Automatic Tissue Segmentation Research Articles

Automated atrophy assessment for Alzheimer's disease diagnosis from brain MRI images

An inventive scheme for automated tissue segmentation and classification is offered in this paper using Fast Discrete Wavelet Transform (DWT)/Band Expansion Process (BEP), Kernel-based least squares Support Vector Machine (KLS-SVM) and F-score, backed by Principal Component Analysis (PCA). Using input as T1, T2 and Proton Density (PD) scans of patients, CSF (Cerebrospinal Fluid), WM (White matter) and GM (Gray matter) are afforded as output, which act as hallmark for brain atrophy and thus sustaining in diagnosis of Alzheimer's disease (AD) from Mild Cognitive Impairment (MCI) and Healthy Controls (HC). The blending of BEP features from DWT and texture features from Gray Level Co-occurrence Matrix (GLC) promises to be a savior in atrophy revelation of the segmented tissues. Data used for evaluation of this study is taken from the ADNI database that encloses T1-weighted s-MRI (Structural Magnetic Imaging Resonance) scans of 158 patients with AD and 145 HC. Preprocessing steps unearthed five parameters for classification (i.e. cortical thickness, curvature, gray matter volume, surface area, and sulcal depth), in the preliminary step. For challenging the classifier performance, ROC (Receiver operating characteristics) curves are painted and the SVM classifiers of two-dimensional spaces took the top two important features as classification features for separating HC and AD to the maximum extent. The final results revealed that Fast DWT + F-Score + PCA + KLS-SVM + Poly Kernel is giving 100% tissue classification accuracy for test samples under consideration with only 7 input features.

Morphological Area Gradient: System-independent Dense Tissue Segmentation in Mammography Images.

Breast density has been identified as one of the strongest risk factors for breast cancer. However, the development of reliable and reproducible methods for the automatic dense tissue segmentation has been an important challenge. Due to the complexity of the acquisition process of mammography images, current approaches need to be calibrated for specific mammographic systems or require access to raw mammograms. In this work, we introduce the Morphological Area Gradient (MAG) as a generic measure for mammography images. MAG is generic in the sense that it does not need calibration or access to raw mammograms. At the core of MAG is the derivative of the area of segmented tissue with respect to the pixel intensity. We have found that the high-density regions can be automatically segmented by minimizing the MAG of a mammogram. To verify the performance of MAG, we collected 566 full-field digital mammograms using two different medical devices and a human expert manually annotated the high-density regions in each image. The proposed MAG method yields a median absolute error of 7.6% and a Dices similarity coefficient of 0.83, which are superior to other clinically validated state-of-the-art algorithms.

Computer-assisted image analysis of the tumor microenvironment on an oral tongue squamous cell carcinoma tissue microarray

Oral tongue squamous cell carcinoma (OTSCC) displays variable levels of immune cells within the tumor microenvironment. The quantity and localization of tumor infiltrating lymphocytes (TILs), specific functional TIL subsets (e.g., CD8+), and biomarker-expressing cells (e.g., PD-L1+) may have prognostic and predictive value. The purpose of this study was to evaluate the robustness and utility of computer-assisted image analysis tools to quantify and localize immunohistochemistry-based biomarkers within the tumor microenvironment on a tissue microarray (TMA). We stained a 91-patient OTSCC TMA with antibodies targeting CD3, CD4, CD8, FOXP3, IDO, and PD-L1. Cell populations were segmented into epithelial (tumor) or stromal compartments according to a mask derived from a pan-cytokeratin stain. Definiens Tissue Studio was used to enumerate marker-positive cells or to quantify the staining intensity. Automated methods were validated against manual tissue segmentation, cell count, and stain intensity quantification. Univariate associations of cell count and stain intensity with smoking status, stage, overall survival (OS), and disease-free survival (DFS) were determined. Our results revealed that the accuracy of automated tissue segmentation was dependent on the distance of the tissue section from the cytokeratin mask and the proportion of the tissue containing tumor vs. stroma. Automated and manual cell counts and stain intensities were highly correlated (Pearson coefficient range: 0.46–0.90; p < 0.001). Within this OTSCC cohort, smokers had significantly stronger PD-L1 stain intensity and higher numbers of CD3+, CD4+ and FOXP3+ TILs. In the subset of patients who had received adjuvant radiotherapy, a higher number of CD8+ TILs was associated with inferior OS and DFS. Taken together, this proof-of-principle study demonstrates the robustness and utility of computer-assisted image analysis for high-throughput assessment of multiple IHC markers on TMAs, with potential implications for studies on prognostic and predictive biomarkers.

Multiseg pipeline: automatic tissue segmentation of brain MR images with subject-specific atlases.

Automated segmentation and labeling of individual brain anatomical regions is challenging due to individual structural variability. Although, atlas-based segmentation has shown its potential for both tissue and structure segmentation, the inherent natural variability as well as disease-related changes in MR appearance is often inappropriately represented by a single atlas image. In order to have a more accurate representation, several atlases may be used for the segmentation task in a given neuroimaging study. In this paper, we present the MultisegPipeline, it uses multiple atlases that have been visually inspected and capture the expected variability in a neonatal population. The MultisegPipeline transfers the labeled regions from each atlas to the target image using deformable registration (ANTs1 or QuickSilver2 is available for this task). Additionally, the set of labels are merged using a label fusion technique that reduces the errors produced by the registration. The final output is a single label map that combines the results produced by all atlases into a consensus solution. In our study, the MultisegPipeline is used to segment brain MR images from 31 infants, a leave-one-out strategy was used to test our framework. The average dice score coefficient was 0.89.

Multispectral Fluorescence Imaging Allows for Distinctive Topographic Assessment and Subclassification of Tumor-Infiltrating and Surrounding Immune Cells.

Histomorphology has significantly changed over the last decades due to technological achievements in immunohistochemistry (IHC) for the visualization of specific proteins and in molecular pathology, particularly in the field of in situ hybridization of small oligonucleotides and amplification of DNA and RNA amplicons. With an increased availability of suitable methods, the demands regarding the observer of histomorphological slides were the supply of complex quantitative data as well as more information about protein expression and cell-cell interactions in tissue sections. Advances in fluorescence-based multiplexed IHC techniques, such as multispectral imaging (MSI), allow the quantification of multiple proteins at the same tissue section. In histopathology, it is a well-known technique for over a decade yet harboring serious problems concerning quantitative preciseness and tissue autofluorescence of multicolor staining when using formalin-fixed, paraffin-embedded (FFPE) tissue specimen. In recent years, milestones in tissue preparation, fluorescent dyes, hardware imaging, and software analysis were achieved including automated tissue segmentation (e.g., tumor vs. stroma) as well as in cellular and subcellular multiparameter analysis.This chapter covers the role that MSI plays in anatomic pathology for the analysis of FFPE tissue sections, discusses the technical aspects of MSI, and provides a review of its application in the characterization of immune cell infiltrates and beyond regarding its prognostic and predictive value and its use for guidance of clinical decisions for immunotherapeutic strategies.

MultisegPipeline: Automatic tissue segmentation of brain MR images with subject-specific atlases

MultisegPipeline: Automatic tissue segmentation of brain MR images with subject-specific atlases

Fully automated tissue segmentation of the prescription isodose region delineated through the Gamma knife plan for cerebral arteriovenous malformation (AVM) using fuzzy C-means (FCM) clustering.

BackgroundGamma knife radiosurgery (GKRS) is a common treatment for cerebral arterio-venous malformations (AVMs), particularly in cases where the malformation is deep-seated, large, or in eloquent areas of the brain. Unfortunately, these procedures can result in radiation injury to brain parenchyma. The fact that every AVM is unique in its vascular morphology makes it nearly impossible to exclude brain parenchyma from isodose radiation exposure during the formulation of a GKRS plan. Calculating the percentages of the various forms of tissue exposed to specific doses of radiation is crucial to understanding the clinical responses and causes of brain parenchyma injury following GKRS for AVM.MethodsIn this study, we developed a fully automated algorithm using unsupervised classification via fuzzy c-means clustering for the analysis of T2 weighted images used in a Gamma knife plan. This algorithm is able to calculate the percentages of nidus, brain tissue, and cerebrospinal fluid (CSF) within the prescription isodose radiation exposure region.ResultsThe proposed algorithm was used to assess the treatment plan of 25 patients with AVM who had undergone GKRS. The Dice similarity index (SI) was used to determine the degree of agreement between the results obtained using the algorithm and a visually guided manual method (the gold standard) performed by an experienced neurosurgeon. In the nidus, the SI was (74.86 ± 1.30%) (mean ± standard deviation), the sensitivity was (83.05 ± 11.91)%, and the specificity was (86.73 ± 10.31)%. In brain tissue, the SI was (79.50 ± 6.01)%, the sensitivity was (73.05 ± 9.77)%, and the specificity was (85.53 ± 7.13)%. In the CSF, the SI was (69.57 ± 15.26)%, the sensitivity was (89.86 ± 5.87)%, and the specificity was (92.36 ± 4.35)%.ConclusionsThe proposed clustering algorithm provides precise percentages of the various types of tissue within the prescription isodose region in the T2 weighted images used in the GKRS plan for AVM. Our results shed light on the causes of brain radiation injury after GKRS for AVM. In the future, this system could be used to improve outcomes and avoid complications associated with GKRS treatment.

Gadolinium effect on thalamus and whole brain tissue segmentation.

Gadolinium-based contrast agent (GBCA) effect on automated segmentation algorithms of subcortical gray matter (GM) is not fully known. The aim of this study is to determine gadolinium effect on the segmentation of the thalamus and whole brain tissue using different automated segmentation techniques. Eighty-four multiple sclerosis (MS) patients underwent an MRI acquisition of two 3DT1-weighted sequences with and without gadolinium injection among which 10 were excluded after image quality check. Manual thalamic segmentation considered as gold standard was performed on unenhanced T1 images. volBrain and FSL-Anat were used to automatically segment the thalamus on both enhanced and unenhanced T1 and the degree of similitude (DICE) values were compared between manual and automatic segmentations. Whole brain tissue segmentation (GM, white matter (WM), and lateral ventricles (LV)) was also performed using SIENAX. A paired samples t test was applied to test the significance of DICE value differences between the thalamic manual and automatic segmentations of both enhanced and unenhanced T1 images. Significant differences (FSL-Anat 1.474% p < 0.001 and volBrain 1.990% p < 0.001) in DICE between thalamic manual and automatic segmentations on both enhanced and unenhanced images were observed. Automatic tissue segmentation showed a mean DICE of 81.5%, with LV having the lowest DICE value (74.2%). When compared to tissue segmentations, automatic thalamic segmentations by FSL-Anat or volBrain demonstrated a higher degree of similitude (FSL-Anat = 91.7% and volBrain = 90.7%). Gadolinium has a significant effect on subcortical GM segmentation. Although significant, the observed subtle changes could be considered acceptable when used for region-based analysis in perfusion or diffusion imaging.

A new tissue segmentation method to calculate 3D dose in small animal radiation therapy

BackgroundIn pre-clinical animal experiments, radiation delivery is usually delivered with kV photon beams, in contrast to the MV beams used in clinical irradiation, because of the small size of the animals. At this medium energy range, however, the contribution of the photoelectric effect to absorbed dose is significant. Accurate dose calculation therefore requires a more detailed tissue definition because both density (ρ) and elemental composition (Zeff) affect the dose distribution. Moreover, when applied to cone beam CT (CBCT) acquisitions, the stoichiometric calibration of HU becomes inefficient as it is designed for highly collimated fan beam CT acquisitions. In this study, we propose an automatic tissue segmentation method of CBCT imaging that assigns both density (ρ) and elemental composition (Zeff) in small animal dose calculation.MethodsThe method is based on the relationship found between CBCT number and ρ*Zeff product computed from known materials. Monte Carlo calculations were performed to evaluate the impact of ρZeff variation on the absorbed dose in tissues. These results led to the creation of a tissue database composed of artificial tissues interpolated from tissue values published by the ICRU. The ρZeff method was validated by measuring transmitted doses through tissue substitute cylinders and a mouse with EBT3 film. Measurements were compared to the results of the Monte Carlo calculations.ResultsThe study of the impact of ρZeff variation over the range of materials, from ρZeff = 2 g.cm− 3 (lung) to 27 g.cm− 3 (cortical bone) led to the creation of 125 artificial tissues. For tissue substitute cylinders, the use of ρZeff method led to maximal and average relative differences between the Monte Carlo results and the EBT3 measurements of 3.6% and 1.6%. Equivalent comparison for the mouse gave maximal and average relative differences of 4.4% and 1.2%, inside the 80% isodose area. Gamma analysis led to a 94.9% success rate in the 10% isodose area with 4% and 0.3 mm criteria in dose and distance.ConclusionsOur new tissue segmentation method was developed for 40kVp CBCT images. Both density and elemental composition are assigned to each voxel by using a relationship between HU and the product ρZeff. The method, validated by comparing measurements and calculations, enables more accurate small animal dose distribution calculated on low energy CBCT images.

A stereotaxic breed-averaged, symmetric T2w canine brain atlas including detailed morphological and volumetrical data sets

Stereotaxic systems and automatic tissue segmentation routines enable neuronavigation as well as reproducible processing of neuroimage datasets. Such systems have been developed for humans, non-human-primates, sheep, and rodents, but not for dogs. Although dogs share important neurofunctional and -anatomical features with humans, and in spite of their importance in translational neuroscience, little is known about the variability of the canine brain morphology and, possibly related, function. Moreover, we lack templates, tissue probability maps (TPM), and stereotaxic brain labels for implementation in standard software utilities such as Statistical Parametric Mapping (SPM). Hence, objective and reproducible, image-based investigations are currently impeded in dogs. We have created a detailed stereotaxic reference frame for dogs including TPM and tissue labels, enabling inter-individual and cross-study neuroimage analysis.T2w datasets were acquired from 16 neurologically inconspicuous dogs of different breeds by 3T MRI. The datasets were averaged after initial preprocessing using linear and nonlinear registration algorithms as implemented in SPM8. TPM for gray (GM) and white matter (WM) as well as cerebrospinal fluid (CSF) were created. Different cortical, subcortical, medullary, and CSF regions were manually labeled to create a spatial binary atlas being aligned with the template. A proof-of-concept for automatic determination of morphological and volumetrical characteristics was performed using additional canine datasets (n = 64) including a subgroup of laboratory beagles (n = 24).Overall, 21 brain regions were labeled using the segmented tissue classes of the brain template. The proof-of-concept trial revealed excellent suitability of the created tools for image processing and subsequent analysis. There was high intra-breed variability in frontal lobe and hippocampus volumes, and noticeable inter-breed corpus callosum volume variation.The T2w brain template provides important, breed-averaged canine brain anatomy features in a spatial standard coordinate system. TPM allows automatic tissue segmentation using SPM and enables unbiased automatic image processing or morphological characterization in different canine breeds. The reported volumetric and morphometric results may serve as a starting point for further research aimed at in vivo analysis of canine brain anatomy and function.

Automatic Spine Tissue Segmentation from MRI Data Based on Cascade of Boosted Classifiers and Active Appearance Model.

The study introduces a novel method for automatic segmentation of vertebral column tissue from MRI images. The paper describes a method that combines multiple stages of Machine Learning techniques to recognize and separate different tissues of the human spine. For the needs of this paper, 50 MRI examinations presenting lumbosacral spine of patients with low back pain were selected. After the initial filtration, automatic vertebrae recognition using Cascade Classifier takes place. Afterwards the main segmentation process using the patch based Active Appearance Model is performed. Obtained results are interpolated using centripetal Catmull–Rom splines. The method was tested on previously unseen vertebrae images segmented manually by 5 physicians. A test validating algorithm convergence per iteration was performed and the Intraclass Correlation Coefficient was calculated. Additionally, the 10-fold cross-validation analysis has been done. Presented method proved to be comparable to the physicians (FF = 90.19 ± 1.01%). Moreover results confirmed a proper algorithm convergence. Automatically segmented area correlated well with manual segmentation for single measurements () and for average measurements () with p = 0.05. The 10-fold cross-validation analysis (FF = 91.37 ± 1.13%) confirmed a good model generalization resulting in practical performance.

Automatic Accurate Infant Cerebellar Tissue Segmentation with Densely Connected Convolutional Network.

The human cerebellum has been recognized as a key brain structure for motor control and cognitive function regulation. Investigation of brain functional development in the early life has recently been focusing on both cerebral and cerebellar development. Accurate segmentation of the infant cerebellum into different tissues is among the most important steps for quantitative development studies. However, this is extremely challenging due to the weak tissue contrast, extremely folded structures, and severe partial volume effect. To date, there are very few works touching infant cerebellum segmentation. We tackle this challenge by proposing a densely connected convolutional network to learn robust feature representations of different cerebellar tissues towards automatic and accurate segmentation. Specifically, we develop a novel deep neural network architecture by directly connecting all the layers to ensure maximum information flow even among distant layers in the network. This is distinct from all previous studies. Importantly, the outputs from all previous layers are passed to all subsequent layers as contextual features that can guide the segmentation. Our method achieved superior performance than other state-of-the-art methods when applied to Baby Connectome Project (BCP) data consisting of both 6- and 12-month-old infant brain images.

A novel method based on independent component analysis for brain MR image tissue classification into CSF, WM and GM for atrophy detection in Alzheimer’s disease

Brain Magnetic Resonance Image (MRI) plays a vital role in diagnosis of diseases like Brain Tumor, Alzheimer, Multiple Sclerosis, Schizophrenia and other White Matter Lesions. In most of the cases accurate segmentation of Brain MRI into tissue types like Cerebro-Spinal Fluid (CSF), White Matter (WM) and Grey Matter (GM) is of interest. The diagnostic accuracy of expert and non-expert Radiologists can be improved with accurate and automated tissue segmentation and classification system. Such system can also be used for trainees to understand the individual tissue distribution in MRI scans. In this paper, we propose a novel automated tissue segmentation and classification method based on Independent Component Analysis (ICA) with Band Expansion Process (BEP) and Support Vector Machine (SVM) classifier which with input as T1, T2 and Proton Density (PD) scans of patient, provides output as CSF, WM and GM indicating the possible atrophy in brain which can help in diagnosis of Alzheimer’s disease (AD). The objective of this work is to test the effectiveness of ICA with different input images generated using BEP for accurate brain tissue segmentation by validating results with different quality metrics. The novel method for generating input images for ICA has been implemented and segmented tissues are used for atrophy detection. The BEP + ICA + Thresholding + ‘SVM trained with Grey Level Co-occurrence Matrix (GLCM) based texture features’ is giving 100% tissue classification accuracy for test samples under consideration.

Effect of exposure to polycyclic aromatic hydrocarbons on basal ganglia and attention-deficit hyperactivity disorder symptoms in primary school children

BackgroundPolycyclic aromatic hydrocarbons (PAHs) have been proposed as environmental risk factors for attention deficit hyperactivity disorder (ADHD). The effects of these pollutants on brain structures potentially involved in the pathophysiology of ADHD are unknown. ObjectiveThe aim of this study was to investigate the effects of PAHs on basal ganglia volumes and ADHD symptoms in school children. MethodsWe conducted an imaging study in 242 children aged 8–12years, recruited through a set of representative schools of the city of Barcelona, Spain. Indoor and outdoor PAHs and benzo[a]pyrene (BPA) levels were assessed in the school environment, one year before the MRI assessment. Whole-brain volumes and basal ganglia volumes (caudate nucleus, globus pallidus, putamen) were derived from structural MRI scans using automated tissue segmentation. ADHD symptoms (ADHD/DSM-IV Scales, American Psychiatric Association 2002) were reported by teachers, and inattentiveness was evaluated with standard error of hit reaction time in the attention network computer-based test. ResultsTotal PAHs and BPA were associated with caudate nucleus volume (CNV) (i.e., an interquartile range increase in BPA outdoor level (67pg/m3) and indoor level (76pg/m3) was significantly linked to a decrease in CNV (mm3) (β=−150.6, 95% CI [−259.1, −42.1], p=0.007, and β=−122.4, 95% CI [−232.9, −11.8], p=0.030 respectively) independently of intracranial volume, age, sex, maternal education and socioeconomic vulnerability index at home). ADHD symptoms and inattentiveness increased in children with higher exposure to BPA, but these associations were not statistically significant. ConclusionsExposure to PAHs, and in particular to BPA, is associated with subclinical changes on the caudate nucleus, even below the legislated annual target levels established in the European Union. The behavioral consequences of this induced brain change were not identified in this study, but given the caudate nucleus involvement in many crucial cognitive and behavior processes, this volume reduction is concerning for the children's neurodevelopment.

Fast diffusion kurtosis imaging (DKI) with Inherent COrrelation-based Normalization (ICON) enhances automatic segmentation of heterogeneous diffusion MRI lesion in acute stroke.

Diffusion kurtosis imaging (DKI) has been shown to augment diffusion-weighted imaging (DWI) for the definition of irreversible ischemic injury. However, the complexity of cerebral structure/composition makes the kurtosis map heterogeneous, limiting the specificity of kurtosis hyperintensity to acute ischemia. We propose an Inherent COrrelation-based Normalization (ICON) analysis to suppress the intrinsic kurtosis heterogeneity for improved characterization of heterogeneous ischemic tissue injury. Fast DKI and relaxation measurements were performed on normal (n=10) and stroke rats following middle cerebral artery occlusion (MCAO) (n=20). We evaluated the correlations between mean kurtosis (MK), mean diffusivity (MD) and fractional anisotropy (FA) derived from the fast DKI sequence and relaxation rates R1 and R2 , and found a highly significant correlation between MK and R1 (p<0.001). We showed that ICON analysis suppressed the intrinsic kurtosis heterogeneity in normal cerebral tissue, enabling automated tissue segmentation in an animal stroke model. We found significantly different kurtosis and diffusivity lesion volumes: 147±59 and 180±66mm3 , respectively (p=0.003, paired t-test). The ratio of kurtosis to diffusivity lesion volume was 84%±19% (p<0.001, one-sample t-test). We found that relaxation-normalized MK (RNMK), but not MD, values were significantly different between kurtosis and diffusivity lesions (p<0.001, analysis of variance). Our study showed that fast DKI with ICON analysis provides a promising means of demarcation of heterogeneous DWI stroke lesions.

Fully-Automated μMRI Morphometric Phenotyping of the Tc1 Mouse Model of Down Syndrome.

We describe a fully automated pipeline for the morphometric phenotyping of mouse brains from μMRI data, and show its application to the Tc1 mouse model of Down syndrome, to identify new morphological phenotypes in the brain of this first transchromosomic animal carrying human chromosome 21. We incorporate an accessible approach for simultaneously scanning multiple ex vivo brains, requiring only a 3D-printed brain holder, and novel image processing steps for their separation and orientation. We employ clinically established multi-atlas techniques–superior to single-atlas methods–together with publicly-available atlas databases for automatic skull-stripping and tissue segmentation, providing high-quality, subject-specific tissue maps. We follow these steps with group-wise registration, structural parcellation and both Voxel- and Tensor-Based Morphometry–advantageous for their ability to highlight morphological differences without the laborious delineation of regions of interest. We show the application of freely available open-source software developed for clinical MRI analysis to mouse brain data: NiftySeg for segmentation and NiftyReg for registration, and discuss atlases and parameters suitable for the preclinical paradigm. We used this pipeline to compare 29 Tc1 brains with 26 wild-type littermate controls, imaged ex vivo at 9.4T. We show an unexpected increase in Tc1 total intracranial volume and, controlling for this, local volume and grey matter density reductions in the Tc1 brain compared to the wild-types, most prominently in the cerebellum, in agreement with human DS and previous histological findings.

Automated tissue segmentation of MR brain images in the presence of white matter lesions

Over the last few years, the increasing interest in brain tissue volume measurements on clinical settings has led to the development of a wide number of automated tissue segmentation methods. However, white matter lesions are known to reduce the performance of automated tissue segmentation methods, which requires manual annotation of the lesions and refilling them before segmentation, which is tedious and time-consuming. Here, we propose a new, fully automated T1-w/FLAIR tissue segmentation approach designed to deal with images in the presence of WM lesions. This approach integrates a robust partial volume tissue segmentation with WM outlier rejection and filling, combining intensity and probabilistic and morphological prior maps. We evaluate the performance of this method on the MRBrainS13 tissue segmentation challenge database, which contains images with vascular WM lesions, and also on a set of Multiple Sclerosis (MS) patient images. On both databases, we validate the performance of our method with other state-of-the-art techniques. On the MRBrainS13 data, the presented approach was at the time of submission the best ranked unsupervised intensity model method of the challenge (7th position) and clearly outperformed the other unsupervised pipelines such as FAST and SPM12. On MS data, the differences in tissue segmentation between the images segmented with our method and the same images where manual expert annotations were used to refill lesions on T1-w images before segmentation were lower or similar to the best state-of-the-art pipeline incorporating automated lesion segmentation and filling. Our results show that the proposed pipeline achieved very competitive results on both vascular and MS lesions. A public version of this approach is available to download for the neuro-imaging community.

Tissue segmentation of computed tomography images using a Random Forest algorithm: a feasibility study

There is a need for robust, fully automated whole body organ segmentation for diagnostic CT. This study investigates and optimizes a Random Forest algorithm for automated organ segmentation; explores the limitations of a Random Forest algorithm applied to the CT environment; and demonstrates segmentation accuracy in a feasibility study of pediatric and adult patients. To the best of our knowledge, this is the first study to investigate a trainable Weka segmentation (TWS) implementation using Random Forest machine-learning as a means to develop a fully automated tissue segmentation tool developed specifically for pediatric and adult examinations in a diagnostic CT environment.Current innovation in computed tomography (CT) is focused on radiomics, patient-specific radiation dose calculation, and image quality improvement using iterative reconstruction, all of which require specific knowledge of tissue and organ systems within a CT image. The purpose of this study was to develop a fully automated Random Forest classifier algorithm for segmentation of neck–chest–abdomen–pelvis CT examinations based on pediatric and adult CT protocols. Seven materials were classified: background, lung/internal air or gas, fat, muscle, solid organ parenchyma, blood/contrast enhanced fluid, and bone tissue using Matlab and the TWS plugin of FIJI. The following classifier feature filters of TWS were investigated: minimum, maximum, mean, and variance evaluated over a voxel radius of 2n, (n from 0 to 4), along with noise reduction and edge preserving filters: Gaussian, bilateral, Kuwahara, and anisotropic diffusion. The Random Forest algorithm used 200 trees with 2 features randomly selected per node. The optimized auto-segmentation algorithm resulted in 16 image features including features derived from maximum, mean, variance Gaussian and Kuwahara filters. Dice similarity coefficient (DSC) calculations between manually segmented and Random Forest algorithm segmented images from 21 patient image sections, were analyzed. The automated algorithm produced segmentation of seven material classes with a median DSC of 0.86 ± 0.03 for pediatric patient protocols, and 0.85 ± 0.04 for adult patient protocols. Additionally, 100 randomly selected patient examinations were segmented and analyzed, and a mean sensitivity of 0.91 (range: 0.82–0.98), specificity of 0.89 (range: 0.70–0.98), and accuracy of 0.90 (range: 0.76–0.98) were demonstrated. In this study, we demonstrate that this fully automated segmentation tool was able to produce fast and accurate segmentation of the neck and trunk of the body over a wide range of patient habitus and scan parameters.

Enlarged striatal volume in adults with ADHD carrying the 9-6 haplotype of the dopamine transporter gene DAT1.

The dopamine transporter gene, DAT1 (SLC6A3), has been studied extensively as a candidate gene for attention-deficit/hyperactivity disorder (ADHD). Different alleles of variable number of tandem repeats (VNTRs) in this gene have been associated with childhood ADHD (10/10 genotype and haplotype 10-6) and adult ADHD (haplotype 9-6). This suggests a differential association depending on age, and a role of DAT1 in modulating the ADHD phenotype over the lifespan. The DAT1 gene may mediate susceptibility to ADHD through effects on striatal volumes, where it is most highly expressed. In an attempt to clarify its mode of action, we examined the effect of three DAT1 alleles (10/10 genotype, and the haplotypes 10-6 and 9-6) on bilateral striatal volumes (nucleus accumbens, caudate nucleus, and putamen) derived from structural magnetic resonance imaging scans using automated tissue segmentation. Analyses were performed separately in three cohorts with cross-sectional MRI data, a childhood/adolescent sample (NeuroIMAGE, 301 patients with ADHD and 186 healthy participants) and two adult samples (IMpACT, 118 patients with ADHD and 111 healthy participants; BIG, 1718 healthy participants). Regression analyses revealed that in the IMpACT cohort, and not in the other cohorts, carriers of the DAT1 adult ADHD risk haplotype 9-6 had 5.9 % larger striatum volume relative to participants not carrying this haplotype. This effect varied by diagnostic status, with the risk haplotype affecting striatal volumes only in patients with ADHD. An explorative analysis in the cohorts combined (N = 2434) showed a significant gene-by-diagnosis-by-age interaction suggesting that carriership of the 9-6 haplotype predisposes to a slower age-related decay of striatal volume specific to the patient group. This study emphasizes the need of a lifespan approach in genetic studies of ADHD.Electronic supplementary materialThe online version of this article (doi:10.1007/s00702-016-1521-x) contains supplementary material, which is available to authorized users.

Principles and methods for automatic and semi-automatic tissue segmentation in MRI data.

The development of magnetic resonance imaging (MRI) revolutionized both the medical and scientific worlds. A large variety of MRI options have generated a huge amount of image data to interpret. The investigation of a specific tissue in 3D or 4D MR images can be facilitated by image processing techniques, such as segmentation and registration. In this work, we provide a brief review of the principles and methods that are commonly applied to achieve superior tissue segmentation results in MRI. The impacts of MR image acquisition on segmentation outcome and the principles of selecting and exploiting segmentation techniques tailored for specific tissue identification tasks are discussed. In the end, two exemplary applications, breast and fibroglandular tissue segmentation in MRI and myocardium segmentation in short-axis cine and real-time MRI, are discussed to explain the typical challenges that can be posed in practical segmentation tasks in MRI data. The corresponding solutions that are adopted to deal with these challenges of the two practical segmentation tasks are thoroughly reviewed.