Automatic Brain Tissue Segmentation Research Articles

Subject-specific atlas for automatic brain tissue segmentation of neonatal magnetic resonance images

Developing advanced systems for 3D brain tissue segmentation from neonatal magnetic resonance (MR) images is vital for newborn structural analysis. However, automatic segmentation of neonatal brain tissues is challenging due to smaller head size and inverted T1/T2 tissue contrast compared to adults. In this work, a subject-specific atlas based technique is presented for segmentation of gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) from neonatal MR images. It involves atlas selection, subject-specific atlas creation using random forest (RF) classifier, and brain tissue segmentation using the expectation maximization-Markov random field (EM-MRF) method. To increase the segmentation accuracy, different tissue intensity- and gradient-based features were used. Evaluation on 40 neonatal MR images (gestational age of 37–44 weeks) demonstrated an overall accuracy of 94.3% and an average Dice similarity coefficient (DSC) of 0.945 (GM), 0.947 (WM), and 0.912 (CSF). Compared to multi-atlas segmentation methods like SEGMA and EM-MRF with multiple atlases, our method improved accuracy by up to 4%, particularly in complex tissue regions. Our proposed method allows accurate brain tissue segmentation, a crucial step in brain magnetic resonance imaging (MRI) applications including brain surface reconstruction and realistic head model creation in neonates.

Improved neurological diagnoses and treatment strategies via automated human brain tissue segmentation from clinical magnetic resonance imaging

ObjectiveSegmentation of medical images is a crucial process in various image analysis applications. Automated segmentation methods excel in accuracy when compared to manual segmentation in the context of medical image analysis. One of the essential phases in the quantitative analysis of the brain is automated brain tissue segmentation using clinically obtained magnetic resonance imaging (MRI) data. It allows for precise quantitative examination of the brain, which aids in diagnosis, identification, and classification of disorders. Consequently, the efficacy of the segmentation approach is crucial to disease diagnosis and treatment planning. MethodsThis study presented a hybrid optimization method for segmenting brain tissue in clinical MRI scans using a fractional Henry horse herd gas optimization-based Shepard convolutional neural network (FrHHGO-based ShCNN). To segment the clinical brain MRI images into white matter (WM), grey matter (GM), and cerebrospinal fluid (CSF) tissues, the proposed framework was evaluated on the Lifespan Human Connectome Projects (HCP) database. The hybrid optimization algorithm, FrHHGO, integrates the fractional Henry gas optimization (FHGO) and horse herd optimization (HHO) algorithms. Training required 30 min, whereas testing and segmentation of brain tissues from an unseen image required an average of 12 s. ResultsCompared to the results obtained with no refinements, the Skull stripping refinement showed significant improvement. As the method included a preprocessing stage, it was flexible enough to enhance image quality, allowing for better results even with low-resolution input. Maximum precision of 93.2%, recall of 91.5%, Dice score of 91.1%, and F1-score of 90.5% were achieved using the proposed FrHHGO-based ShCNN, which was superior to all other approaches. ConclusionThe proposed method may outperform existing state-of-the-art methodologies in qualitative and quantitative measurements across a wide range of medical modalities. It might demonstrate its potential for real-life clinical application.

Automatic Brain Tissue and Lesion Segmentation and Multi-Parametric Mapping of Contrast-Enhancing Gliomas without the Injection of Contrast Agents: A Preliminary Study.

This study aimed to develop a rapid, 1 mm3 isotropic resolution, whole-brain MRI technique for automatic lesion segmentation and multi-parametric mapping without using contrast by continuously applying balanced steady-state free precession with inversion pulses throughout incomplete inversion recovery in a single 6 min scan. Modified k-means clustering was performed for automatic brain tissue and lesion segmentation using distinct signal evolutions that contained mixed T1/T2/magnetization transfer properties. Multi-compartment modeling was used to derive quantitative multi-parametric maps for tissue characterization. Fourteen patients with contrast-enhancing gliomas were scanned with this sequence prior to the injection of a contrast agent, and their segmented lesions were compared to conventionally defined manual segmentations of T2-hyperintense and contrast-enhancing lesions. Simultaneous T1, T2, and macromolecular proton fraction maps were generated and compared to conventional 2D T1 and T2 mapping and myelination water fraction mapping acquired with MAGiC. The lesion volumes defined with the new method were comparable to the manual segmentations (r = 0.70, p < 0.01; t-test p > 0.05). The T1, T2, and macromolecular proton fraction mapping values of the whole brain were comparable to the reference values and could distinguish different brain tissues and lesion types (p < 0.05), including infiltrating tumor regions within the T2-lesion. Highly efficient, whole-brain, multi-contrast imaging facilitated automatic lesion segmentation and quantitative multi-parametric mapping without contrast, highlighting its potential value in the clinic when gadolinium is contraindicated.

EP06.11: Deep learning‐based automatic brain tissue segmentation in prenatal ultrasound

EP06.11: Deep learning‐based automatic brain tissue segmentation in prenatal ultrasound

Learning to segment fetal brain tissue from noisy annotations.

Automatic fetal brain tissue segmentation can enhance the quantitative assessment of brain development at this critical stage. Deep learning methods represent the state of the art in medical image segmentation and have also achieved impressive results in brain segmentation. However, effective training of a deep learning model to perform this task requires a large number of training images to represent the rapid development of the transient fetal brain structures. On the other hand, manual multi-label segmentation of a large number of 3D images is prohibitive. To address this challenge, we segmented 272 training images, covering 19-39 gestational weeks, using an automatic multi-atlas segmentation strategy based on deformable registration and probabilistic atlas fusion, and manually corrected large errors in those segmentations. Since this process generated a large training dataset with noisy segmentations, we developed a novel label smoothing procedure and a loss function to train a deep learning model with smoothed noisy segmentations. Our proposed methods properly account for the uncertainty in tissue boundaries. We evaluated our method on 23 manually-segmented test images of a separate set of fetuses. Results show that our method achieves an average Dice similarity coefficient of 0.893 and 0.916 for the transient structures of younger and older fetuses, respectively. Our method generated results that were significantly more accurate than several state-of-the-art methods including nnU-Net that achieved the closest results to our method. Our trained model can serve as a valuable tool to enhance the accuracy and reproducibility of fetal brain analysis in MRI.

Fusion of quantitative susceptibility maps and T1-weighted images improve brain tissue contrast in primates

Recent progress in quantitative susceptibility mapping (QSM) has enabled the accurate delineation of submillimeter-scale subcortical brain structures in humans. However, the simultaneous visualization of cortical, subcortical, and white matter structure remains challenging, utilizing QSM data solely. Here we present TQ-SILiCON, a fusion method that enhances the contrast of cortex and subcortical structures and provides an excellent white matter delineation by combining QSM and conventional T1-weighted (T1w) images. In this study, we first applied QSM in the macaque monkey to map iron-rich subcortical structures. Implementing the same QSM acquisition and analysis methods allowed a similar accurate delineation of subcortical structures in humans. However, the QSM contrast of white and cortical gray matter was not sufficient for appropriate segmentation. Applying automatic brain tissue segmentation to TQ-SILiCON images of the macaque improved the classification of subcortical brain structures as compared to the single T1 contrast by maintaining an excellent white to cortical gray matter contrast. Furthermore, we validated our dual-contrast fusion approach in humans and similarly demonstrated improvements in automated segmentation of the cortex and subcortical structures. We believe the proposed contrast will facilitate translational studies in nonhuman primates to investigate the pathophysiology of neurodegenerative diseases that affect subcortical structures such as the basal ganglia in humans.

Automatic macaque brain segmentation based on 7T MRI

BackgroundIn monkey neuroimaging, particularly magnetic resonance imaging (MRI) studies, quick and accurate automatic macaque brain segmentation is essential. However, there are few processing and analysis tools dedicated to automatic brain tissue segmentation and labeling of the macaque brain on a subject-specific basis. As a result, currently most adopted methods are through direct implementation of existing tools that have been designed for human brain. However, the operation steps combining different functional modules of a variety of processing and analysis tool software are inevitably complicated, cumbersome, time-consuming and labor-intensive. New methodIn this study, we proposed a novel quick and accurate automatic macaque brain segmentation method based on multi-atlas registration and majority-vote algorithm. First, the single-atlas method based on S-HAMMER is used to register each template image of the reference atlas set (including brain tissue labeled images and brain anatomical structure labeled images) to the preprocessed image to be segmented. Thus, we obtain the corresponding deformation field and spatially transform the labeled image, and then get multiple segmentation results by local weighted voting method, which perform label fusion to obtain the final labeled images of brain structures segmentation result. ResultsBy collecting high SNR and high spatial resolution images of macaque brain images from our 7T human MRI scanner, we have constructed two brain templates for each individual macaque subject, and macaque brain tissues and brain anatomical structure by one-atlas method. However, segmentation result of single-atlas method is not much accurate in some brain tissue area. It takes about 2 h and need more manual correction for segmentation. Automatic segmentation of macaque brain structure based on multi-atlas method was reasonably successful, the accuracy of segmentation was greatly improved without manual correction. Also, the proposed method provided good tissue fitting to V1 with smooth and continuous boundary. The Dice similarity of multi-atlas method showing 3.24%, 4.24%, 2.55%, 2.85%, 3.05%, and 0.35% improvement in image slices of 63, 66, 70, 71, 99 and 100, respectively. The entire processing time for the construction of a single template map took ~40 min. ConclusionsThis study proposed a novel automatic segmentation method of individual macaque brain structure based on multi-atlas registration method, which is concise and reliable. It may offer a valuable tool to applications in the field of brain and neuroscience research using the macaque as an experimental animal model.

A polynomial regression-based approach to estimate relaxation rate maps suitable for multiparametric segmentation of clinical brain MRI studies in multiple sclerosis

Background and ObjectiveRelaxation parameter maps (RPMs) calculated from spin-echo data have provided a basis for the segmentation of normal brain tissues and white matter lesions in multiple sclerosis (MS) MRI studies. However, Conventional Spin-Echo (CSE) sequences, once the core of clinical MRI studies, have been largely replaced by faster ones, which do not allow the calculation a-posteriori of RPMs from clinical studies. Aim of the study was to develop and validate a method to estimate RPMs (pseudo-RPMs) from routine clinical MRI protocols (including 3D-Gradient Echo T1w, FLAIR and fast-T2w sequences), suitable for fully automatic multiparametric segmentation of normal-appearing and pathological brain tissues in MS. MethodsThe proposed method processes spatially normalized clinical MRI studies through a multistep pipeline, to collect a set of data points of matched signal intensities (from MRI studies) and relaxation parameters (from a CSE-derived digital template and an MS lesion database), which are then fitted by a multiple and multivariate 4-th degree polynomial regression, providing pseudo-RPMs. The method was applied to a dataset of 59 clinical MRI studies providing pseudo-RPMs that were segmented through a method originally developed for the CSE-derived RPMs. Results of the segmentation in 12 studies were used to iteratively optimize method parameters. Accuracy of segmentation of normal-appearing brain tissues from the pseudo-RPMs was assessed by comparing their age-related changes, as measured in 47 clinical studies, against those measured acquired using CSE sequences in a comparable dataset of 47 patients. Lesion segmentation was validated against manual segmentation carried out by three neuroradiologists. ResultsAge-related changes of normal-appearing brain tissue volumes measured using the pseudo-RPMs substantially overlapped those measured using the RPMs obtained from CSE sequences, and segmentation of MS lesions showed a moderate-high spatial overlap with manual segmentation, comparable to that achieved by the widely used Lesion Segmentation Tool on FLAIR images, with a greater volumetric agreement. ConclusionsThe proposed approach allows calculation from clinical studies of pseudo-RPMs, which are equivalent to those obtainable from CSE sequences, avoiding the need for the acquisition of additional, dedicated sequences for segmentation purposes.

APRNet: A 3D Anisotropic Pyramidal Reversible Network With Multi-Modal Cross-Dimension Attention for Brain Tissue Segmentation in MR Images.

Brain tissue segmentation in multi-modal magnetic resonance (MR) images is significant for the clinical diagnosis of brain diseases. Due to blurred boundaries, low contrast, and intricate anatomical relationships between brain tissue regions, automatic brain tissue segmentation without prior knowledge is still challenging. This paper presents a novel 3D fully convolutional network (FCN) for brain tissue segmentation, called APRNet. In this network, we first propose a 3D anisotropic pyramidal convolutional reversible residual sequence (3DAPC-RRS) module to integrate the intra-slice information with the inter-slice information without significant memory consumption; secondly, we design a multi-modal cross-dimension attention (MCDA) module to automatically capture the effective information in each dimension of multi-modal images; then, we apply 3DAPC-RRS modules and MCDA modules to a 3D FCN with multiple encoded streams and one decoded stream for constituting the overall architecture of APRNet. We evaluated APRNet on two benchmark challenges, namely MRBrainS13 and iSeg-2017. The experimental results show that APRNet yields state-of-the-art segmentation results on both benchmark challenge datasets and achieves the best segmentation performance on the cerebrospinal fluid region. Compared with other methods, our proposed approach exploits the complementary information of different modalities to segment brain tissue regions in both adult and infant MR images, and it achieves the average Dice coefficient of 87.22% and 93.03% on the MRBrainS13 and iSeg-2017 testing data, respectively. The proposed method is beneficial for quantitative brain analysis in the clinical study, and our code is made publicly available.

BrainSec: Automated Brain Tissue Segmentation Pipeline for Scalable Neuropathological Analysis.

As neurodegenerative disease pathological hallmarks have been reported in both grey matter (GM) and white matter (WM) with different density distributions, automating the segmentation process of GM/WM would be extremely advantageous for aiding in neuropathologic deep phenotyping. Standard segmentation methods typically involve manual annotations, where a trained researcher traces the delineation of GM/WM in ultra-high-resolution Whole Slide Images (WSIs). This method can be time-consuming and subjective, preventing a scalable analysis on pathology images. This paper proposes an automated segmentation pipeline (BrainSec) combining a Convolutional Neural Network (CNN) module for segmenting GM/WM regions and a post-processing module to remove artifacts/residues of tissues. The final output generates XML annotations that can be visualized via Aperio ImageScope. First, we investigate two baseline models for medical image segmentation: FCN, and U-Net. Then we propose a patch-based approach, BrainSec, to classify the GM/WM/background regions. We demonstrate BrainSec is robust and has reliable performance by testing it on over 180 WSIs that incorporate numerous unique cases as well as distinct neuroanatomic brain regions. We also apply gradient-weighted class activation mapping (Grad-CAM) to interpret the segmentation masks and provide relevant explanations and insights. In addition, we have integrated BrainSec with an existing Amyloid-β pathology classification model into a unified framework (without incurring significant computation complexity) to identify pathologies, visualize their distributions, and quantify each type of pathologies in segmented GM/WM regions, respectively.

Segmentation of Brain Tumors from MRI Images Using Convolutional Autoencoder

The use of machine learning algorithms and modern technologies for automatic segmentation of brain tissue increases in everyday clinical diagnostics. One of the most commonly used machine learning algorithms for image processing is convolutional neural networks. We present a new convolutional neural autoencoder for brain tumor segmentation based on semantic segmentation. The developed architecture is small, and it is tested on the largest online image database. The dataset consists of 3064 T1-weighted contrast-enhanced magnetic resonance images. The proposed architecture’s performance is tested using a combination of two different data division methods, and two different evaluation methods, and by training the network with the original and augmented dataset. Using one of these data division methods, the network’s generalization ability in medical diagnostics was also tested. The best results were obtained for record-wise data division, training the network with the augmented dataset. The average accuracy classification of pixels is 99.23% and 99.28% for 5-fold cross-validation and one test, respectively, and the average dice coefficient is 71.68% and 72.87%. Considering the achieved performance results, execution speed, and subject generalization ability, the developed network has great potential for being a decision support system in everyday clinical practice.

MPRAGE to MP2RAGE UNI translation via generative adversarial network improves the automatic tissue and lesion segmentation in multiple sclerosis patients

Background and objectiveCompared to the conventional magnetization-prepared rapid gradient-echo imaging (MPRAGE) MRI sequence, the specialized magnetization prepared 2 rapid acquisition gradient echoes (MP2RAGE) shows a higher brain tissue and lesion contrast in multiple sclerosis (MS) patients. The goal of this work is to retrospectively generate realistic-looking MP2RAGE uniform images (UNI) from already acquired MPRAGE images in order to improve the automatic lesion and tissue segmentation. MethodsFor this task we propose a generative adversarial network (GAN). Multi-contrast MRI data of 12 healthy controls and 44 patients diagnosed with MS was retrospectively analyzed. Imaging was acquired at 3T using a SIEMENS scanner with MPRAGE, MP2RAGE, FLAIR, and DIR sequences. We train the GAN with both healthy controls and MS patients to generate synthetic MP2RAGE UNI images. These images were then compared to the real MP2RAGE UNI (considered as ground truth) analyzing the output of automatic brain tissue and lesion segmentation tools. Reference-based metrics as well as the lesion-wise true and false positives, Dice coefficient, and volume difference were considered for the evaluation. Statistical differences were assessed with the Wilcoxon signed-rank test. ResultsThe synthetic MP2RAGE UNI significantly improves the lesion and tissue segmentation masks in terms of Dice coefficient and volume difference (p-values < 0.001) compared to the MPRAGE. For the segmentation metrics analyzed no statistically significant differences are found between the synthetic and acquired MP2RAGE UNI. ConclusionSynthesized MP2RAGE UNI images are visually realistic and improve the output of automatic segmentation tools.

Brain Tissue Segmentation from Magnetic Resonance Brain Images Using Histogram Based Swarm Optimization Techniques.

In order to reduce time complexity and to improve the computational efficiency in diagnosing process, automated brain tissue segmentation for magnetic resonance brain images is proposed in this paper. This method incorporates two processes, the first one is preprocessing and the second one is segmentation of brain tissue using Histogram based Swarm Optimization techniques. The proposed method was investigated with images obtained from twenty volumes and eighteen volumes of T1-Weighted images obtained from Internet Brain Segmentation Repository (IBSR), Alzheimer disease images from Minimum Interval Resonance Imaging in Alzheimer's Disease (MIRIAD) and T2-Weighted real-time images collected from SBC Scan Center Dindigul. The proposed technique was tested with three brain image datasets. Quantitative evaluation was done with Jaccard (JC) and Dice (DC) and also it was compared with existing swarm optimization techniques and other methods like Adaptive Maximum a posteriori probability (AMAP), Biased Maximum a posteriori Probability (BMAP), Maximum a posteriori Probability (MAP), Maximum Likelihood (ML) and Tree structure K-Means (TK-Means). The performance comparative analysis shows that our proposed method Histogram based Darwinian Particle Swarm Optimization (HDPSO) gives better results than other proposed techniques such as Histogram based Particle Swarm Optimization (HPSO), Histogram based Fractional Order Darwinian Particle Swarm Optimization (HFODPSO) and with existing swarm optimization techniques and other techniques like Adaptive Maximum a posteriori Probability (AMAP), Biased Maximum a posteriori Probability (BMAP), Maximum a posteriori Probability (MAP), Maximum Likelihood (ML) and Tree structure K-Means (TK-Means).

Fully automatic brain tumor extraction and tissue segmentation from multimodal MRI brain images

AbstractSegmentation of Brain tumor from the magnetic resonance imaging (MRI) of head scans is an essential requirement for clinical diagnosis since manual segmentation is a fatigue and time‐consuming process. Recent computer‐aided diagnosis systems depend on the development of fully automatic methods to overcome these problems. In the present work, a fully automated algorithm is proposed to extract and segment tumor regions from multimodal magnetic resonance imaging (MMMRI) sequences. The algorithm has three phases: (a) tumor portion extraction, (b) tumor substructure segmentation, and (c) 3D postprocessing. First, the algorithm extracts tumor portion using a set of image processing operations from T2, fluid‐attenuated inversion recovery (FLAIR), and T1C images. Here, the proposed modified fuzzy c means clustering algorithm is used for enhancing the tumor portion extraction process. Then, the substructures of tumor such as edema, enhancing tumor, and necrotic regions are segmented from MMMRI sequences, T2, FLAIR, and T1C using region‐wise set operations in Phase II. Finally, 3D visualization of the segmented tumor and volume estimation is performed as postprocessing in Phase III. The proposed work was experimented on BraTS 2013 dataset. The quantitative analysis is performed using William's Index, Dice, sensitivity, specificity, and accuracy and is compared with 19 state‐of‐the‐art methods. The proposed method yields comparable results as 77%, 53%, and 59% of Dice for complete, core, and enhancing tumor regions, respectively.

Sparse representation of DWI images for fully automated brain tissue segmentation

BackgroundBrain tissue segmentation plays an important role in biomedical research and clinical applications. Traditional segmentation is performed on T1-weighted and/or T2-weighted MRI images. Recently, brain segmentation based on diffusion weighted imaging (DWI) has attracted research interest due to its advantage in diffusion MRI image processing and anatomically-constrained tractography. New methodWe propose a fully automated brain segmentation method based on sparse representation of DWI signals and applied it on nine healthy subjects of Human Connectome Project aged 25–35 years. Learning a dictionary from DWI signals of each subject, brain voxels are classified into gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) according to their sparse representation of clustered dictionary atoms, achieving good agreement with the segmentation on T1-weighted images using SPM12, as assessed by the DICE score. ResultsThe average DICE score for all nine subjects was 0.814 for CSF, 0.850 for GM, and 0.890 for WM. The proposed method is very fast and robust for a wide range of sparse coding parameter selection. It also works well on DWI data with less number of shells or gradient directions. Comparison with existing methodsOn average, our segmentation results are superior to previous methods for all three brain tissue classes in terms of DICE scores. ConclusionThe proposed method demonstrates the feasibility of segmenting the brain solely based on the tissue response to diffusion encoding.

Brain tissue segmentation for medical decision support systems

Automatic brain tissue segmentation on clinically acquired magnetic resonance image is a very challenging task due to the presence of intensity inhomogeneity, noise, and the complex anatomical structure of interest. Due to the existence of noise in clinical magnetic resonance brain images, various segmentation techniques suffer from low segmentation accuracy. Thus, to overcome the ambiguity caused by the above special effects, an enhanced fuzzy relaxation approach called fuzzy relaxation-based modified fuzzy c-means clustering algorithm is presented. In the proposed method, exposure-based sub-image fuzzy brightness adaptation algorithm is implemented for the enhancement of brain tissues, and it is followed by a modified fuzzy c-means clustering algorithm to segment the enhanced brain magnetic resonance image into white matter, gray matter and cerebrospinal fluid tissues. The proposed method is compared with other existing methods in terms of quantitative measures such as peak signal to noise ratio, discrete entropy, contrast improvement index, sensitivity, specificity, accuracy, jaccard similarity, and dice similarity coefficient. Experimental results demonstrate that the proposed method achieves a good trade-off between intensity inhomogeneity and noise. The proposed method conforms its success on brain tissue segmentation and provides extensive support to radiologists and clinical centers.

Automatic Brain Tissue Segmentation using Modified K-Means Algorithm Based on Image Processing Techniques

Brain tumor, due to uncontrolled development of abnormal cells, is one of the hazardous illnesses that happen in the brain. A fully automatic brain tissue segmentation using improved k means segmentation is discussed in this paper. Generally the brain tumor tissue can appear at any location at different size and shapes. Manual brain tumor detection is not only time-consuming, it is also linked to human errors and depends on the expertise and experience of a medical pathologist. Automatic detection is required in a computer-aided detection system (CAD) for medical images such as MRI. This automatic detection includes pre-processing, segmentation and medical image classification. The preprocessing techniques eliminate noise. Separate the region of interest from the background picture using the segmentation methods. Finally, the classification is conducted to identify brain tumor automatically. The outcomes are also compared between the suggested method and the current methods.

Machine Learning-Based Framework for Differential Diagnosis Between Vascular Dementia and Alzheimer's Disease Using Structural MRI Features.

Background and Objective: Vascular dementia (VaD) and Alzheimer's disease (AD) could be characterized by the same syndrome of dementia. This study aims to assess whether multi-parameter features derived from structural MRI can serve as the informative biomarker for differential diagnosis between VaD and AD using machine learning.Methods: A total of 93 patients imaged with brain MRI including 58 AD and 35 VaD confirmed by two chief physicians were recruited in this study from June 2013 to July 2019. Automated brain tissue segmentation was performed by the AccuBrain tool to extract multi-parameter volumetric measurements from different brain regions. Firstly, a total of 62 structural MRI biomarkers were addressed to select significantly different features between VaD and AD for dimensionality reduction. Then, the least absolute shrinkage and selection operator (LASSO) was further used to construct a feature set that is fed into a support vector machine (SVM) classifier. To ensure the unbiased evaluation of model performance, a comparative study of classification models was implemented by using different machine learning algorithms in order to determine which performs best in the application of differential diagnosis between VaD and AD. The diagnostic performance of the classification models was evaluated by the quantitative metrics derived from the receiver operating characteristic curve (ROC).Results: The experimental results demonstrate that the SVM with RBF achieved an encouraging performance with sensitivity (SEN), specificity (SPE), and accuracy (ACC) values of 82.65%, 87.17%, and 84.35%, respectively (AUC = 0.861, 95% CI = 0.820–0.902), for the differential diagnosis between VaD and AD.Conclusions: The proposed computer-aided diagnosis method highlights the potential of combining structural MRI and machine learning to support clinical decision making in distinction of VaD vs. AD.

Skip-connected 3D DenseNet for volumetric infant brain MRI segmentation

Automatic 6-month infant brain tissue segmentation of magnetic resonance imaging (MRI) is still less accurate owing to the low intensity contrast among tissues. To tackle the problem, we introduce an accurate segmentation method for volumetric infant brain MRI built upon a densely connected network that achieves state-of-the-art accuracy. Specifically, we carefully design a fully convolutional densely connected network with skip connections such that the information from different levels of dense blocks can be directly combined to achieve highly accurate segmentation results. The proposed network, called 3D-SkipDenseSeg, exploits the advantage of the recently DenseNet for classification task and extends this to segment the 6-month infant brain tissue segmentation of magnetic resonance imaging (MRI). Experimental results demonstrate a competitive performance with regard to both segmentation accuracy and parameter efficiency of the proposed method over the existing methods; namely, the proposed 3D-SkipDenseSeg achieved the best dice similarity coefficient (DSC) of 90.37 ± 1.38% (WM), 92.27 ± 0.81% (GM), and 95.79 ± 0.54% (CSF) among the 21 participating teams in the 6-month infant brain dataset (iSeg-2017) and required only 10–30% of the parameters compared to similar deep learning-based methods.

Automatic brain tissue segmentation in fetal MRI using convolutional neural networks

MR images of fetuses allow clinicians to detect brain abnormalities in an early stage of development. The cornerstone of volumetric and morphologic analysis in fetal MRI is segmentation of the fetal brain into different tissue classes. Manual segmentation is cumbersome and time consuming, hence automatic segmentation could substantially simplify the procedure. However, automatic brain tissue segmentation in these scans is challenging owing to artifacts including intensity inhomogeneity, caused in particular by spontaneous fetal movements during the scan. Unlike methods that estimate the bias field to remove intensity inhomogeneity as a preprocessing step to segmentation, we propose to perform segmentation using a convolutional neural network that exploits images with synthetically introduced intensity inhomogeneity as data augmentation. The method first uses a CNN to extract the intracranial volume. Thereafter, another CNN with the same architecture is employed to segment the extracted volume into seven brain tissue classes: cerebellum, basal ganglia and thalami, ventricular cerebrospinal fluid, white matter, brain stem, cortical gray matter and extracerebral cerebrospinal fluid. To make the method applicable to slices showing intensity inhomogeneity artifacts, the training data was augmented by applying a combination of linear gradients with random offsets and orientations to image slices without artifacts. To evaluate the performance of the method, Dice coefficient (DC) and Mean surface distance (MSD) per tissue class were computed between automatic and manual expert annotations. When the training data was enriched by simulated intensity inhomogeneity artifacts, the average achieved DC over all tissue classes and images increased from 0.77 to 0.88, and MSD decreased from 0.78 mm to 0.37 mm. These results demonstrate that the proposed approach can potentially replace or complement preprocessing steps, such as bias field corrections, and thereby improve the segmentation performance.