary data, take into account spatial information about the lesions and correct for false positives. All these features should not exclude computational leanness and adaptability to available data.Electronic supplementary materialThe online version of this article (doi:10.1007/s12021-015-9260-y) contains supplementary material, which is available to authorized users.

show abstract

Section: Algorithms For Wmh Segmentationmentioning

confidence: 99%

Section: Application In the Segmentation Of Ms Lesionsmentioning

confidence: 99%

Automatic Detection of White Matter Hyperintensities in Healthy Aging and Pathology Using Magnetic Resonance Imaging: A Review

et al. 2015

View full text Add to dashboard Cite

show abstract

“…For 3D-FLAIR, there are many reports regarding application to multiple sclerosis. 5,6,[42][43][44][45][46][47][48][49][50][51][52][53][54] Smaller lesions can be detected by 3D-FLAIR than by 2D-FLAIR due to thinner slices and fewer flow artifacts with 3D-FLAIR. 45,46 Excellent detection of cortical lesions by 3D-FLAIR has also been reported (Fig.…”

Section: Clinical Applicationsmentioning

confidence: 99%

The Technical and Clinical Features of 3D-FLAIR in Neuroimaging

Naganawa

2015

magn reson med sci

View full text Add to dashboard Cite

In clinical MR neuroimaging, 3D fluid-attenuated inversion recovery (3D-FLAIR) with a variable-flip-angle turbo spin echo sequence is becoming popular. There are more than 100 reports regarding 3D-FLAIR in the PubMed database. In this article, the technical and clinical features of 3D-FLAIR for neuroimaging are reviewed and summarized. 3D-FLAIR allows thinner slices with multi-planar reformation capability, a higher flow sensitivity, high sensitivity to subtle T 1 changes in fluid, images without cerebrospinal fluid (CSF) inflow artifacts, and a 3D dataset compatible with computer-aided analysis. In addition, 3D-FLAIR can be obtained within a clinically reasonable scan time. It is important for radiologists to be familiar with the features of 3D-FLAIR and to provide useful information for patients.

show abstract

“…For example, Khayati et al [18] used 2D FLAIR images with low resolution and the partial volume effect reduced the accuracy of the segmentation results. More recently, Simões et al [6] developed an automatic segmentation using only 3D FLAIR images but required BET and FAST for the preprocessing and 3D Slicer for evaluation. To the best of our knowledge, our approach is the only integrated software tool using only 3D FLAIR images.…”

Section: Discussionmentioning

confidence: 99%

Automated White Matter Hyperintensity Detection in Multiple Sclerosis Using 3D T2 FLAIR

Zeng

Utriainen

Wang

et al. 2014

International Journal of Biomedical Imaging

View full text Add to dashboard Cite

White matter hyperintensities (WMH) seen on T2WI are a hallmark of multiple sclerosis (MS) as it indicates inflammation associated with the disease. Automatic detection of the WMH can be valuable in diagnosing and monitoring of treatment effectiveness. T2 fluid attenuated inversion recovery (FLAIR) MR images provided good contrast between the lesions and other tissue; however the signal intensity of gray matter tissue was close to the lesions in FLAIR images that may cause more false positives in the segment result. We developed and evaluated a tool for automated WMH detection only using high resolution 3D T2 fluid attenuated inversion recovery (FLAIR) MR images. We use a high spatial frequency suppression method to reduce the gray matter area signal intensity. We evaluate our method in 26 MS patients and 26 age matched health controls. The data from the automated algorithm showed good agreement with that from the manual segmentation. The linear correlation between these two approaches in comparing WMH volumes was found to be Y = 1.04X + 1.74 (R 2 = 0.96). The automated algorithm estimates the number, volume, and category of WMH.

show abstract

Automatic segmentation of cerebral white matter hyperintensities using only 3D FLAIR images

Cited by 52 publications

References 36 publications

Automatic Detection of White Matter Hyperintensities in Healthy Aging and Pathology Using Magnetic Resonance Imaging: A Review

Automatic Detection of White Matter Hyperintensities in Healthy Aging and Pathology Using Magnetic Resonance Imaging: A Review

The Technical and Clinical Features of 3D-FLAIR in Neuroimaging

Automated White Matter Hyperintensity Detection in Multiple Sclerosis Using 3D T2 FLAIR

Contact Info

Product

Resources

About