scholarly journals Auto-kNN: Brain Tissue Segmentation using Automatically Trained k-Nearest-Neighbor Classification

2013 ◽  
Author(s):  
Henri Vrooman ◽  
Fedde Van der Lijn ◽  
Wiro Niessen
Keyword(s):  
White Matter ◽  
Brain Tissue ◽  
Nearest Neighbor ◽  
White Matter Lesion ◽  
Lesion Detection ◽  
K Nearest Neighbor ◽  
Tissue Segmentation ◽  
Rigid Registration ◽  
Brain Tissue Segmentation ◽  
Skull Stripping

In this paper we applied one of our regularly used processing pipelines for fully automated brain tissue segmentation. Brain tissue was segmented in cerebrospinal fluid (CSF), gray matter (GM) and white matter (WM). Our algorithms for skull stripping, tissue segmentation and white matter lesion (WML) detection were slightly adapted and applied to twelve data sets within the MRBrainS13 brain tissue segmentation challenge. Skull stripping is performed using non-rigid registration of 5 atlas masks. Our tissue segmentation is based on an automatically trained kNN-classifier. Training samples were obtained by non-rigid registration of 5 manually labeled scans followed by a pruning step in feature space to remove any residual erroneously sampled tissue voxels. The kNN-classification incorporates voxel intensities from a T1-weighted scan and a FLAIR scan. The white matter lesion detection is based on an automatically determined threshold on the FLAIR scan. The application of the algorithms on the data from the MRBrainS13 Challenge showed that our pipeline produces acceptable segmentations. Average resulting Dice scores were 77.86 (CSF), 81.22 (GM), 87.27 (WM), 93.78 (total parenchyma), and 96.26 (all intracranial structures). Total processing time was about 2 hours per subject.

White matter lesion extension to automatic brain tissue segmentation on MRI

NeuroImage ◽  
2009 ◽  
Vol 45 (4) ◽  
pp. 1151-1161 ◽  
Author(s):  
Renske de Boer ◽  
Henri A. Vrooman ◽  
Fedde van der Lijn ◽  
Meike W. Vernooij ◽  
M. Arfan Ikram ◽  
...  
Keyword(s):  
White Matter ◽  
Brain Tissue ◽  
White Matter Lesion ◽  
Tissue Segmentation ◽  
Brain Tissue Segmentation ◽  
Lesion Extension

Multi-spectral brain tissue segmentation using automatically trained k-Nearest-Neighbor classification

NeuroImage ◽  
2007 ◽  
Vol 37 (1) ◽  
pp. 71-81 ◽  
Author(s):  
Henri A. Vrooman ◽  
Chris A. Cocosco ◽  
Fedde van der Lijn ◽  
Rik Stokking ◽  
M. Arfan Ikram ◽  
...  
Keyword(s):  
Brain Tissue ◽  
Nearest Neighbor ◽  
K Nearest Neighbor ◽  
Tissue Segmentation ◽  
Nearest Neighbor Classification ◽  
Brain Tissue Segmentation ◽  
Neighbor Classification

scholarly journals Accurate white matter lesion segmentation by k nearest neighbor classification with tissue type priors (kNN-TTPs)

2013 ◽  
Vol 3 ◽  
pp. 462-469 ◽  
Author(s):  
Martijn D. Steenwijk ◽  
Petra J.W. Pouwels ◽  
Marita Daams ◽  
Jan Willem van Dalen ◽  
Matthan W.A. Caan ◽  
...  
Keyword(s):  
White Matter ◽  
Nearest Neighbor ◽  
White Matter Lesion ◽  
Tissue Type ◽  
Lesion Segmentation ◽  
K Nearest Neighbor ◽  
Nearest Neighbor Classification ◽  
Neighbor Classification

scholarly journals Impacts of skull stripping on construction of three-dimensional T1-weighted imaging-based brain structural network in full-term neonates

2020 ◽  
Author(s):  
Geliang Wang ◽  
Yajie Hu ◽  
Xianjun Li ◽  
Miaomiao Wang ◽  
Congcong Liu ◽  
...  
Keyword(s):  
Brain Tissue ◽  
Full Term ◽  
Neonatal Brain ◽  
Tissue Segmentation ◽  
Term Neonates ◽  
Brain Extraction ◽  
Brain Tissue Segmentation ◽  
Skull Stripping ◽  
Structural Network ◽  
Manual Correction

Abstract Background: Skull stripping remains a challenge for neonatal brain MR image analysis. However, little is known about how accuracy of the skull stripping affects the neonatal brain tissue segmentation and subsequent network construction. This paper therefore aimed to clarify this issue by comparing two automatic (FSL’s Brain Extraction Tool, BET; Infant Brain Extraction and Analysis Toolbox, iBEAT) and a semiautomatic (iBEAT with manual correction) processes in constructing 3D T1-weighted imaging (T1WI)-based brain structural network. Methods: Twenty-two full-term neonates (gestational age, 37-42 weeks; boys/girls, 13/9) without abnormalities on MRI who underwent brain 3D T1WI were retrospectively recruited. Two automatic (BET and iBEAT) and a semiautomatic preprocessing (iBEAT with manual correction) workflows were separately used to perform the skull stripping. Brain tissue segmentation and volume calculation were performed by a John Hopkins atlas-based method. Sixty-four gray matter regions were selected as nodes; volume covariance network and its properties (clustering coefficient, C p ; characteristic path length, L p ; local efficiency, E local ; global efficiency, E global ) were calculated by GRETNA. Analysis of variance (ANOVA) was used to compare the differences in the calculated volumes between three workflows. Results: There were significant differences in volumes of 48 brain region between three workflows ( P <0.05). Three neonatal brain structural networks presented small-world topology. The semiautomatic workflow showed remarkably decreased C p , increased L p , decreased E local , and E global , in contrast to two automatic ones. Conclusions: Imperfect skull stripping indeed affected the accuracy of brain structural network in full-term neonates.

scholarly journals Impacts of skull stripping on construction of three-dimensional T1-weighted imaging-based brain structural network in full-term neonates

2020 ◽  
Author(s):  
Geliang Wang ◽  
Yajie Hu ◽  
Xianjun Li ◽  
Miaomiao Wang ◽  
Congcong Liu ◽  
...  
Keyword(s):  
Brain Tissue ◽  
Full Term ◽  
Neonatal Brain ◽  
Tissue Segmentation ◽  
Term Neonates ◽  
Brain Extraction ◽  
Brain Tissue Segmentation ◽  
Skull Stripping ◽  
Structural Network ◽  
Manual Correction

Abstract Background: Skull stripping remains a challenge for neonatal brain MR image analysis. However, little is known about how accuracy of the skull stripping affects the neonatal brain tissue segmentation and subsequent network construction. This paper therefore aimed to clarify this issue by comparing two automatic (FMRIB Software Library's Brain Extraction Tool, BET; Infant Brain Extraction and Analysis Toolbox, iBEAT) and a semiautomatic (iBEAT with manual correction) processes in constructing 3D T1-Weighted Imaging (T1WI)-based brain structural network. Methods: Twenty-two full-term neonates (gestational age, 37-42 weeks; boys/girls, 13/9) without abnormalities on MRI who underwent brain 3D T1WI were retrospectively recruited. Two automatic (BET and iBEAT) and a semiautomatic preprocessing (iBEAT with manual correction) workflows were separately used to perform the skull stripping. Brain tissue segmentation and volume calculation were performed by a John Hopkins atlas-based method. Sixty-four gray matter regions were selected as nodes; volume covariance network and its properties (clustering coefficient, C p ; characteristic path length, L p ; local efficiency, E local ; global efficiency, E global ) were calculated by GRETNA. Analysis of variance (ANOVA) was used to compare the differences in the calculated volume between three workflows. Results: There were significant differences in volumes of 50 brain regions between three workflows ( P <0.05). Three neonatal brain structural networks presented small-world topology. The semiautomatic workflow showed remarkably decreased C p , increased L p , decreased E local , and decreased E global , in contrast to two automatic ones. Conclusions: Imperfect skull stripping indeed affected the accuracy of brain structural network in full-term neonates.

scholarly journals Semi-Supervised Learning in Medical Image Segmentation: Brain Tissue with White Matter Hyperintensity Segmentation Using FLAIR Image

2021 ◽  
Author(s):  
ZunHyan Rieu ◽  
Donghyeon Kim ◽  
JeeYoung Kim ◽  
Regina EY Kim ◽  
Minho Lee ◽  
...  
Keyword(s):  
White Matter ◽  
Supervised Learning ◽  
Brain Tissue ◽  
Medical Image Segmentation ◽  
White Matter Hyperintensity ◽  
Learning Method ◽  
Brain Segmentation ◽  
Tissue Segmentation ◽  
Flair Image ◽  
Brain Tissue Segmentation

White matter hyperintensity (WMH) has been considered the primary biomarker from small-vessel cerebrovascular disease to Alzheimer&rsquo;s disease (AD) and has been reported for its correlation of brain structural changes. To perform WMH related analysis with brain structure, both T1-weighted (T1w) and (Fluid Attenuated Inversion Recovery(FLAIR) are required. However, in a clinical situation, it is limited to obtain 3D T1w and FLAIR images simultaneously. Also, the most of brain segmentation technique supports 3D T1w only. Therefore, we introduced the semi-supervised learning method that can perform brain segmentation using FLAIR image only. Our method achieved a dice overlap score of 0.86 for brain tissue segmentation on FLAIR, with the relative volume difference between T1w and FLAIR segmentation under 4.8%, which is just as reliable as the segmentation done by its paired T1w image. We believe our semi-supervised learning method has a great potential to be used to other MRI sequences and provide encouragement to people who seek brain tissue segmentation from a non-T1w image.

scholarly journals Impacts of skull stripping on construction of three-dimensional T1-weighted imaging-based brain structural network in full-term neonates

2020 ◽  
Author(s):  
Geliang Wang ◽  
Yajie Hu ◽  
Xianjun Li ◽  
Miaomiao Wang ◽  
Congcong Liu ◽  
...  
Keyword(s):  
Brain Tissue ◽  
Full Term ◽  
Neonatal Brain ◽  
Tissue Segmentation ◽  
Term Neonates ◽  
Brain Extraction ◽  
Brain Tissue Segmentation ◽  
Skull Stripping ◽  
Structural Network ◽  
Manual Correction

Abstract Background: Skull stripping remains a challenge for neonatal brain MR image analysis. However, little is known about how accuracy of the skull stripping affects the neonatal brain tissue segmentation and subsequent network construction. This paper therefore aimed to clarify this issue by comparing two automatic (FMRIB Software Library's Brain Extraction Tool, BET; Infant Brain Extraction and Analysis Toolbox, iBEAT) and a semiautomatic (iBEAT with manual correction) processes in constructing 3D T1-Weighted Imaging (T1WI)-based brain structural network. Methods: Twenty-two full-term neonates (gestational age, 37-42 weeks; boys/girls, 13/9) without abnormalities on MRI who underwent brain 3D T1WI were retrospectively recruited. Two automatic (BET and iBEAT) and a semiautomatic preprocessing (iBEAT with manual correction) workflows were separately used to perform the skull stripping. Brain tissue segmentation and volume calculation were performed by a John Hopkins atlas-based method. Sixty-four gray matter regions were selected as nodes; volume covariance network and its properties (clustering coefficient, C p ; characteristic path length, L p ; local efficiency, E local ; global efficiency, E global ) were calculated by GRETNA. Analysis of variance (ANOVA) was used to compare the differences in the calculated volume between three workflows. Results: There were significant differences in volumes of 50 brain regions between three workflows ( P <0.05). Three neonatal brain structural networks presented small-world topology. The semiautomatic workflow showed remarkably decreased C p , increased L p , decreased E local , and decreased E global , in contrast to two automatic ones. Conclusions: Imperfect skull stripping indeed affected the accuracy of brain structural network in full-term neonates.

Sign in / Sign up

Export Citation Format

Share Document