Brain Tissue Segmentation Method Research Articles

Minimizing the effect of white matter lesions on deep learning based tissue segmentation for brain volumetry.

Automated methods for segmentation-based brain volumetry may be confounded by the presence of white matter (WM) lesions, which introduce abnormal intensities that can alter the classification of not only neighboring but also distant brain tissue. These lesions are common in pathologies where brain volumetry is also an important prognostic marker, such as in multiple sclerosis (MS), and thus reducing their effects is critical for improving volumetric accuracy and reliability. In this work, we analyze the effect of WM lesions on deep learning based brain tissue segmentation methods for brain volumetry and introduce techniques to reduce the error these lesions produce on the measured volumes. We propose a 3D patch-based deep learning framework for brain tissue segmentation which is trained on the outputs of a reference classical method. To deal more robustly with pathological cases having WM lesions, we use a combination of small patches and a percentile-based input normalization. To minimize the effect of WM lesions, we also propose a multi-task double U-Net architecture performing end-to-end inpainting and segmentation, along with a training data generation procedure. In the evaluation, we first analyze the error introduced by artificial WM lesions on our framework as well as in the reference segmentation method without the use of lesion inpainting techniques. To the best of our knowledge, this is the first analysis of WM lesion effect on a deep learning based tissue segmentation approach for brain volumetry. The proposed framework shows a significantly smaller and more localized error introduced by WM lesions than the reference segmentation method, that displays much larger global differences. We also evaluated the proposed lesion effect minimization technique by comparing the measured volumes before and after introducing artificial WM lesions to healthy images. The proposed approach performing end-to-end inpainting and segmentation effectively reduces the error introduced by small and large WM lesions in the resulting volumetry, obtaining absolute volume differences of 0.01 ± 0.03% for GM and 0.02 ± 0.04% for WM. Increasing the accuracy and reliability of automated brain volumetry methods will reduce the sample size needed to establish meaningful correlations in clinical studies and allow its use in individualized assessments as a diagnostic and prognostic marker for neurodegenerative pathologies.

An automatic self‐initialized clustering method for brain tissue segmentation and pathology detection from magnetic resonance human head scans with graphics processing unit machine

AbstractThe proposed work introduces a fully automatic modified fuzzy c‐means (MFCM) algorithm for segmenting brain tissue into gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) which identifies the pathological conditions of magnetic resonance human head scans. The present work implements histogram smoothing using Gaussian distribution for finding the number of clusters (K) and cluster centers (C) to initialize modified FCM algorithm (MFCM). The modification includes the local impact of each pixel based on the median of local neighborhoods. This needs more computational power to reduce the processing time and requires a parallel programming environment like the Graphics Processing Unit. The parallel MFCM is performed with the help of compute unified device architecture language and reduced the processing time up to 80 speedup folds than the serial implementation in Matlab and 20 speedup folds than C programming implementation. The method is examined with the Internet Brain Segmentation Repository (IBSR20) T1W dataset. The quantitative and qualitative results of the proposed method are compared with state‐of‐the‐art‐methods using the Dice coefficient (DC). Proposed method yields high DC 0.84 ± 0.03 for GM, 0.83 ± 0.04 for WM, and 0.41 ± 0.12 for CSF segmentation. In post‐processing, 3D volumes of segmented regions have been constructed and compared with the gold standard quantitatively and qualitatively.

Brain tissue segmentation method based on maximum between-cluster variance optimized by the difference search algorithm

Objective To study a maximum between-cluster variance based on differential search algorithm, and to select the multi-threshold for effectively segmentation of brain magnetic resonance images. Methods The brain extraction tool(BET) algorithm was used to remove the non-brain tissue part of the original magnetic resonance image. The best-fit with coalescing(BFC) algorithm was used to remove the intensity non-uniformity. The differential search algorithm was used to optimize the maximum between-cluster variance of the image to find the optimal threshold for multi-threshold segmentation of the magnetic resonance image. The method was validated using simulated magnetic resonance(MR) brain image data provided by BrainWeb. Results For MR images with different noise levels and intensity inhomogeneities, the proposed method was better than FSL, SPM and Brainsuite methods. Conclusions The maximum between-cluster variance based on differential search algorithm has better segmentation accuracy and robustness, especially for cerebrospinal fluid. Key words: Magnetic resonance imaging; Differential search; Image segmentation; Multi threshold; OTSU

Histogram Based Multimodal Minimum Cross Entropy Thresholding Method for Magnetic Resonance Brain Tissue Segmentation

Histogram Based Multimodal Minimum Cross Entropy Thresholding Method for Magnetic Resonance Brain Tissue Segmentation

Application of single- and dual-energy CT brain tissue segmentation to PET monitoring of proton therapy

The purpose of this work was to evaluate the ability of single and dual energy computed tomography (SECT, DECT) to estimate tissue composition and density for usage in Monte Carlo (MC) simulations of irradiation induced β+ activity distributions. This was done to assess the impact on positron emission tomography (PET) range verification in proton therapy.A DECT-based brain tissue segmentation method was developed for white matter (WM), grey matter (GM) and cerebrospinal fluid (CSF). The elemental composition of reference tissues was assigned to closest CT numbers in DECT space (DECTdist). The method was also applied to SECT data (SECTdist). In a validation experiment, the proton irradiation induced PET activity of three brain equivalent solutions (BES) was compared to simulations based on different tissue segmentations. Five patients scanned with a dual source DECT scanner were analyzed to compare the different segmentation methods. A single magnetic resonance (MR) scan was used for comparison with an established segmentation toolkit. Additionally, one patient with SECT and post-treatment PET scans was investigated.For BES, DECTdist and SECTdist reduced differences to the reference simulation by up to 62% when compared to the conventional stoichiometric segmentation (SECTSchneider). In comparison to MR brain segmentation, Dice similarity coefficients for WM, GM and CSF were 0.61, 0.67 and 0.66 for DECTdist and 0.54, 0.41 and 0.66 for SECTdist. MC simulations of PET treatment verification in patients showed important differences between DECTdist/SECTdist and SECTSchneider for patients with large CSF areas within the treatment field but not in WM and GM. Differences could be misinterpreted as PET derived range shifts of up to 4 mm. DECTdist and SECTdist yielded comparable activity distributions, and comparison of SECTdist to a measured patient PET scan showed improved agreement when compared to SECTSchneider.The agreement between predicted and measured PET activity distributions was improved by employing a brain specific segmentation applicable to both DECT and SECT data.

State-of-the-Art Methods for Brain Tissue Segmentation: A Review.

Brain tissue segmentation is one of the most sought after research areas in medical image processing. It provides detailed quantitative brain analysis for accurate disease diagnosis, detection, and classification of abnormalities. It plays an essential role in discriminating healthy tissues from lesion tissues. Therefore, accurate disease diagnosis and treatment planning depend merely on the performance of the segmentation method used. In this review, we have studied the recent advances in brain tissue segmentation methods and their state-of-the-art in neuroscience research. The review also highlights the major challenges faced during tissue segmentation of the brain. An effective comparison is made among state-of-the-art brain tissue segmentation methods. Moreover, a study of some of the validation measures to evaluate different segmentation methods is also discussed. The brain tissue segmentation, content in terms of methodologies, and experiments presented in this review are encouraging enough to attract researchers working in this field.

Unsupervised tissue classification of brain MR images for voxel-based morphometry analysis

In this article, a fully unsupervised method for brain tissue segmentation of T1-weighted MRI 3D volumes is proposed. The method uses the Fuzzy C-Means (FCM) clustering algorithm and a Fully Connected Cascade Neural Network (FCCNN) classifier. Traditional manual segmentation methods require neuro-radiological expertise and significant time while semiautomatic methods depend on parameter's setup and trial-and-error methodologies that may lead to high intraoperator/interoperator variability. The proposed method selects the most useful MRI data according to FCM fuzziness values and trains the FCCNN to learn to classify brain’ tissues into White Matter, Gray Matter, and Cerebro-Spinal Fluid in an unsupervised way. The method has been tested on the IBSR dataset, on the BrainWeb Phantom, on the BrainWeb SBD dataset, and on the real dataset “University of Palermo Policlinico Hospital” (UPPH), Italy. Sensitivity, Specificity, Dice and F-Factor scores have been calculated on the IBSR and BrainWeb datasets segmented using the proposed method, the FCM algorithm, and two state-of-the-art brain segmentation software packages (FSL and SPM) to prove the effectiveness of the proposed approach. A qualitative evaluation involving a group of five expert radiologists has been performed segmenting the real dataset using the proposed approach and the comparison algorithms. Finally, a usability analysis on the proposed method and reference methods has been carried out from the same group of expert radiologists. The achieved results show that the segmentations of the proposed method are comparable or better than the reference methods with a better usability and degree of acceptance.

Automatic method for white matter lesion segmentation based on T1‐fluid‐attenuated inversion recovery images

The authors propose a fast and effective solution for automatic segmentation of white matter lesions by using T1 and fluid‐attenuated inversion recovery (FLAIR) image modalities with no need for manual segmentation and atlas registration. Initially, a brain tissue segmentation method is used to segment the T1 image into cerebrospinal fluid (CSF), grey matter and white matter. Based on the obtained tissue segmentation results, the region of interest (ROI) of the FLAIR image is created by subtracting the CSF from the FLAIR image. Subsequently, the authors calculate the z‐score of the intensities in the ROI and define a threshold to perform a preliminary identification of abnormalities from normal tissues. The abnormalities obtained at this stage are used as the prior knowledge for the modified level‐set technique. The proposed level set method here is applied based on local Gaussian distribution to precisely detect the boundaries of the white matter lesions in the ROI. The level set method based on local Gaussian distribution fitting energy is robust to the intensity inhomogeneity of MR data and therefore capable of precisely extracting the boundaries of white matter lesions. Experimental analysis and quantitative comparisons with the peak‐seeking and state‐of‐the‐art white matter lesion segmentation (WMLS) techniques demonstrate that the algorithm is a stable and effective approach which significantly outperforms other trusted solutions for white matter lesion segmentation.

Evaluating the effects of white matter multiple sclerosis lesions on the volume estimation of 6 brain tissue segmentation methods.

The accuracy of automatic tissue segmentation methods can be affected by the presence of hypointense white matter lesions during the tissue segmentation process. Our aim was to evaluate the impact of MS white matter lesions on the brain tissue measurements of 6 well-known segmentation techniques. These include straightforward techniques such as Artificial Neural Network and fuzzy C-means as well as more advanced techniques such as the Fuzzy And Noise Tolerant Adaptive Segmentation Method, fMRI of the Brain Automated Segmentation Tool, SPM5, and SPM8. Thirty T1-weighted images from patients with MS from 3 different scanners were segmented twice, first including white matter lesions and then masking the lesions before segmentation and relabeling as WM afterward. The differences in total tissue volume and tissue volume outside the lesion regions were computed between the images by using the 2 methodologies. Total gray matter volume was overestimated by all methods when lesion volume increased. The tissue volume outside the lesion regions was also affected by white matter lesions with differences up to 20 cm(3) on images with a high lesion load (≈50 cm(3)). SPM8 and Fuzzy And Noise Tolerant Adaptive Segmentation Method were the methods less influenced by white matter lesions, whereas the effect of white matter lesions was more prominent on fuzzy C-means and the fMRI of the Brain Automated Segmentation Tool. Although lesions were removed after segmentation to avoid their impact on tissue segmentation, the methods still overestimated GM tissue in most cases. This finding is especially relevant because on images with high lesion load, this bias will most likely distort actual tissue atrophy measurements.

Comparison of 10 brain tissue segmentation methods using revisited IBSR annotations

Ground-truth annotations from the well-known Internet Brain Segmentation Repository (IBSR) datasets consider Sulcal cerebrospinal fluid (SCSF) voxels as gray matter. This can lead to bias when evaluating the performance of tissue segmentation methods. In this work we compare the accuracy of 10 brain tissue segmentation methods analyzing the effects of SCSF ground-truth voxels on accuracy estimations. The set of methods is composed by FAST, SPM5, SPM8, GAMIXTURE, ANN, FCM, KNN, SVPASEG, FANTASM, and PVC. Methods are evaluated using original IBSR ground-truth and ranked by means of their performance on pairwise comparisons using permutation tests. Afterward, the evaluation is repeated using IBSR ground-truth without considering SCSF. The Dice coefficient of all methods is affected by changes in SCSF annotations, especially on SPM5, SPM8 and FAST. When not considering SCSF voxels, SVPASEG (0.90 ± 0.01) and SPM8 (0.91 ± 0.01) are the methods from our study that appear more suitable for gray matter tissue segmentation, while FAST (0.89 ± 0.02) is the best tool for segmenting white matter tissue. The performance and the accuracy of methods on IBSR images vary notably when not considering SCSF voxels. The fact that three of the most common methods (FAST, SPM5, and SPM8) report an important change in their accuracy suggest to consider these differences in labeling for new comparative studies.

Subject Specific Sparse Dictionary Learning for Atlas based Brain MRI Segmentation.

Quantitative measurements from segmentations of soft tissues from magnetic resonance images (MRI) of human brains provide important biomarkers for normal aging, as well as disease progression. In this paper, we propose a patch-based tissue classification method from MR images using sparse dictionary learning from an atlas. Unlike most atlas-based classification methods, deformable registration from the atlas to the subject is not required. An "atlas" consists of an MR image, its tissue probabilities, and the hard segmentation. The "subject" consists of the MR image and the corresponding affine registered atlas probabilities (or priors). A subject specific patch dictionary is created by learning relevant patches from the atlas. Then the subject patches are modeled as sparse combinations of learned atlas patches. The same sparse combination is applied to the segmentation patches of the atlas to generate tissue memberships of the subject. The novel combination of prior probabilities in the example patches enables us to distinguish tissues having similar intensities but having different spatial location. We show that our method outperforms two state-of-the-art whole brain tissue segmentation methods. We experimented on 12 subjects having manual tissue delineations, obtaining mean Dice coefficients of 0:91 and 0:87 for cortical gray matter and cerebral white matter, respectively. In addition, experiments on subjects with ventriculomegaly shows significantly better segmentation using our approach than the competing methods.

Multi-Atlas-based Segmentation with Hierarchical Max-Flow

This study investigates a method for brain tissue segmentation from 3D T1 weighted (T1w) MR images via convex relaxation with a hierarchical ordering constraint. It employs a multi-atlas-based initialization from 5 training images and is tested on 12 T1w MR images provided by the MICCAI 2013 MRBrainS segmentation challenge. The registered atlas images, fully segmented into eight different brain structures, are used to formulate shape and intensity priors for a Maximum A-Posteriori (MAP) energy that is subsequently minimized with a dual hierarchical max-flow computation. The algorithm makes use of a hierarchical label ordering constraint to regularize label families individually and its inherently globally optimal results guarantee robust segmentations. Major parts of the image processing pipeline are implemented using General-Purpose Programming on Graphics Processing Units (GPGPU) for a substantial increase in computation speed.

Application of Quantitative MRI for Brain Tissue Segmentation at 1.5 T and 3.0 T Field Strengths

BackgroundBrain tissue segmentation of white matter (WM), grey matter (GM), and cerebrospinal fluid (CSF) are important in neuroradiological applications. Quantitative Mri (qMRI) allows segmentation based on physical tissue properties, and the dependencies on MR scanner settings are removed. Brain tissue groups into clusters in the three dimensional space formed by the qMRI parameters R1, R2 and PD, and partial volume voxels are intermediate in this space. The qMRI parameters, however, depend on the main magnetic field strength. Therefore, longitudinal studies can be seriously limited by system upgrades. The aim of this work was to apply one recently described brain tissue segmentation method, based on qMRI, at both 1.5 T and 3.0 T field strengths, and to investigate similarities and differences.MethodsIn vivo qMRI measurements were performed on 10 healthy subjects using both 1.5 T and 3.0 T MR scanners. The brain tissue segmentation method was applied for both 1.5 T and 3.0 T and volumes of WM, GM, CSF and brain parenchymal fraction (BPF) were calculated on both field strengths. Repeatability was calculated for each scanner and a General Linear Model was used to examine the effect of field strength. Voxel-wise t-tests were also performed to evaluate regional differences.ResultsStatistically significant differences were found between 1.5 T and 3.0 T for WM, GM, CSF and BPF (p<0.001). Analyses of main effects showed that WM was underestimated, while GM and CSF were overestimated on 1.5 T compared to 3.0 T. The mean differences between 1.5 T and 3.0 T were -66 mL WM, 40 mL GM, 29 mL CSF and -1.99% BPF. Voxel-wise t-tests revealed regional differences of WM and GM in deep brain structures, cerebellum and brain stem.ConclusionsMost of the brain was identically classified at the two field strengths, although some regional differences were observed.

A Hybrid hierarchical approach for brain tissue segmentation by combining brain Atlas and least square support vector machine

In this paper, we present a new semi-automatic brain tissue segmentation method based on a hybrid hierarchical approach that combines a brain atlas as a priori information and a least-square support vector machine (LS-SVM). The method consists of three steps. In the first two steps, the skull is removed and the cerebrospinal fluid (CSF) is extracted. These two steps are performed using the toolbox FMRIB's automated segmentation tool integrated in the FSL software (FSL-FAST) developed in Oxford Centre for functional MRI of the brain (FMRIB). Then, in the third step, the LS-SVM is used to segment grey matter (GM) and white matter (WM). The training samples for LS-SVM are selected from the registered brain atlas. The voxel intensities and spatial positions are selected as the two feature groups for training and test. SVM as a powerful discriminator is able to handle nonlinear classification problems; however, it cannot provide posterior probability. Thus, we use a sigmoid function to map the SVM output into probabilities. The proposed method is used to segment CSF, GM and WM from the simulated magnetic resonance imaging (MRI) using Brainweb MRI simulator and real data provided by Internet Brain Segmentation Repository. The semi-automatically segmented brain tissues were evaluated by comparing to the corresponding ground truth. The Dice and Jaccard similarity coefficients, sensitivity and specificity were calculated for the quantitative validation of the results. The quantitative results show that the proposed method segments brain tissues accurately with respect to corresponding ground truth.

Partial volume estimation and segmentation of brain tissue based on diffusion tensor MRI

Brain tissue segmentation based on diffusion tensor magnetic resonance imaging (DT-MRI) data has been attempted by previous researchers. Due to inherent low spatial resolution of DT-MRI data, conventional methods suffered from partial volume averaging among the different types of tissues, which may result in inaccurate segmentation results. The purpose was to develop a new brain tissue segmentation method for DT-MRI data in which effect of the partial volume averaging is taken into account. The method estimates the partial volume fractions of white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) within each voxel using a maximum a posteriori probability principle, based on five DT parameters (three eigenvalues, apparent diffusion coefficient, and fractional anisotropy). The authors evaluated the performance of the proposed method quantitatively by using digital phantom data. Moreover, the authors applied the method to real DT-MRI data of the human brain, and compared the results with those of a conventional segmentation method. In the digital phantom experiments, the root mean square error in term of partial volume fraction with the method for WM, GM, and CSF were 0.137, 0.049, and 0.085, respectively. The volume overlap measures between the segmentation results and the ground truth of the digital phantom were more than 0.9 in all three tissue types, while those between the results by the conventional method and the ground truth ranged between 0.550 and 0.854. In visual comparisons for real DT-MRI, WM/GM/CSF regions estimated by the method were more similar to the corresponding regions depicted in the structural image than those estimated by the conventional method. The results of the digital phantom experiment and real DT-MRI data demonstrated that the method improved accuracy in estimation and segmentation of brain tissue on DT-MRI data over the conventional method. This method may be useful in evaluating the cortical and subcortical diffusivity in neurological diseases.

Accuracy and reproducibility study of automatic MRI brain tissue segmentation methods

The ability to study changes in brain morphometry in longitudinal studies majorly depends on the accuracy and reproducibility of the brain tissue quantification. We evaluate the accuracy and reproducibility of four previously proposed automatic brain tissue segmentation methods: FAST, SPM5, an automatically trained k-nearest neighbor (kNN) classifier, and a conventional kNN classifier based on a prior training set. The intensity nonuniformity correction and skull-stripping mask were the same for all methods. Evaluations were performed on MRI scans of elderly subjects derived from the general population. Accuracy was evaluated by comparison to two manual segmentations of MRI scans of six subjects (mean age 65.9±4.4years). Reproducibility was assessed by comparing the automatic segmentations of 30 subjects (mean age 57.0±3.7years) who were scanned twice within a short time interval. All methods showed good accuracy and reproducibility, with only small differences between methods. The conventional kNN classifier was the most accurate method with similarity indices of 0.82/0.90/0.94 for cerebrospinal fluid/gray matter/white matter, but it showed the lowest reproducibility. FAST yielded the most reproducible segmentation volumes with volume difference standard deviations of 0.55/0.49/0.38 (percentage of intracranial volume) respectively. The results of the reproducibility experiment can be used to calculate the required number of subjects in the design of a longitudinal study with sufficient power to detect changes over time in brain (tissue) volume. Example sample size calculations demonstrate a rather large effect of the choice of segmentation method on the required number of subjects.

White matter lesion extension to automatic brain tissue segmentation on MRI

A fully automated brain tissue segmentation method is optimized and extended with white matter lesion segmentation. Cerebrospinal fluid (CSF), gray matter (GM) and white matter (WM) are segmented by an atlas-based k-nearest neighbor classifier on multi-modal magnetic resonance imaging data. This classifier is trained by registering brain atlases to the subject. The resulting GM segmentation is used to automatically find a white matter lesion (WML) threshold in a fluid-attenuated inversion recovery scan. False positive lesions are removed by ensuring that the lesions are within the white matter. The method was visually validated on a set of 209 subjects. No segmentation errors were found in 98% of the brain tissue segmentations and 97% of the WML segmentations. A quantitative evaluation using manual segmentations was performed on a subset of 6 subjects for CSF, GM and WM segmentation and an additional 14 for the WML segmentations. The results indicated that the automatic segmentation accuracy is close to the interobserver variability of manual segmentations.

Regularized fuzzy c-means method for brain tissue clustering

This paper presents a regularized fuzzy c-means clustering method for brain tissue segmentation from magnetic resonance images. A regularizer of the total variation type is explored and a method to estimate the regularization parameter is proposed.

Improved image co-registration technique based on mutual information: application to pre- and post-operative brain SPECT

We propose a multimodal free-form registration algorithm based on maximization of mutual information. The warped image is modeled as a viscous fluid that deforms under the influence of forces derived from the gradient of the mutual information registration criterion. Parzen windowing is used to estimate the joint intensity probability of the images to be matched. The method is evaluated for non-rigid inter-subject registration of MR brain images. The accuracy of the method is verified using simulated multi-modal MR images with known ground truth deformation. The results show that the root mean square difference between the recovered and the ground truth deformation is smaller than 1 voxel. We illustrate the application of the method for atlas-based brain tissue segmentation in MR images in case of gross morphological differences between atlas and patient images.

A viscous fluid model for multimodal non-rigid image registration using mutual information

We propose a multimodal free-form registration algorithm based on maximization of mutual information. The warped image is modeled as a viscous fluid that deforms under the influence of forces derived from the gradient of the mutual information registration criterion. Parzen windowing is used to estimate the joint intensity probability of the images to be matched. The method is evaluated for non-rigid inter-subject registration of MR brain images. The accuracy of the method is verified using simulated multi-modal MR images with known ground truth deformation. The results show that the root mean square difference between the recovered and the ground truth deformation is smaller than 1 voxel. We illustrate the application of the method for atlas-based brain tissue segmentation in MR images in case of gross morphological differences between atlas and patient images.