Hippocampus segmentation in MR images using atlas registration, voxel classification, and graph cuts

Eye Size and Shape in Relation to Refractive Error in Children: A Magnetic Resonance Imaging Study

Purpose

The purpose of this study was to determine the association between eye shape and volume measured with magnetic resonance imaging (MRI) and optical biometry and with spherical equivalent (SE) in children.

Methods

For this study, there were 3637 10-year-old children from a population-based birth-cohort study that underwent optical biometry (IOL-master 500) and T2-weighted MRI scanning (height, width, and volume). Cycloplegic refractive error was determined by automated refraction. The MRI images of the eyes were segmented using an automated algorithm combining atlas registration with voxel classification. Associations among optical biometry, anthropometry, MRI measurements, and RE were tested using Pearson correlation. Differences between refractive error groups were tested using ANOVA.

Results

The mean volume of the posterior segment was 6350 (±680) mm3. Myopic eyes (SE ≤ -0.5 diopters [D]) had 470 mm3 (P < 0.001) and 970 mm3 (P < 0.001) larger posterior segment volume than emmetropic and hyperopic eyes (SE ≥ +2.0D), respectively. The majority of eyes (77.1%) had an oblate shape, but 47.4% of myopic eyes had a prolate shape versus 3.9% of hyperopic eyes. The correlation between SE and MRI-derived posterior segment length (r -0.51, P < 0.001) was stronger than the correlation with height (r -0.30, P < 0.001) or width of the eye (r -0.10, P < 0.001).

Conclusions

In this study, eye shape at 10 years of age was predominantly oblate, even in eyes with myopia. Of all MRI measurements, posterior segment length was most prominently associated with SE. Whether eye shape predicts future myopia development or progression should be investigated in longitudinal studies.

Is Hippocampal Volume a Relevant Early Marker of Dementia?

OBJECTIVE

Hippocampal volume (HV) is a key imaging marker to improve Alzheimer's disease risk prediction. However, longitudinal studies are rare, and hippocampus may also be implicated in the subtle aging-related cognitive decline observed in dementia-free individuals. Our aim was to determine whether HV, measured by manual or automatic segmentation, is associated with dementia risk and cognitive decline in participants with and without incident dementia.

METHODS

At baseline, 510 dementia-free participants from the French longitudinal ESPRIT cohort underwent magnetic resonance imaging. HV was measured by manual and by automatic segmentation (FreeSurfer 6.0). The presence of dementia and cognitive functions were investigated at each follow-up (2, 4, 7, 10, 12, and 15 years). Cox proportional hazards models and linear mixed models were used to assess the association of HV with dementia risk and with cognitive decline, respectively.

RESULTS

During the 15-years follow-up, 42 participants developed dementia. Reduced HV (regardless of the measurement method) was significantly associated with higher dementia risk and cognitive decline in the whole sample. However, only the automatically measured HV was associated with cognitive decline in dementia-free participants.

CONCLUSION

These results suggest that HV can be used to predict the long-term risk of dementia but also cognitive decline in a dementia-free population. This raises the question of the relevance of HV measurement as an early marker of dementia in the general population.

Deep learning for the diagnosis of mesial temporal lobe epilepsy

OBJECTIVE

This study aimed to enable the automatic detection of the hippocampus and diagnose mesial temporal lobe epilepsy (MTLE) with the hippocampus as the epileptogenic area using artificial intelligence (AI). We compared the diagnostic accuracies of AI and neurosurgical physicians for MTLE with the hippocampus as the epileptogenic area.

METHOD

In this study, we used an AI program to diagnose MTLE. The image sets were processed using a code written in Python 3.7.4. and analyzed using Open Computer Vision 4.5.1. The deep learning model, which was a fine-tuned VGG16 model, consisted of several layers. The diagnostic accuracies of AI and board-certified neurosurgeons were compared.

RESULTS

AI detected the hippocampi automatically and diagnosed MTLE with the hippocampus as the epileptogenic area on both T2-weighted imaging (T2WI) and fluid-attenuated inversion recovery (FLAIR) images. The diagnostic accuracies of AI based on T2WI and FLAIR data were 99% and 89%, respectively, and those of neurosurgeons based on T2WI and FLAIR data were 94% and 95%, respectively. The diagnostic accuracy of AI was statistically higher than that of board-certified neurosurgeons based on T2WI data (p = 0.00129).

CONCLUSION

The deep learning-based AI program is highly accurate and can diagnose MTLE better than some board-certified neurosurgeons. AI can maintain a certain level of output accuracy and can be a reliable assistant to doctors.

Hippocampus Segmentation Using U-Net Convolutional Network from Brain Magnetic Resonance Imaging (MRI)

Hippocampus is a part of the limbic system in human brain that plays an important role in forming memories and dealing with intellectual abilities. In most of the neurological disorders related to dementia, such as, Alzheimer's disease, hippocampus is one of the earliest affected regions. Because there are no effective dementia drugs, an ambient assisted living approach may help to prevent or slow the progression of dementia. By segmenting and analyzing the size/shape of hippocampus, it may be possible to classify the early dementia stages. Because of complex structure, traditional image segmentation techniques can't segment hippocampus accurately. Machine learning (ML) is a well known tool in medical image processing that can predict and deliver the outcomes accurately by learning from it's previous results. Convolutional Neural Networks (CNN) is one of the most popular ML algorithms. In this work, a U-Net Convolutional Network based approach is used for hippocampus segmentation from 2D brain images. It is observed that, the original U-Net architecture can segment hippocampus with an average performance rate of 93.6%, which outperforms all other discussed state-of-arts. By using a filter size of [Formula: see text], the original U-Net architecture performs a sequence of convolutional processes. We tweaked the architecture further to extract more relevant features by replacing all [Formula: see text] kernels with three alternative kernels of sizes [Formula: see text], [Formula: see text], and [Formula: see text]. It is observed that, the modified architecture achieved an average performance rate of 96.5%, which outperforms the original U-Net model convincingly.

Differences Between MR Brain Region Segmentation Methods: Impact on Single-Subject Analysis

For the segmentation of magnetic resonance brain images into anatomical regions, numerous fully automated methods have been proposed and compared to reference segmentations obtained manually. However, systematic differences might exist between the resulting segmentations, depending on the segmentation method and underlying brain atlas. This potentially results in sensitivity differences to disease and can further complicate the comparison of individual patients to normative data. In this study, we aim to answer two research questions: 1) to what extent are methods interchangeable, as long as the same method is being used for computing normative volume distributions and patient-specific volumes? and 2) can different methods be used for computing normative volume distributions and assessing patient-specific volumes? To answer these questions, we compared volumes of six brain regions calculated by five state-of-the-art segmentation methods: Erasmus MC (EMC), FreeSurfer (FS), geodesic information flows (GIF), multi-atlas label propagation with expectation–maximization (MALP-EM), and model-based brain segmentation (MBS). We applied the methods on 988 non-demented (ND) subjects and computed the correlation (PCC-v) and absolute agreement (ICC-v) on the volumes. For most regions, the PCC-v was good (>0.75), indicating that volume differences between methods in ND subjects are mainly due to systematic differences. The ICC-v was generally lower, especially for the smaller regions, indicating that it is essential that the same method is used to generate normative and patient data. To evaluate the impact on single-subject analysis, we also applied the methods to 42 patients with Alzheimer’s disease (AD). In the case where the normative distributions and the patient-specific volumes were calculated by the same method, the patient’s distance to the normative distribution was assessed with the z-score. We determined the diagnostic value of this z-score, which showed to be consistent across methods. The absolute agreement on the AD patients’ z-scores was high for regions of thalamus and putamen. This is encouraging as it indicates that the studied methods are interchangeable for these regions. For regions such as the hippocampus, amygdala, caudate nucleus and accumbens, and globus pallidus, not all method combinations showed a high ICC-z. Whether two methods are indeed interchangeable should be confirmed for the specific application and dataset of interest.

Hippocampus Segmentation Method Based on Subspace Patch-Sparsity Clustering in Noisy Brain MRI

Since the hippocampus is of small size, low contrast, and irregular shape, a novel hippocampus segmentation method based on subspace patch-sparsity clustering in brain MRI is proposed to improve the segmentation accuracy, which requires that the representation coefficients in different subspaces should be as sparse as possible, while the representation coefficients in the same subspace should be as average as possible. By restraining the coefficient matrix with the patch-sparse constraint, the coefficient matrix contains a patch-sparse structure, which is helpful to the hippocampus segmentation. The experimental results show that our proposed method is effective in the noisy brain MRI data, which can well deal with hippocampus segmentation problem.

Pixel-Wise Classification in Hippocampus Histological Images

This paper presents a method for pixel-wise classification applied for the first time on hippocampus histological images. The goal is achieved by representing pixels in a 14-D vector, composed of grey-level information and moment invariants. Then, several popular machine learning models are used to categorize them, and multiple metrics are computed to evaluate the performance of the different models. The multilayer perceptron, random forest, support vector machine, and radial basis function networks were compared, achieving the multilayer perceptron model the highest result on accuracy metric, AUC, and F ₁ score with highly satisfactory results for substituting a manual classification task, due to an expert opinion in the hippocampus histological images.

Automated Brain Region Segmentation for Single Cell Resolution Histological Images Based on Markov Random Field

The brain consists of massive regions with different functions and the precise delineation of brain region boundaries is important for brain region identification and atlas illustration. In this paper we propose a hierarchical Markov random field (MRF) model for brain region segmentation, where a MRF is applied to the downsampled low-resolution images and the result is used to initialize another MRF for the original high-resolution images. A fractional differential feature and a gray level co-occurrence matrix are extracted as the observed vector for the MRF and a new potential energy function, which can capture the spatial characteristic of brain regions, is proposed as well. A fuzzy entropy criterion is used to fine-tune the boundary from the hierarchical MRF model. We test the model both on synthetic images and real histological mouse brain images. The result suggests that the model can accurately identify target regions and even the whole mouse brain outline as a special case. An interesting observation is that the model cannot only segment regions with different cell density but also can segment regions with similar cell density and different cell morphology texture. Thus this model shows great potential for building the high-resolution 3D brain atlas.

Multi-Atlas Segmentation of Anatomical Brain Structures Using Hierarchical Hypergraph Learning

Accurate segmentation of anatomical brain structures is crucial for many neuroimaging applications, e.g., early brain development studies and the study of imaging biomarkers of neurodegenerative diseases. Although multi-atlas segmentation (MAS) has achieved many successes in the medical imaging area, this approach encounters limitations in segmenting anatomical structures associated with poor image contrast. To address this issue, we propose a new MAS method that uses a hypergraph learning framework to model the complex subject-within and subject-to-atlas image voxel relationships and propagate the label on the atlas image to the target subject image. To alleviate the low-image contrast issue, we propose two strategies equipped with our hypergraph learning framework. First, we use a hierarchical strategy that exploits high-level context features for hypergraph construction. Because the context features are computed on the tentatively estimated probability maps, we can ultimately turn the hypergraph learning into a hierarchical model. Second, instead of only propagating the labels from the atlas images to the target subject image, we use a dynamic label propagation strategy that can gradually use increasing reliably identified labels from the subject image to aid in predicting the labels on the difficult-to-label subject image voxels. Compared with the state-of-the-art label fusion methods, our results show that the hierarchical hypergraph learning framework can substantially improve the robustness and accuracy in the segmentation of anatomical brain structures with low image contrast from magnetic resonance (MR) images.

A Combined Deep-Learning and Lattice Boltzmann Model for Segmentation of the Hippocampus in MRI

Segmentation of the hippocampus (HC) in magnetic resonance imaging (MRI) is an essential step for diagnosis and monitoring of several clinical situations such as Alzheimer's disease (AD), schizophrenia and epilepsy. Automatic segmentation of HC structures is challenging due to their small volume, complex shape, low contrast and discontinuous boundaries. The active contour model (ACM) with a statistical shape prior is robust. However, it is difficult to build a shape prior that is general enough to cover all possible shapes of the HC and that suffers the problems of complicated registration of the shape prior and the target object and of low efficiency. In this paper, we propose a semi-automatic model that combines a deep belief network (DBN) and the lattice Boltzmann (LB) method for the segmentation of HC. The training process of DBN consists of unsupervised bottom-up training and supervised training of a top restricted Boltzmann machine (RBM). Given an input image, the trained DBN is utilized to infer the patient-specific shape prior of the HC. The specific shape prior is not only used to determine the initial contour, but is also introduced into the LB model as part of the external force to refine the segmentation. We used a subset of OASIS-1 as the training set and the preliminary release of EADC-ADNI as the testing set. The segmentation results of our method have good correlation and consistency with the manual segmentation results.

Association between hippocampal volume change and change in memory following electroconvulsive therapy in late-life depression

OBJECTIVE

Electroconvulsive therapy (ECT)-induced hippocampal volume change (HVC) has been repeatedly described in recent years. The similar time course of HVC and ECT-related cognitive effects suggest a relation, that is to date, understudied. This study investigates whether HVC following ECT predicts the change in memory performance six months after the end of the ECT treatment.

METHODS

Hippocampal volume (HV) was measured via high-resolution 3D T1-weighted images in 88 patients with late-life depression, within 1 week before and after ECT. Memory performance was assessed before and six months after ECT. Multiple linear regression was used to examine whether change in memory performance could be predicted based on ECT-induced changes in HV.

RESULTS

Larger right absolute HVC predicts less pronounced improvement on the VAT (visual memory) in the whole sample. For the 8-Word Test (verbal memory), Category Fluency Test (semantic memory), and MMSE, the effect is only present in patients who switched from right unilateral to bitemporal stimulation after six ECT sessions. Absolute HVC in the left hemisphere was not significantly related to cognitive change.

CONCLUSION

A larger absolute change in right HV during ECT is associated with less improvement in memory performance up to 6 months post-ECT.

Brain Volumes and Longitudinal Cognitive Change: A Population-based Study

OBJECTIVE

To investigate the association of brain volumes, white matter lesion (WML) volumes, and lacunes, with cognitive decline in a population-based cohort of nondemented persons.

METHODS

Within the Rotterdam Study, 3624 participants underwent brain magnetic resonance imaging. Cognition was evaluated at baseline (2005 to 2009) and at the follow-up visit (2011 to 2013). We used a test battery that tapped into domains of executive function, information processing speed, motor speed, and memory. The volumetric measures assessed were total brain volume, lobar (gray matter and white matter) volumes, and hippocampal volumes. We also studied the association of WML volumes and lacunes with cognitive decline using linear regression models.

RESULTS

Total brain volume was associated with decline in global cognition, information processing, and motor speed (P<0.001) in analyses controlled for demographic and vascular factors. Specifically, smaller frontal and parietal lobes were associated with decline in information processing and motor speed, and smaller temporal and parietal lobes were associated with decline in general cognition and motor speed (P<0.001 for all tests). Total WML volume was associated with decline in executive function. Lobar WML volume, hippocampal volume, and lacunes were not associated with cognitive decline.

CONCLUSIONS

Lower brain volume is associated with subsequent cognitive decline. Although lower total brain volume was significantly associated with decline in global cognition, specific lobar volumes were associated with decline in certain cognitive domains.

Longitudinal Neuroimaging Hippocampal Markers for Diagnosing Alzheimer's Disease

Hippocampal atrophy measures from magnetic resonance imaging (MRI) are powerful tools for monitoring Alzheimer's disease (AD) progression. In this paper, we introduce a longitudinal image analysis framework based on robust registration and simultaneous hippocampal segmentation and longitudinal marker classification of brain MRI of an arbitrary number of time points. The framework comprises two innovative parts: a longitudinal segmentation and a longitudinal classification step. The results show that both steps of the longitudinal pipeline improved the reliability and the accuracy of the discrimination between clinical groups. We introduce a novel approach to the joint segmentation of the hippocampus across multiple time points; this approach is based on graph cuts of longitudinal MRI scans with constraints on hippocampal atrophy and supported by atlases. Furthermore, we use linear mixed effect (LME) modeling for differential diagnosis between clinical groups. The classifiers are trained from the average residue between the longitudinal marker of the subjects and the LME model. In our experiments, we analyzed MRI-derived longitudinal hippocampal markers from two publicly available datasets (Alzheimer's Disease Neuroimaging Initiative, ADNI and Minimal Interval Resonance Imaging in Alzheimer's Disease, MIRIAD). In test/retest reliability experiments, the proposed method yielded lower volume errors and significantly higher dice overlaps than the cross-sectional approach (volume errors: 1.55% vs 0.8%; dice overlaps: 0.945 vs 0.975). To diagnose AD, the discrimination ability of our proposal gave an area under the receiver operating characteristic (ROC) curve (AUC) [Formula: see text] 0.947 for the control vs AD, AUC [Formula: see text] 0.720 for mild cognitive impairment (MCI) vs AD, and AUC [Formula: see text] 0.805 for the control vs MCI.

Hippocampal volume change following ECT is mediated by rs699947 in the promotor region of VEGF

Several studies have shown that electroconvulsive therapy (ECT) results in increased hippocampal volume. It is likely that a multitude of mechanisms including neurogenesis, gliogenesis, synaptogenesis, angiogenesis, and vasculogenesis contribute to this volume increase. Neurotrophins, like vascular endothelial growth factor (VEGF) and brain-derived neurotrophic factor (BDNF) seem to play a crucial mediating role in several of these mechanisms. We hypothesized that two regulatory SNPs in the VEGF and BDNF gene influence the changes in hippocampal volume following ECT. We combined genotyping and brain MRI assessment in a sample of older adults suffering from major depressive disorder to test this hypothesis. Our results show an effect of rs699947 (in the promotor region of VEGF) on hippocampal volume changes following ECT. However, we did not find a clear effect of rs6265 (in BDNF). To the best of our knowledge, this is the first study investigating possible genetic mechanisms involved in hippocampal volume change during ECT treatment.

Spatially Regularized Shape Analysis of the Hippocampus Using P-Spline Based Shape Regression

Shape analysis is increasingly becoming important to study changes in brain structures in relation to clinical neurological outcomes. This is a challenging task due to the high dimensionality of shape representations and the often limited number of available shapes. Current techniques counter the poor ratio between dimensions and sample size by using regularization in shape space, but do not take into account the spatial relations within the shapes. This can lead to models that are biologically implausible and difficult to interpret. We propose to use P-spline based regression, which combines a generalized linear model (GLM) with the coefficients described as B-splines and a penalty term that constrains the regression coefficients to be spatially smooth. Owing to the GLM, this method can naturally predict both continuous and discrete outcomes and can include non-spatial covariates without penalization. We evaluated our method on hippocampus shapes extracted from magnetic resonance (MR) images of 510 non-demented, elderly people. We related the hippocampal shape to age, memory score, and sex. The proposed method retained the good performance of current techniques, such as ridge regression, but produced smoother coefficient fields that are easier to interpret.

Automatic Labeling of MR Brain Images Through the Hashing Retrieval Based Atlas Forest

The multi-atlas method is one of the efficient and common automatic labeling method, which uses the prior information provided by expert-labeled images to guide the labeling of the target. However, most multi-atlas-based methods depend on the registration that may not give the correct information during the label propagation. To address the issue, we designed a new automatic labeling method through the hashing retrieval based atlas forest. The proposed method propagates labels without registration to reduce the errors, and constructs a target-oriented learning model to integrate information among the atlases. This method innovates a coarse classification strategy to preprocess the dataset, which retains the integrity of dataset and reduces computing time. Furthermore, the method considers each voxel in the atlas as a sample and encodes these samples with hashing for the fast sample retrieval. In the stage of labeling, the method selects suitable samples through hashing learning and trains atlas forests by integrating the information from the dataset. Then, the trained model is used to predict the labels of the target. Experimental results on two datasets illustrated that the proposed method is promising in the automatic labeling of MR brain images.

MRI morphology of the hippocampus in drug-resistant temporal lobe epilepsy: Shape inflation of left hippocampus and correlation of right-sided hippocampal volume and shape with visuospatial function in patients with right-sided TLE

We sought to quantify the morphology in vivo of hippocampi in patients with drug resistant temporal lobe epilepsy (TLE) via magnetic resonance imaging (MRI), prior to temporal lobe resection, and the correlation of surface-based shape analysis of morphology and clinical cognitive function. Thirty patients with drug-resistant TLE and twenty healthy controls underwent clinical neuropsychological testing, and brain MRI at Lund University Hospital prior to hippocampal resection. A neuroradiologist categorised radiological findings into normal hippocampus, subtle changes or definite hippocampal sclerosis. We manually segmented MRI of the hippocampus of participants using ANALYZE 11.0 software; and analysed hippocampal shape using SPHARM-PDM software. For radiologist visual-ratings of definite left hippocampal sclerosis in those with left-sided TLE, hippocampal volumes were significantly smaller compared to normal controls. In right-sided TLE we found contralateral shape inflation of the left hippocampus, partially confirming previous shape analytic studies of the hippocampus in TLE. We found significant correlation of volume and surface deflation of the right hippocampus in right-sided TLE with reduced performance on the two right-lateralised visuospatial memory tests, the Rey Complex Figure Test (Immediate and Delayed recall) and the Recognition Memory Test for faces. Decreased hippocampal volume was correlated with poorer performance on these tasks. The morphology of the hippocampus can be quantified via neuroimaging shape analysis in TLE. Contralateral shape inflation of the left hippocampus in right-sided TLE is intriguing, and may result from functional compensation and/or abnormal tissue. In right-sided TLE, hippocampal structural integrity, quantified as hippocampal shape, is correlated with lateralised visuospatial function.

Disease Pathway Cut for Multi-Target drugs

Background

Biomarker discovery studies have been moving the focus from a single target gene to a set of target genes. However, the number of target genes in a drug should be minimum to avoid drug side-effect or toxicity. But still, the set of target genes should effectively block all possible paths of disease progression.

Methods

In this article, we propose a network based computational analysis for target gene identification for multi-target drugs. The min-cut algorithm is employed to cut all the paths from onset genes to apoptotic genes on a disease pathway. If the pathway network is completely disconnected, development of disease will not further go on. The genes corresponding to the end points of the cutting edges are identified as candidate target genes for a multi-target drug.

Results and conclusions

The proposed method was applied to 10 disease pathways. In total, thirty candidate genes were suggested. The result was validated with gene set enrichment analysis software, PubMed literature review and de facto drug targets.

A New Multi-Atlas Registration Framework for Multimodal Pathological Images Using Conventional Monomodal Normal Atlases

Using multi-atlas registration (MAR), information carried by atlases can be transferred onto a new input image for the tasks of region of interest (ROI) segmentation, anatomical landmark detection, and so on. Conventional atlases used in MAR methods are monomodal and contain only normal anatomical structures. Therefore, the majority of MAR methods cannot handle input multimodal pathological images, which are often collected in routine image-based diagnosis. This is because registering monomodal atlases with normal appearances to multimodal pathological images involves two major problems: (1) missing imaging modalities in the monomodal atlases, and (2) influence from pathological regions. In this paper, we propose a new MAR framework to tackle these problems. In this framework, a deep learning based image synthesizers are applied for synthesizing multimodal normal atlases from conventional monomodal normal atlases. To reduce the influence from pathological regions, we further propose a multimodal lowrank approach to recover multimodal normal-looking images from multimodal pathological images. Finally, the multimodal normal atlases can be registered to the recovered multimodal images in a multi-channel way. We evaluate our MAR framework via brain ROI segmentation of multimodal tumor brain images. Due to the utilization of multimodal information and the reduced influence from pathological regions, experimental results show that registration based on our method is more accurate and robust, leading to significantly improved brain ROI segmentation compared with state-of-the-art methods.

Automated and manual hippocampal segmentation techniques: Comparison of results, reproducibility and clinical applicability

BACKGROUND

Imaging techniques used to measure hippocampal atrophy are key to understanding the clinical progression of Alzheimer's disease (AD). Various semi-automated hippocampal segmentation techniques are available and require human expert input to learn how to accurately segment new data. Our goal was to compare 1) the performance of our automated hippocampal segmentation technique relative to manual segmentations, and 2) the performance of our automated technique when provided with a training set from two different raters. We also explored the ability of hippocampal volumes obtained using manual and automated hippocampal segmentations to predict conversion from MCI to AD.

METHODS

We analyzed 161 1.5 T T1-weighted brain magnetic resonance images (MRI) from the ADCS Donepezil/Vitamin E clinical study. All subjects carried a diagnosis of mild cognitive impairment (MCI). Three different segmentation outputs (one produced by manual tracing and two produced by a semi-automated algorithm trained with training sets developed by two raters) were compared using single measure intraclass correlation statistics (smICC). The radial distance method was used to assess each segmentation technique's ability to detect hippocampal atrophy in 3D. We then compared how well each segmentation method detected baseline hippocampal differences between MCI subjects who remained stable (MCInc) and those who converted to AD (MCIc) during the trial. Our statistical maps were corrected for multiple comparisons using permutation-based statistics with a threshold of p < .01.

RESULTS

Our smICC analyses showed significant agreement between the manual and automated hippocampal segmentations from rater 1 [right smICC = 0.78 (95%CI 0.72-0.84); left smICC = 0.79 (95%CI 0.72-0.85)], the manual segmentations from rater 1 versus the automated segmentations from rater 2 [right smICC = 0.78 (95%CI 0.7-0.84); left smICC = 0.78 (95%CI 0.71-0.84)], and the automated segmentations of rater 1 versus rater 2 [right smICC = 0.97 (95%CI 0.96-0.98); left smICC = 0.97 (95%CI 0.96-0.98)]. All three segmentation methods detected significant CA1 and subicular atrophy in MCIc compared to MCInc at baseline (manual: right pcorrected = 0.0112, left pcorrected = 0.0006; automated rater 1: right pcorrected = 0.0318, left pcorrected = 0.0302; automated rater 2: right pcorrected = 0.0029, left pcorrected = 0.0166).

CONCLUSIONS

The hippocampal volumes obtained with a fast semi-automated segmentation method were highly comparable to the ones obtained with the labor-intensive manual segmentation method. The AdaBoost automated hippocampal segmentation technique is highly reliable allowing the efficient analysis of large data sets.

Multi-Atlas Segmentation Using Partially Annotated Data: Methods and Annotation Strategies

Multi-atlas segmentation is a widely used tool in medical image analysis, providing robust and accurate results by learning from annotated atlas datasets. However, the availability of fully annotated atlas images for training is limited due to the time required for the labelling task. Segmentation methods requiring only a proportion of each atlas image to be labelled could therefore reduce the workload on expert raters tasked with annotating atlas images. To address this issue, we first re-examine the labelling problem common in many existing approaches and formulate its solution in terms of a Markov Random Field energy minimisation problem on a graph connecting atlases and the target image. This provides a unifying framework for multi-atlas segmentation. We then show how modifications in the graph configuration of the proposed framework enable the use of partially annotated atlas images and investigate different partial annotation strategies. The proposed method was evaluated on two Magnetic Resonance Imaging (MRI) datasets for hippocampal and cardiac segmentation. Experiments were performed aimed at (1) recreating existing segmentation techniques with the proposed framework and (2) demonstrating the potential of employing sparsely annotated atlas data for multi-atlas segmentation.

Supervoxel based method for multi-atlas segmentation of brain MR images

Multi-atlas segmentation has been widely applied to the analysis of brain MR images. However, the state-of-the-art techniques in multi-atlas segmentation, including both patch-based and learning-based methods, are strongly dependent on the pairwise registration or exhibit huge spatial inconsistency. The paper proposes a new segmentation framework based on supervoxels to solve the existing challenges of previous methods. The supervoxel is an aggregation of voxels with similar attributes, which can be used to replace the voxel grid. By formulating the segmentation as a tissue labeling problem associated with a maximum-a-posteriori inference in Markov random field, the problem is solved via a graphical model with supervoxels being considered as the nodes. In addition, a dense labeling scheme is developed to refine the supervoxel labeling results, and the spatial consistency is incorporated in the proposed method. The proposed approach is robust to the pairwise registration errors and of high computational efficiency. Extensive experimental evaluations on three publically available brain MR datasets demonstrate the effectiveness and superior performance of the proposed approach.

Coupled changes in hippocampal structure and cognitive ability in later life

Introduction

The hippocampus plays an important role in cognitive abilities which often decline with advancing age.

Methods

In a longitudinal study of community-dwelling adults, we investigated whether there were coupled changes in hippocampal structure and verbal memory, working memory, and processing speed between the ages of 73 (N = 655) and 76 years (N = 469). Hippocampal structure was indexed by hippocampal volume, hippocampal volume as a percentage of intracranial volume (H_ICV), fractional anisotropy (FA), mean diffusivity (MD), and longitudinal relaxation time (T1).

Results

Mean levels of hippocampal volume, H_ICV, FA, T1, and all three cognitive abilities domains decreased, whereas MD increased, from age 73 to 76. At baseline, higher hippocampal volume was associated with better working memory and verbal memory, but none of these correlations survived correction for multiple comparisons. Higher FA, lower MD, and lower T1 at baseline were associated with better cognitive abilities in all three domains; only the correlation between baseline hippocampal MD and T1, and change in the three cognitive domains, survived correction for multiple comparisons. Individuals with higher hippocampal MD at age 73 experienced a greater decline in all three cognitive abilities between ages 73 and 76. However, no significant associations with changes in cognitive abilities were found with hippocampal volume, FA, and T1 measures at baseline. Similarly, no significant associations were found between cognitive abilities at age 73 and changes in the hippocampal MRI biomarkers between ages 73 and 76.

Conclusion

Our results provide evidence to better understand how the hippocampus ages in healthy adults in relation to the cognitive domains in which it is involved, suggesting that better hippocampal MD at age 73 predicts less relative decline in three important cognitive domains across the next 3 years. It can potentially assist in diagnosing early stages of aging-related neuropathologies, because in some cases, accelerated decline could predict pathologies.

A Survey of Graph Cuts/Graph Search Based Medical Image Segmentation

Medical image segmentation is a fundamental and challenging problem for analyzing medical images. Among different existing medical image segmentation methods, graph-based approaches are relatively new and show good features in clinical applications. In the graph-based method, pixels or regions in the original image are interpreted into nodes in a graph. By considering Markov random field to model the contexture information of the image, the medical image segmentation problem can be transformed into a graph-based energy minimization problem. This problem can be solved by the use of minimum s-t cut/ maximum flow algorithm. This review is devoted to cut-based medical segmentation methods, including graph cuts and graph search for region and surface segmentation. Different varieties of cut-based methods, including graph-cuts-based methods, model integrated graph cuts methods, graph-search-based methods, and graph search/graph cuts based methods, are systematically reviewed. Graph cuts and graph search with deep learning technique are also discussed.

Association of Coffee Consumption with MRI Markers and Cognitive Function: A Population-Based Study

BACKGROUND

Coffee is one of the most widely consumed beverages worldwide and has been of considerable interest in research on cognition and dementia.

OBJECTIVE

To investigate the effect of coffee on preclinical brain MRI markers of dementia and cognitive performance.

METHODS

In 2,914 participants from the population-based Rotterdam Study (mean age: 59.3±7.2 years, 55% females), we assessed coffee consumption, performed brain MRI, and assessed cognition at baseline. To study cognitive change, cognitive assessment was repeated after 5 years of follow-up. Coffee consumption was analyzed continuously (per cup increase) and in categories (0-1, >1-3, >3 cups/day). Using logistic and linear regression, associations of coffee consumption with lacunar infarcts and brain tissue volumes on MRI, and cognitive performance (cross-sectional and longitudinal) were investigated, adjusting for relevant confounders.

RESULTS

We found that higher coffee consumption was associated with a lower prevalence of lacunar infarcts [odds ratio per cup increase: 0.88 (95% CI:0.79;0.98)], and smaller hippocampal volume [difference: -0.01 (95% CI:-0.02;0.00)]. Also, we found that the highest category of coffee consumption was associated with better performance on the Letter Digit Substitution Task [difference: 1.13(95% CI:0.39;1.88)], Word Fluency test [0.74(95% CI:0.04,1.45)], Stroop interference task [1.82(95% CI:0.23;3.41)], and worse performance on the 15-Word Learning test delayed recall [-0.38(95% CI:-0.74;-0.02)]. These associations were not found when cognition was analyzed longitudinally.

CONCLUSION

We found complex associations between coffee consumption, brain structure, and cognition. Higher coffee consumption was cross-sectionally associated with a lower occurrence of lacunar infarcts and better executive function, but also with smaller hippocampal volume and worse memory function.

Comparison of image intensity, local, and multi-atlas priors in brain tissue classification

PURPOSE

Automated and accurate tissue classification in three-dimensional brain magnetic resonance images is essential in volumetric morphometry or as a preprocessing step for diagnosing brain diseases. However, noise, intensity in homogeneity, and partial volume effects limit the classification accuracy of existing methods. This paper provides a comparative study on the contributions of three commonly used image information priors for tissue classification in normal brains: image intensity, local, and multi-atlas priors.

METHODS

We compared the effectiveness of the three priors by comparing the four methods modeling them: K-Means (KM), KM combined with a Markov Random Field (KM-MRF), multi-atlas segmentation (MAS), and the combination of KM, MRF, and MAS (KM-MRF-MAS). The key parameters and factors in each of the four methods are analyzed, and the performance of all the models is compared quantitatively and qualitatively on both simulated and real data.

RESULTS

The KM-MRF-MAS model that combines the three image information priors performs best.

CONCLUSIONS

The image intensity prior is insufficient to generate reasonable results for a few images. Introducing local and multi-atlas priors results in improved brain tissue classification. This study provides a general guide on what image information priors can be used for effective brain tissue classification.

The bumps under the hippocampus

Shown in every neuroanatomy textbook, a key morphological feature is the bumpy ridges, which we refer to as hippocampal dentation, on the inferior aspect of the hippocampus. Like the folding of the cerebral cortex, hippocampal dentation allows for greater surface area in a confined space. However, examining numerous approaches to hippocampal segmentation and morphology analysis, virtually all published 3D renderings of the hippocampus show the inferior surface to be quite smooth or mildly irregular; we have rarely seen the characteristic bumpy structure on reconstructed 3D surfaces. The only exception is a 9.4T postmortem study (Yushkevich et al. [2009]: NeuroImage 44:385-398). An apparent question is, does this indicate that this specific morphological signature can only be captured using ultra high-resolution techniques? Or, is such information buried in the data we commonly acquire, awaiting a computation technique that can extract and render it clearly? In this study, we propose an automatic and robust super-resolution technique that captures the fine scale morphometric features of the hippocampus based on common 3T MR images. The method is validated on 9.4T ultra-high field images and then applied on 3T data sets. This method opens possibilities of future research on the hippocampus and other sub-cortical structural morphometry correlating the degree of dentation with a range of diseases including epilepsy, Alzheimer's disease, and schizophrenia. Hum Brain Mapp 39:472-490, 2018. © 2017 Wiley Periodicals, Inc.

Neuroimaging Feature Terminology: A Controlled Terminology for the Annotation of Brain Imaging Features

Ontologies and terminologies are used for interoperability of knowledge and data in a standard manner among interdisciplinary research groups. Existing imaging ontologies capture general aspects of the imaging domain as a whole such as methodological concepts or calibrations of imaging instruments. However, none of the existing ontologies covers the diagnostic features measured by imaging technologies in the context of neurodegenerative diseases. Therefore, the Neuro-Imaging Feature Terminology (NIFT) was developed to organize the knowledge domain of measured brain features in association with neurodegenerative diseases by imaging technologies. The purpose is to identify quantitative imaging biomarkers that can be extracted from multi-modal brain imaging data. This terminology attempts to cover measured features and parameters in brain scans relevant to disease progression. In this paper, we demonstrate the systematic retrieval of measured indices from literature and how the extracted knowledge can be further used for disease modeling that integrates neuroimaging features with molecular processes.

ConvNet-Based Localization of Anatomical Structures in 3-D Medical Images

Localization of anatomical structures is a prerequisite for many tasks in a medical image analysis. We propose a method for automatic localization of one or more anatomical structures in 3-D medical images through detection of their presence in 2-D image slices using a convolutional neural network (ConvNet). A single ConvNet is trained to detect the presence of the anatomical structure of interest in axial, coronal, and sagittal slices extracted from a 3-D image. To allow the ConvNet to analyze slices of different sizes, spatial pyramid pooling is applied. After detection, 3-D bounding boxes are created by combining the output of the ConvNet in all slices. In the experiments, 200 chest CT, 100 cardiac CT angiography (CTA), and 100 abdomen CT scans were used. The heart, ascending aorta, aortic arch, and descending aorta were localized in chest CT scans, the left cardiac ventricle in cardiac CTA scans, and the liver in abdomen CT scans. Localization was evaluated using the distances between automatically and manually defined reference bounding box centroids and walls. The best results were achieved in the localization of structures with clearly defined boundaries (e.g., aortic arch) and the worst when the structure boundary was not clearly visible (e.g., liver). The method was more robust and accurate in localization multiple structures.

Hippocampus Segmentation Based on Local Linear Mapping

We propose local linear mapping (LLM), a novel fusion framework for distance field (DF) to perform automatic hippocampus segmentation. A k-means cluster method is propose for constructing magnetic resonance (MR) and DF dictionaries. In LLM, we assume that the MR and DF samples are located on two nonlinear manifolds and the mapping from the MR manifold to the DF manifold is differentiable and locally linear. We combine the MR dictionary using local linear representation to present the test sample, and combine the DF dictionary using the corresponding coefficients derived from local linear representation procedure to predict the DF of the test sample. We then merge the overlapped predicted DF patch to obtain the DF value of each point in the test image via a confidence-based weighted average method. This approach enabled us to estimate the label of the test image according to the predicted DF. The proposed method was evaluated on brain images of 35 subjects obtained from SATA dataset. Results indicate the effectiveness of the proposed method, which yields mean Dice similarity coefficients of 0.8697, 0.8770 and 0.8734 for the left, right and bi-lateral hippocampus, respectively.

Concatenated Spatially-localized Random Forests for Hippocampus Labeling in Adult and Infant MR Brain Images

Automatic labeling of the hippocampus in brain MR images is highly demanded, as it has played an important role in imaging-based brain studies. However, accurate labeling of the hippocampus is still challenging, partially due to the ambiguous intensity boundary between the hippocampus and surrounding anatomies. In this paper, we propose a concatenated set of spatially-localized random forests for multi-atlas-based hippocampus labeling of adult/infant brain MR images. The contribution in our work is two-fold. First, each forest classifier is trained to label just a specific sub-region of the hippocampus, thus enhancing the labeling accuracy. Second, a novel forest selection strategy is proposed, such that each voxel in the test image can automatically select a set of optimal forests, and then dynamically fuses their respective outputs for determining the final label. Furthermore, we enhance the spatially-localized random forests with the aid of the auto-context strategy. In this way, our proposed learning framework can gradually refine the tentative labeling result for better performance. Experiments show that, regarding the large datasets of both adult and infant brain MR images, our method owns satisfactory scalability by segmenting the hippocampus accurately and efficiently.

The effect of hippocampal function, volume and connectivity on posterior cingulate cortex functioning during episodic memory fMRI in mild cognitive impairment

Objectives

Diminished function of the posterior cingulate cortex (PCC) is a typical finding in early Alzheimer’s disease (AD). It is hypothesized that in early stage AD, PCC functioning relates to or reflects hippocampal dysfunction or atrophy. The aim of this study was to examine the relationship between hippocampus function, volume and structural connectivity, and PCC activation during an episodic memory task-related fMRI study in mild cognitive impairment (MCI).

Method

MCI patients (n = 27) underwent episodic memory task-related fMRI, 3D-T1w MRI, 2D T2-FLAIR MRI and diffusion tensor imaging. Stepwise linear regression analysis was performed to examine the relationship between PCC activation and hippocampal activation, hippocampal volume and diffusion measures within the cingulum along the hippocampus.

Results

We found a significant relationship between PCC and hippocampus activation during successful episodic memory encoding and correct recognition in MCI patients. We found no relationship between the PCC and structural hippocampal predictors.

Conclusions

Our results indicate a relationship between PCC and hippocampus activation during episodic memory engagement in MCI. This may suggest that during episodic memory, functional network deterioration is the most important predictor of PCC functioning in MCI.

Key Points

• PCC functioning during episodic memory relates to hippocampal functioning in MCI.

• PCC functioning during episodic memory does not relate to hippocampal structure in MCI.

• Functional network changes are an important predictor of PCC functioning in MCI.

Electronic supplementary material

The online version of this article (doi:10.1007/s00330-017-4768-1) contains supplementary material, which is available to authorized users.

Support Vector Machine with nonlinear-kernel optimization for lateralization of epileptogenic hippocampus in MR images

Surgical treatment is suggested for seizure control in medically intractable epilepsy patients. Detailed pre-surgical evaluation and lateralization using Magnetic Resonance Images (MRI) is expected to result in a successful surgical outcome. In this study, an optimized pattern recognition approach is proposed for lateralization of mesial Temporal Lobe Epilepsy (mTLE) patients using asymmetry of imaging indices of hippocampus. T1-weighted and Fluid-Attenuated Inversion Recovery (FLAIR) images of 76 symptomatic mTLE patients are considered. First, hippocampus is segmented using automatic and manual segmentation methods; then, volumetric and intensity features are extracted from the MR images. A nonlinear Support Vector Machine (SVM) with optimized Gaussian Radial Basis Function (GRBF) kernel is used to classify the imaging features. Using leave-one-out cross validation, this method results in a correct lateralization rate of 82%, a probability of detection for the left side of 0.90 (with false alarm probability of 0.04) and a probability of detection for the right side of 0.69 (with zero false alarm probability). The lateralization results are compared to linear SVM, multi-layer perceptron Artificial Neural Network (ANN), and volumetry and FLAIR asymmetry analysis. This lateralization method is suggested for pre-surgical evaluation using MRI before surgical treatment in mTLE patients. It achieves a more correct lateralization rate and fewer false positives.

Comparative performance evaluation of automated segmentation methods of hippocampus from magnetic resonance images of temporal lobe epilepsy patients

PURPOSE

Segmentation of the hippocampus from magnetic resonance (MR) images is a key task in the evaluation of mesial temporal lobe epilepsy (mTLE) patients. Several automated algorithms have been proposed although manual segmentation remains the benchmark. Choosing a reliable algorithm is problematic since structural definition pertaining to multiple edges, missing and fuzzy boundaries, and shape changes varies among mTLE subjects. Lack of statistical references and guidance for quantifying the reliability and reproducibility of automated techniques has further detracted from automated approaches. The purpose of this study was to develop a systematic and statistical approach using a large dataset for the evaluation of automated methods and establish a method that would achieve results better approximating those attained by manual tracing in the epileptogenic hippocampus.

METHODS

A template database of 195 (81 males, 114 females; age range 32-67 yr, mean 49.16 yr) MR images of mTLE patients was used in this study. Hippocampal segmentation was accomplished manually and by two well-known tools (FreeSurfer and hammer) and two previously published methods developed at their institution [Automatic brain structure segmentation (ABSS) and LocalInfo]. To establish which method was better performing for mTLE cases, several voxel-based, distance-based, and volume-based performance metrics were considered. Statistical validations of the results using automated techniques were compared with the results of benchmark manual segmentation. Extracted metrics were analyzed to find the method that provided a more similar result relative to the benchmark.

RESULTS

Among the four automated methods, ABSS generated the most accurate results. For this method, the Dice coefficient was 5.13%, 14.10%, and 16.67% higher, Hausdorff was 22.65%, 86.73%, and 69.58% lower, precision was 4.94%, -4.94%, and 12.35% higher, and the root mean square (RMS) was 19.05%, 61.90%, and 65.08% lower than LocalInfo, FreeSurfer, and hammer, respectively. The Bland-Altman similarity analysis revealed a low bias for the ABSS and LocalInfo techniques compared to the others.

CONCLUSIONS

The ABSS method for automated hippocampal segmentation outperformed other methods, best approximating what could be achieved by manual tracing. This study also shows that four categories of input data can cause automated segmentation methods to fail. They include incomplete studies, artifact, low signal-to-noise ratio, and inhomogeneity. Different scanner platforms and pulse sequences were considered as means by which to improve reliability of the automated methods. Other modifications were specially devised to enhance a particular method assessed in this study.

Relationship Between Hippocampal Volume, Serum BDNF, and Depression Severity Following Electroconvulsive Therapy in Late-Life Depression

Recent structural imaging studies have described hippocampal volume changes following electroconvulsive therapy (ECT). It has been proposed that serum brain-derived neurotrophic factor (sBDNF)-mediated neuroplasticity contributes critically to brain changes following antidepressant treatment. To date no studies have investigated the relationship between changes in hippocampal volume, mood, and sBDNF following ECT. Here, we combine these measurements in a longitudinal study of severe late-life unipolar depression (LLD). We treated 88 elderly patients with severe LLD twice weekly until remission (Montgomery-Åsberg Depression Rating Scale (MADRS) <10). sBDNF and MADRS were obtained before ECT (T0), after the sixth ECT (T1), 1 week after the last ECT (T2), 4 weeks after the last ECT (T3), and 6 months after the last ECT (T4). Hippocampal volumes were quantified by manual segmentation of 3T structural magnetic resonance images in 66 patients at T0 and T2 and in 23 patients at T0, T2, and T4. Linear mixed models (LMM) were used to examine the evolution of MADRS, sBDNF, and hippocampal volume over time. Following ECT, there was a significant decrease in MADRS scores and a significant increase in hippocampal volume. Hippocampal volume decreased back to baseline values at T4. Compared with T0, sBDNF levels remained unchanged at T1, T2, and T3. There was no coevolution between changes in MADRS scores, hippocampal volume, and sBDNF. Hippocampal volume increase following ECT is an independent neurobiological effect unrelated to sBDNF and depressive symptomatology, suggesting a complex mechanism of action of ECT in LLD.

Consistent Multi-Atlas Hippocampus Segmentation for Longitudinal MR Brain Images with Temporal Sparse Representation

In this paper, we propose a novel multi-atlas based longitudinal label fusion method with temporal sparse representation technique to segment hippocampi at all time points simultaneously. First, we use groupwise longitudinal registration to simultaneously (1) estimate a group-mean image of a subject image sequence and (2) register its all time-point images to the estimated group-mean image consistently over time. Then, by registering all atlases with the group-mean image, we can align all atlases longitudinally consistently to each time point of the subject image sequence. Finally, we propose a longitudinal label fusion method to propagate all atlas labels to the subject image sequence by simultaneously labeling a set of temporally-corresponded voxels with a temporal consistency constraint on sparse representation. Experimental results demonstrate that our proposed method can achieve more accurate and consistent hippocampus segmentation than the state-of-the-art counterpart methods.

Brain atrophy in Alzheimer's Disease and aging

Thanks to its safety and accessibility, magnetic resonance imaging (MRI) is extensively used in clinical routine and research field, largely contributing to our understanding of the pathophysiology of neurodegenerative disorders such as Alzheimer's disease (AD). This review aims to provide a comprehensive overview of the main findings in AD and normal aging over the past twenty years, focusing on the patterns of gray and white matter changes assessed in vivo using MRI. Major progresses in the field concern the segmentation of the hippocampus with novel manual and automatic segmentation approaches, which might soon enable to assess also hippocampal subfields. Advancements in quantification of hippocampal volumetry might pave the way to its broader use as outcome marker in AD clinical trials. Patterns of cortical atrophy have been shown to accurately track disease progression and seem promising in distinguishing among AD subtypes. Disease progression has also been associated with changes in white matter tracts. Recent studies have investigated two areas often overlooked in AD, such as the striatum and basal forebrain, reporting significant atrophy, although the impact of these changes on cognition is still unclear. Future integration of different MRI modalities may further advance the field by providing more powerful biomarkers of disease onset and progression.

Abnormality Detection via Iterative Deformable Registration and Basis-Pursuit Decomposition

We present a generic method for automatic detection of abnormal regions in medical images as deviations from a normative data base. The algorithm decomposes an image, or more broadly a function defined on the image grid, into the superposition of a normal part and a residual term. A statistical model is constructed with regional sparse learning to represent normative anatomical variations among a reference population (e.g., healthy controls), in conjunction with a Markov random field regularization that ensures mutual consistency of the regional learning among partially overlapping image blocks. The decomposition is performed in a principled way so that the normal part fits well with the learned normative model, while the residual term absorbs pathological patterns, which may then be detected through a statistical significance test. The decomposition is applied to multiple image features from an individual scan, detecting abnormalities using both intensity and shape information. We form an iterative scheme that interleaves abnormality detection with deformable registration, gradually improving robustness of the spatial normalization and precision of the detection. The algorithm is evaluated with simulated images and clinical data of brain lesions, and is shown to achieve robust deformable registration and localize pathological regions simultaneously. The algorithm is also applied on images from Alzheimer's disease patients to demonstrate the generality of the method.

An Automatic Method for Nucleus Boundary Segmentation Based on a Closed Cubic Spline

The recognition of brain nuclei is the basis for localizing brain functions. Traditional histological research, represented by atlas illustration, achieves the goal of nucleus boundary recognition by manual delineation, but it has become increasingly difficult to extend this handmade method to delineating brain regions and nuclei from large datasets acquired by the recently developed single-cell-resolution imaging techniques for the whole brain. Here, we propose a method based on a closed cubic spline (CCS), which can automatically segment the boundaries of nuclei that differ to a relatively high degree in cell density from the surrounding areas and has been validated on model images and Nissl-stained microimages of mouse brain. It may even be extended to the segmentation of target outlines on MRI or CT images. The proposed method for the automatic extraction of nucleus boundaries would greatly accelerate the illustration of high-resolution brain atlases.

Optimization-based interactive segmentation interface for multiregion problems

Interactive segmentation is becoming of increasing interest to the medical imaging community in that it combines the positive aspects of both manual and automated segmentation. However, general-purpose tools have been lacking in terms of segmenting multiple regions simultaneously with a high degree of coupling between groups of labels. Hierarchical max-flow segmentation has taken advantage of this coupling for individual applications, but until recently, these algorithms were constrained to a particular hierarchy and could not be considered general-purpose. In a generalized form, the hierarchy for any given segmentation problem is specified in run-time, allowing different hierarchies to be quickly explored. We present an interactive segmentation interface, which uses generalized hierarchical max-flow for optimization-based multiregion segmentation guided by user-defined seeds. Applications in cardiac and neonatal brain segmentation are given as example applications of its generality.

Energy minimization in medical image analysis: Methodologies and applications

Energy minimization is of particular interest in medical image analysis. In the past two decades, a variety of optimization schemes have been developed. In this paper, we present a comprehensive survey of the state-of-the-art optimization approaches. These algorithms are mainly classified into two categories: continuous method and discrete method. The former includes Newton-Raphson method, gradient descent method, conjugate gradient method, proximal gradient method, coordinate descent method, and genetic algorithm-based method, while the latter covers graph cuts method, belief propagation method, tree-reweighted message passing method, linear programming method, maximum margin learning method, simulated annealing method, and iterated conditional modes method. We also discuss the minimal surface method, primal-dual method, and the multi-objective optimization method. In addition, we review several comparative studies that evaluate the performance of different minimization techniques in terms of accuracy, efficiency, or complexity. These optimization techniques are widely used in many medical applications, for example, image segmentation, registration, reconstruction, motion tracking, and compressed sensing. We thus give an overview on those applications as well.