Patch-based segmentation using expert priors: application to hippocampus and ventricle segmentation

Multi-atlas label fusion with random local binary pattern features: Application to hippocampus segmentation

Automatic and reliable segmentation of the hippocampus from magnetic resonance (MR) brain images is extremely important in a variety of neuroimage studies. To improve the hippocampus segmentation performance, a local binary pattern based feature extraction method is developed for machine learning based multi-atlas hippocampus segmentation. Under the framework of multi-atlas image segmentation (MAIS), a set of selected atlases are registered to images to be segmented using a non-linear image registration algorithm. The registered atlases are then used as training data to build linear regression models for segmenting the images based on the image features, referred to as random local binary pattern (RLBP), extracted using a novel image feature extraction method. The RLBP based MAIS algorithm has been validated for segmenting hippocampus based on a data set of 135 T1 MR images which are from the Alzheimer’s Disease Neuroimaging Initiative database (adni.loni.usc.edu). By using manual segmentation labels produced by experienced tracers as the standard of truth, six segmentation evaluation metrics were used to evaluate the image segmentation results by comparing automatic segmentation results with the manual segmentation labels. We further computed Cohen’s d effect size to investigate the sensitivity of each segmenting method in detecting volumetric differences of the hippocampus between different groups of subjects. The evaluation results showed that our method was competitive to state-of-the-art label fusion methods in terms of accuracy. Hippocampal volumetric analysis showed that the proposed RLBP method performed well in detecting the volumetric differences of the hippocampus between groups of Alzheimer’s disease patients, mild cognitive impairment subjects, and normal controls. These results have demonstrated that the RLBP based multi-atlas image segmentation method could facilitate efficient and accurate extraction of the hippocampus and may help predict Alzheimer’s disease. The codes of the proposed method is available (https://www.nitrc.org/frs/?group_id=1242).

High-order Feature Learning for Multi-atlas based Label Fusion: Application to Brain Segmentation with MRI

Multi-atlas based segmentation methods have shown their effectiveness in brain regions-of-interesting (ROIs) segmentation, by propagating labels from multiple atlases to a target image based on the similarity between patches in the target image and multiple atlas images. Most of the existing multiatlas based methods use image intensity features to calculate the similarity between a pair of image patches for label fusion. In particular, using only low-level image intensity features cannot adequately characterize the complex appearance patterns (e.g., the high-order relationship between voxels within a patch) of brain magnetic resonance (MR) images. To address this issue, this paper develops a high-order feature learning framework for multi-atlas based label fusion, where high-order features of image patches are extracted and fused for segmenting ROIs of structural brain MR images. Specifically, an unsupervised feature learning method (i.e., means-covariances restricted Boltzmann machine, mcRBM) is employed to learn high-order features (i.e., mean and covariance features) of patches in brain MR images. Then, a group-fused sparsity dictionary learning method is proposed to jointly calculate the voting weights for label fusion, based on the learned high-order and the original image intensity features. The proposed method is compared with several state-of-the-art label fusion methods on ADNI, NIREP and LONI-LPBA40 datasets. The Dice ratio achieved by our method is 88:30%, 88:83%, 79:54% and 81:02% on left and right hippocampus on the ADNI, NIREP and LONI-LPBA40 datasets, respectively, while the best Dice ratio yielded by the other methods are 86:51%, 87:39%, 78:48% and 79:65% on three datasets, respectively.

Normative hippocampal volumetric measurements using magnetic resonance imaging

Background/aim

A wide variety of neurological and psychiatric disorders have been shown to be closely related to changes in hippocampal volume (HV). It appears that hippocampal volumetry will be an indispensable part of clinical practice for a number of neuropsychiatric disorders in the near future. The aim of this study was to establish a normative data set for HV according to age and sex in the general population.

Materials and methods

Hippocampal magnetic resonance imaging scans of 302 healthy volunteers were obtained using a 1.5 T unit with a 20-channel head coil. The hippocampal volumetric assessment was conducted using the volBrain fully automated segmentation algorithm on coronal oblique T1-weighted magnetization prepared rapid gradient-echo (MP-RAGE) images obtained perpendicular to the long axis of the hippocampus. The mean values of HV of groups according to age and sex were calculated. The associations between HV and age and sex were analyzed.

Results

The mean HV of the study group was found to be 3.81 ± 0.46 cm3. We found that the mean HV of males (3.94 ± 0.49 cm3) was significantly higher than that of females (3.74 ± 0.42 cm3), and the mean right HV (3.86 ± 0.48 cm3) was significantly higher than that of the left HV (3.78 ± 0.49 cm3) (P = 0.001). Among both females and males, there were statistically significant but poor negative correlations between age and volumetric measurements of both the right and the left hippocampi (P < 0.05).

Conclusion

The normative hippocampal volumetric data obtained in this study may be beneficial in clinical applications for many neuropsychiatric diseases, especially for mesial temporal sclerosis and cognitive disorders.

Accurate and robust segmentation of neuroanatomy in T1-weighted MRI by combining spatial priors with deep convolutional neural networks

Neuroanatomical segmentation in magnetic resonance imaging (MRI) of the brain is a prerequisite for quantitative volume, thickness, and shape measurements, as well as an important intermediate step in many preprocessing pipelines. This work introduces a new highly accurate and versatile method based on 3D convolutional neural networks for the automatic segmentation of neuroanatomy in T1‐weighted MRI. In combination with a deep 3D fully convolutional architecture, efficient linear registration‐derived spatial priors are used to incorporate additional spatial context into the network. An aggressive data augmentation scheme using random elastic deformations is also used to regularize the networks, allowing for excellent performance even in cases where only limited labeled training data are available. Applied to hippocampus segmentation in an elderly population (mean Dice coefficient = 92.1%) and subcortical segmentation in a healthy adult population (mean Dice coefficient = 89.5%), we demonstrate new state‐of‐the‐art accuracies and a high robustness to outliers. Further validation on a multistructure segmentation task in a scan–rescan dataset demonstrates accuracy (mean Dice coefficient = 86.6%) similar to the scan–rescan reliability of expert manual segmentations (mean Dice coefficient = 86.9%), and improved reliability compared to both expert manual segmentations and automated segmentations using FIRST. Furthermore, our method maintains a highly competitive runtime performance (e.g., requiring only 10 s for left/right hippocampal segmentation in 1 × 1 × 1 mm³ MNI stereotaxic space), orders of magnitude faster than conventional multiatlas segmentation methods.

Hippocampus Segmentation Based on Iterative Local Linear Mapping With Representative and Local Structure-Preserved Feature Embedding

Hippocampus segmentation plays a significant role in mental disease diagnoses, such as Alzheimer's disease, epilepsy, and so on. Patch-based multi-atlas segmentation (PBMAS) approach is a popular method for hippocampus segmentation and has achieved a promising result. However, the PBMAS approach needs high computation cost due to registration and the segmentation accuracy is subject to the registration accuracy. In this paper, we propose a novel method based on iterative local linear mapping (ILLM) with the representative and local structure-preserved feature embedding to achieve accurate and robust hippocampus segmentation with no need for registration. In the proposed approach, semi-supervised deep autoencoder (SSDA) exploits unsupervised deep autoencoder and local structure-preserved manifold regularization to nonlinearly transform the extracted magnetic resonance (MR) patch to embedded feature manifold, whose adjacent relationship is similar to the signed distance map (SDM) patch manifold. Local linear mapping is used to preliminarily predict SDM patch corresponding to the MR patch. Subsequently, threshold segmentation generates a preliminary segmentation. The ILLM refines the segmentation result iteratively by ensuring the local constraints of embedded feature manifold and SDM patch manifold using a space-constrained dictionary update. Thus, a refined segmentation is obtained with no need for registration. The experiments on 135 subjects from ADNI dataset show that the proposed approach is superior to the state-of-the-art PBMAS and classification-based approaches with mean Dice similarity coefficients of 0.8852±0.0203 and 0.8783 ± 0.0251 for bilateral hippocampus segmentation of 1.5T and 3.0T datasets, respectively.

PSACNN: Pulse sequence adaptive fast whole brain segmentation

With the advent of convolutional neural networks (CNN), supervised learning methods are increasingly being used for whole brain segmentation. However, a large, manually annotated training dataset of labeled brain images required to train such supervised methods is frequently difficult to obtain or create. In addition, existing training datasets are generally acquired with a homogeneous magnetic resonance imaging (MRI) acquisition protocol. CNNs trained on such datasets are unable to generalize on test data with different acquisition protocols. Modern neuroimaging studies and clinical trials are necessarily multi-center initiatives with a wide variety of acquisition protocols. Despite stringent protocol harmonization practices, it is very difficult to standardize the gamut of MRI imaging parameters across scanners, field strengths, receive coils etc., that affect image contrast. In this paper we propose a CNN-based segmentation algorithm that, in addition to being highly accurate and fast, is also resilient to variation in the input acquisition. Our approach relies on building approximate forward models of pulse sequences that produce a typical test image. For a given pulse sequence, we use its forward model to generate plausible, synthetic training examples that appear as if they were acquired in a scanner with that pulse sequence. Sampling over a wide variety of pulse sequences results in a wide variety of augmented training examples that help build an image contrast invariant model. Our method trains a single CNN that can segment input MRI images with acquisition parameters as disparate as T1-weighted and T2-weighted contrasts with only T1-weighted training data. The segmentations generated are highly accurate with state-of-the-art results (overall Dice overlap=0.94), with a fast run time (≈ 45 s), and consistent across a wide range of acquisition protocols.

Use of Flutemetamol F 18-Labeled Positron Emission Tomography and Other Biomarkers to Assess Risk of Clinical Progression in Patients With Amnestic Mild Cognitive Impairment

Importance

Patients with amnestic mild cognitive impairment (aMCI) may progress to clinical Alzheimer disease (AD), remain stable, or revert to normal. Earlier progression to AD among patients who were β-amyloid positive vs those who were β-amyloid negative has been previously observed. Current research now accepts that a combination of biomarkers could provide greater refinement in the assessment of risk for clinical progression.

Objective

To evaluate the ability of flutemetamol F 18 and other biomarkers to assess the risk of progression from aMCI to probable AD.

Design, Setting, and Participants

In this multicenter cohort study, from November 11, 2009, to January 16, 2014, patients with aMCI underwent positron emission tomography (PET) at baseline followed by local clinical assessments every 6 months for up to 3 years. Patients with aMCI (365 screened; 232 were eligible) were recruited from 28 clinical centers in Europe and the United States. Physicians remained strictly blinded to the results of PET, and the standard of truth was an independent clinical adjudication committee that confirmed or refuted local assessments. Flutemetamol F 18-labeled PET scans were read centrally as either negative or positive by 5 blinded readers with no knowledge of clinical status. Statistical analysis was conducted from February 19, 2014, to January 26, 2018.

Interventions

Flutemetamol F 18-labeled PET at baseline followed by up to 6 clinical visits every 6 months, as well as magnetic resonance imaging and multiple cognitive measures.

Main Outcomes and Measures

Time from PET to probable AD or last follow-up was plotted as a Kaplan-Meier survival curve; PET scan results, age, hippocampal volume, and aMCI stage were entered into Cox proportional hazards logistic regression analyses to identify variables associated with progression to probable AD.

Results

Of 232 patients with aMCI (118 women and 114 men; mean [SD] age, 71.1 [8.6] years), 98 (42.2%) had positive results detected on PET scan. By 36 months, the rates of progression to probable AD were 36.2% overall (81 of 224 patients), 53.6% (52 of 97) for patients with positive results detected on PET scan, and 22.8% (29 of 127) for patients with negative results detected on PET scan. Hazard ratios for association with progression were 2.51 (95% CI, 1.57-3.99; P < .001) for a positive β-amyloid scan alone (primary outcome measure), 5.60 (95% CI, 3.14-9.98; P < .001) with additional low hippocampal volume, and 8.45 (95% CI, 4.40-16.24; P < .001) when poorer cognitive status was added to the model.

Conclusions and Relevance

A combination of positive results of flutemetamol F 18-labeled PET, low hippocampal volume, and cognitive status corresponded with a high probability of risk of progression from aMCI to probable AD within 36 months.

Topological correction of infant white matter surfaces using anatomically constrained convolutional neural network

Reconstruction of accurate cortical surfaces without topological errors (i.e., handles and holes) from infant brain MR images is very important in early brain development studies. However, infant brain MR images typically suffer extremely low tissue contrast and dynamic imaging appearance patterns. Thus, it is inevitable to have large amounts of topological errors in the segmented infant brain tissue images, which lead to inaccurately reconstructed cortical surfaces with topological errors. To address this issue, inspired by recent advances in deep learning, we propose an anatomically constrained network for topological correction on infant cortical surfaces. Specifically, in our method, we first locate regions of potential topological defects by leveraging a topology-preserving level set method. Then, we propose an anatomically constrained network to correct those candidate voxels in the located regions. Since infant cortical surfaces often contain large and complex handles or holes, it is difficult to completely correct all errors using one-shot correction. Therefore, we further enroll these two steps into an iterative framework to gradually correct large topological errors. To the best of our knowledge, this is the first work to introduce deep learning approach for topological correction of infant cortical surfaces. We compare our method with the state-of-the-art methods on both simulated topological errors and real topological errors in human infant brain MR images. Moreover, we also validate our method on the infant brain MR images of macaques. All experimental results show the superior performance of the proposed method.

Automated Multi-Atlas Segmentation of Hippocampal and Extrahippocampal Subregions in Alzheimer's Disease at 3T and 7T: What Atlas Composition Works Best?

BACKGROUND

Multi-atlas segmentation, a popular technique implemented in the Automated Segmentation of Hippocampal Subfields (ASHS) software, utilizes multiple expert-labelled images ("atlases") to delineate medial temporal lobe substructures. This multi-atlas method is increasingly being employed in early Alzheimer's disease (AD) research, it is therefore becoming important to know how the construction of the atlas set in terms of proportions of controls and patients with mild cognitive impairment (MCI) and/or AD affects segmentation accuracy.

OBJECTIVE

To evaluate whether the proportion of controls in the training sets affects the segmentation accuracy of both controls and patients with MCI and/or early AD at 3T and 7T.

METHODS

We performed cross-validation experiments varying the proportion of control subjects in the training set, ranging from a patient-only to a control-only set. Segmentation accuracy of the test set was evaluated by the Dice similarity coeffiecient (DSC). A two-stage statistical analysis was applied to determine whether atlas composition is linked to segmentation accuracy in control subjects and patients, for 3T and 7T.

RESULTS

The different atlas compositions did not significantly affect segmentation accuracy at 3T and for patients at 7T. For controls at 7T, including more control subjects in the training set significantly improves the segmentation accuracy, but only marginally, with the maximum of 0.0003 DSC improvement per percent increment of control subject in the training set.

CONCLUSION

ASHS is robust in this study, and the results indicate that future studies investigating hippocampal subfields in early AD populations can be flexible in the selection of their atlas compositions.

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.

Multi-Modality Sparse Representation for Alzheimer's Disease Classification

BACKGROUND

Alzheimer's disease (AD) and mild cognitive impairment (MCI) are age-related neurodegenerative diseases characterized by progressive loss of memory and irreversible cognitive functions. The hippocampus, a brain area critical for learning and memory processes, is especially susceptible to damage at early stages of AD.

OBJECTIVE

We aimed to develop prediction model using a multi-modality sparse representation approach.

METHODS

We proposed a sparse representation approach to the hippocampus using structural T1-weighted magnetic resonance imaging (MRI) and 18-fluorodeoxyglucose-positron emission tomography (FDG-PET) to distinguish AD/MCI from healthy control subjects (HCs). We considered structural and function information for the hippocampus and applied a sparse patch-based approach to effectively reduce the dimensions of neuroimaging biomarkers.

RESULTS

In experiments using Alzheimer's Disease Neuroimaging Initiative data, our proposed method demonstrated more reliable than previous classification studies. The effects of different parameters on segmentation accuracy were also evaluated. The mean classification accuracy obtained with our proposed method was 0.94 for AD/HCs, 0.82 for MCI/HCs, and 0.86 for AD/MCI.

CONCLUSION

We extracted multi-modal features from automatically defined hippocampal regions of training subjects and found this method to be discriminative and robust for AD and MCI classification. The extraction of features in T1 and FDG-PET images is expected to improve classification performance due to the relationship between brain structure and function.

Automated segmentation of medial temporal lobe subregions on in vivo T1-weighted MRI in early stages of Alzheimer's disease

Medial temporal lobe (MTL) substructures are the earliest regions affected by neurofibrillary tangle pathology-and thus are promising biomarkers for Alzheimer's disease (AD). However, automatic segmentation of the MTL using only T1-weighted (T1w) magnetic resonance imaging (MRI) is challenging due to the large anatomical variability of the MTL cortex and the confound of the dura mater, which is commonly segmented as gray matter by state-of-the-art algorithms because they have similar intensity in T1w MRI. To address these challenges, we developed a novel atlas set, consisting of 15 cognitively normal older adults and 14 patients with mild cognitive impairment with a label explicitly assigned to the dura, that can be used by the multiatlas automated pipeline (Automatic Segmentation of Hippocampal Subfields [ASHS-T1]) for the segmentation of MTL subregions, including anterior/posterior hippocampus, entorhinal cortex (ERC), Brodmann areas (BA) 35 and 36, and parahippocampal cortex on T1w MRI. Cross-validation experiments indicated good segmentation accuracy of ASHS-T1 and that the dura can be reliably separated from the cortex (6.5% mislabeled as gray matter). Conversely, FreeSurfer segmented majority of the dura mater (62.4%) as gray matter and the degree of dura mislabeling decreased with increasing disease severity. To evaluate its clinical utility, we applied the pipeline to T1w images of 663 ADNI subjects and significant volume/thickness loss is observed in BA35, ERC, and posterior hippocampus in early prodromal AD and all subregions at later stages. As such, the publicly available new atlas and ASHS-T1 could have important utility in the early diagnosis and monitoring of AD and enhancing brain-behavior studies of these regions.

Extended multimodal whole-brain anatomical covariance analysis: detection of disrupted correlation networks related to amyloid deposition

Background

An anatomical covariance analysis (ACA) enables to elucidate inter-regional connections on a group basis, but little is known about the connections among white matter structures or among gray and white matter structures. Effect of including multiple magnetic resonance imaging (MRI) modalities into ACA framework in detecting white-to-white or gray-to-white connections is yet to be investigated.

New method

Proposed extended anatomical covariance analysis (eACA), analyzes correlations among gray and white matter structures (multi-structural) in various types of imaging modalities (T1-weighted images, T2 maps obtained from dual-echo sequences, and diffusion tensor images (DTI)). To demonstrate the capability to detect a disruption of the correlation network affected by pathology, we applied the eACA to two groups of cognitively-normal elderly individuals, one with (PiB+) and one without (PiB-) amyloid deposition in their brains.

Results

The volume of each anatomical structure was symmetric and functionally related structures formed a cluster. The pseudo-T2 value was highly homogeneous across the entire cortex in the PiB- group, while a number of physiological correlations were altered in the PiB + group. The DTI demonstrated unique correlation network among structures within the same phylogenetic portions of the brain that were altered in the PiB + group.

Comparison with Existing Method

The proposed eACA expands the concept of existing ACA to the connections among the white matter structures. The extension to other image modalities expands the way in which connectivity may be detected.

Conclusion

The eACA has potential to evaluate alterations of the anatomical network related to pathological processes.

An artificial neural network model for clinical score prediction in Alzheimer disease using structural neuroimaging measures

Background

The development of diagnostic and prognostic tools for Alzheimer disease is complicated by substantial clinical heterogeneity in prodromal stages. Many neuroimaging studies have focused on case–control classification and predicting conversion from mild cognitive impairment to Alzheimer disease, but predicting scores from clinical assessments (such as the Alzheimer’s Disease Assessment Scale or the Mini Mental State Examination) using MRI data has received less attention. Predicting clinical scores can be crucial in providing a nuanced prognosis and inferring symptomatic severity.

Methods

We predicted clinical scores at the individual level using a novel anatomically partitioned artificial neural network (APANN) model. The model combined input from 2 structural MRI measures relevant to the neurodegenerative patterns observed in Alzheimer disease: hippocampal segmentations and cortical thickness. We evaluated the performance of the APANN model with 10 rounds of 10-fold cross-validation in 3 experiments, using cohorts from the Alzheimer’s Disease Neuroimaging Initiative (ADNI): ADNI1, ADNI2 and ADNI1 + 2.

Results

Pearson correlation and root mean square error between the actual and predicted scores on the Alzheimer’s Disease Assessment Scale (ADNI1: r = 0.60; ADNI2: r = 0.68; ADNI1 + 2: r = 0.63) and Mini Mental State Examination (ADNI1: r = 0.52; ADNI2: r = 0.55; ADNI1 + 2: r = 0.55) showed that APANN can accurately infer clinical severity from MRI data.

Limitations

To rigorously validate the model, we focused primarily on large cross-sectional baseline data sets with only proof-of-concept longitudinal results.

Conclusion

The APANN provides a highly robust and scalable framework for predicting clinical severity at the individual level using high-dimensional, multimodal neuroimaging data.

3D whole brain segmentation using spatially localized atlas network tiles

Detailed whole brain segmentation is an essential quantitative technique in medical image analysis, which provides a non-invasive way of measuring brain regions from a clinical acquired structural magnetic resonance imaging (MRI). Recently, deep convolution neural network (CNN) has been applied to whole brain segmentation. However, restricted by current GPU memory, 2D based methods, downsampling based 3D CNN methods, and patch-based high-resolution 3D CNN methods have been the de facto standard solutions. 3D patch-based high resolution methods typically yield superior performance among CNN approaches on detailed whole brain segmentation (>100 labels), however, whose performance are still commonly inferior compared with state-of-the-art multi-atlas segmentation methods (MAS) due to the following challenges: (1) a single network is typically used to learn both spatial and contextual information for the patches, (2) limited manually traced whole brain volumes are available (typically less than 50) for training a network. In this work, we propose the spatially localized atlas network tiles (SLANT) method to distribute multiple independent 3D fully convolutional networks (FCN) for high-resolution whole brain segmentation. To address the first challenge, multiple spatially distributed networks were used in the SLANT method, in which each network learned contextual information for a fixed spatial location. To address the second challenge, auxiliary labels on 5111 initially unlabeled scans were created by multi-atlas segmentation for training. Since the method integrated multiple traditional medical image processing methods with deep learning, we developed a containerized pipeline to deploy the end-to-end solution. From the results, the proposed method achieved superior performance compared with multi-atlas segmentation methods, while reducing the computational time from >30 h to 15 min. The method has been made available in open source (https://github.com/MASILab/SLANTbrainSeg).

An Efficient Melanoma Diagnosis Approach Using Integrated HMF Multi-Atlas Map Based Segmentation

Melanoma is a life threading disease when it grows outside the corium layer of the skin. Mortality rates of the Melanoma cases are maximum among the skin cancer patients. The cost required for the treatment of advanced melanoma cases is very high and the survival rate is low. Numerous computerized dermoscopy systems are developed based on the combination of shape, texture and color features to facilitate early diagnosis of melanoma. The availability and cost of the dermoscopic imaging system is still an issue. To mitigate this issue, this paper presented an integrated segmentation and Third Dimensional (3D) feature extraction approach for the accurate diagnosis of melanoma. A multi-atlas method is applied for the image segmentation. The patch-based label fusion model is expressed in a Bayesian framework to improve the segmentation accuracy. A depth map is obtained from the Two-dimensional (2D) dermoscopic image for reconstructing the 3D skin lesion represented as structure tensors. The 3D shape features including the relative depth features are obtained. Streaks are the significant morphological terms of the melanoma in the radial growth phase. The proposed method yields maximum segmentation accuracy, sensibility, specificity and minimum cost function than the existing segmentation technique and classifier.

A Multi-Atlas Label Fusion Tool for Neonatal Brain MRI Parcellation and Quantification

Structure-by-structure analysis, in which the brain magnetic resonance imaging (MRI) is parcellated based on its anatomical units, is widely used to investigate chronological changes in morphology or signal intensity during normal development, as well as to identify the alterations seen in various diseases or conditions. The multi-atlas label fusion (MALF) method is considered a highly accurate parcellation approach, and anticipated for clinical application to quantitatively evaluate early developmental processes. However, the current MALF methods, which are designed for neonatal brain segmentations, are not widely available. In this study, we developed a T1-weighted, neonatal, multi-atlas repository and integrated it into the MALF-based brain segmentation tools in the cloud-based platform, MRICloud. The cloud platform ensures users instant access to the advanced MALF tool for neonatal brains, with no software or installation requirements for the client. The Web platform by braingps.mricloud.org will eliminate the dependence on a particular operating system (eg, Windows, Macintosh, or Linux) and the requirement for high computational performance of the user's computers. The MALF-based, fully automated, image parcellation could achieve excellent agreement with manual parcellation, and the whole and regional brain volumes quantified through this method demonstrated developmental trajectories comparable to those from a previous publication. This solution will make the latest MALF tools readily available to users, with minimum barriers, and will expedite and accelerate advancements in developmental neuroscience research, neonatology, and pediatric neuroradiology.

Feasibility of multi-atlas cardiac segmentation from thoracic planning CT in a probabilistic framework

Toxicity to cardiac and coronary structures is an important late morbidity for patients undergoing left-sided breast radiotherapy. Many current studies have relied on estimates of cardiac doses assuming standardised anatomy, with a calculated increase in relative risk of 7.4% per Gy (mean heart dose). To provide individualised estimates for dose, delineation of various cardiac structures on patient images is required. Automatic multi-atlas based segmentation can provide a consistent, robust solution, however there are challenges to this method. We are aiming to develop and validate a cardiac atlas and segmentation framework, with a focus on the limitations and uncertainties in the process. We present a probabilistic approach to segmentation, which provides a simple method to incorporate inter-observer variation, as well as a useful tool for evaluating the accuracy and sources of error in segmentation. A dataset consisting of 20 planning computed tomography (CT) images of Australian breast cancer patients with delineations of 17 structures (including whole heart, four chambers, coronary arteries and valves) was manually contoured by three independent observers, following a protocol based on a published reference atlas, with verification by a cardiologist. To develop and validate the segmentation framework a leave-one-out cross-validation strategy was implemented. Performance of the automatic segmentations was evaluated relative to inter-observer variability in manually-derived contours; measures of volume and surface accuracy (Dice similarity coefficient (DSC) and mean absolute surface distance (MASD), respectively) were used to compare automatic segmentation to the consensus segmentation from manual contours. For the whole heart, the resulting segmentation achieved a DSC of [Formula: see text], with a MASD of [Formula: see text] mm. Quantitative results, together with the analysis of probabilistic labelling, indicate the feasibility of accurate and consistent segmentation of larger structures, whereas this is not the case for many smaller structures, where a major limitation in segmentation accuracy is the inter-observer variability in manual contouring.

Lifespan Changes of the Human Brain In Alzheimer's Disease

Brain imaging studies have shown that slow and progressive cerebral atrophy characterized the development of Alzheimer's Disease (AD). Despite a large number of studies dedicated to AD, key questions about the lifespan evolution of AD biomarkers remain open. When does the AD model diverge from the normal aging model? What is the lifespan trajectory of imaging biomarkers for AD? How do the trajectories of biomarkers in AD differ from normal aging? To answer these questions, we proposed an innovative way by inferring brain structure model across the entire lifespan using a massive number of MRI (N = 4329). We compared the normal model based on 2944 control subjects with the pathological model based on 3262 patients (AD + Mild cognitive Impaired subjects) older than 55 years and controls younger than 55 years. Our study provides evidences of early divergence of the AD models from the normal aging trajectory before 40 years for the hippocampus, followed by the lateral ventricles and the amygdala around 40 years. Moreover, our lifespan model reveals the evolution of these biomarkers and suggests close abnormality evolution for the hippocampus and the amygdala, whereas trajectory of ventricular enlargement appears to follow an inverted U-shape. Finally, our models indicate that medial temporal lobe atrophy and ventricular enlargement are two mid-life physiopathological events characterizing AD brain.

Computer-Vision Techniques for Water-Fat Separation in Ultra High-Field MRI Local Specific Absorption Rate Estimation

OBJECTIVE

The purpose of this paper is to prove that computer-vision techniques allow synthesizing water-fat separation maps for local specific absorption rate (SAR) estimation, when patient-specific water-fat images are not available.

METHODS

We obtained ground truth head models by using patient-specific water-fat images. We obtained two different label-fusion water-fat models generating a water-fat multiatlas and applying the STAPLE and local-MAP-STAPLE label-fusion methods. We also obtained patch-based water-fat models applying a local group-wise weighted combination of the multiatlas. Electromagnetic (EM) simulations were performed, and B1+ magnitude and 10 g averaged SAR maps were generated.

RESULTS

We found local approaches provide a high DICE overlap (72.6 ± 10.2% fat and 91.6 ± 1.5% water in local-MAP-STAPLE, and 68.8 ± 8.2% fat and 91.1 ± 1.0% water in patch-based), low Hausdorff distances (18.6 ± 7.7 mm fat and 7.4 ± 11.2 mm water in local-MAP-STAPLE, and 16.4 ± 8.5 mm fat and 7.2 ± 11.8 mm water in patch-based) and a low error in volume estimation (15.6 ± 34.4% fat and 5.6 ± 4.1% water in the local-MAP-STAPLE, and 14.0 ± 17.7% fat and 4.7 ± 2.8% water in patch-based). The positions of the peak 10 g-averaged local SAR hotspots were the same for every model.

CONCLUSION

We have created patient-specific head models using three different computer-vision-based water-fat separation approaches and compared the predictions of B1+ field and SAR distributions generated by simulating these models. Our results prove that a computer-vision approach can be used for patient-specific water-fat separation, and utilized for local SAR estimation in high-field MRI.

SIGNIFICANCE

Computer-vision approaches can be used for patient-specific water-fat separation and for patient specific local SAR estimation, when water-fat images of the patient are not available.

Brain structure segmentation in the presence of multiple sclerosis lesions

Intensity-based multi-atlas segmentation strategies have shown to be particularly successful in segmenting brain images of healthy subjects. However, in the same way as most of the methods in the state of the art, their performance tends to be affected by the presence of MRI visible lesions, such as those found in multiple sclerosis (MS) patients. Here, we present an approach to minimize the effect of the abnormal lesion intensities on multi-atlas segmentation. We propose a new voxel/patch correspondence model for intensity-based multi-atlas label fusion strategies that leads to more accurate similarity measures, having a key role in the final brain segmentation. We present the theory of this model and integrate it into two well-known fusion strategies: Non-local Spatial STAPLE (NLSS) and Joint Label Fusion (JLF). The experiments performed show that our proposal improves the segmentation performance of the lesion areas. The results indicate a mean Dice Similarity Coefficient (DSC) improvement of 1.96% for NLSS (3.29% inside and 0.79% around the lesion masks) and, an improvement of 2.06% for JLF (2.31% inside and 1.42% around lesions). Furthermore, we show that, with the proposed strategy, the well-established preprocessing step of lesion filling can be disregarded, obtaining similar or even more accurate segmentation results.

•

We present an approach to improve multi-atlas brain parcellation of MS patients.

•

We integrate our model into 2 well-known segmentation strategies.

•

Our model improves the segmentation on the lesion areas.

•

The improvement on the lesion areas is also reflected in the global performance.

•

With our model, lesion filling can be omitted, obtaining at least similar results.

Adaptive Bayesian label fusion using kernel-based similarity metrics in hippocampus segmentation

The effectiveness of brain magnetic resonance imaging (MRI) as a useful evaluation tool strongly depends on the performed segmentation of associated tissues or anatomical structures. We introduce an enhanced brain segmentation approach of Bayesian label fusion that includes the construction of adaptive target-specific probabilistic priors using atlases ranked by kernel-based similarity metrics to deal with the anatomical variability of collected MRI data. In particular, the developed segmentation approach appraises patch-based voxel representation to enhance the voxel embedding in spaces with increased tissue discrimination, as well as the construction of a neighborhood-dependent model that addresses the label assignment of each region with a different patch complexity. To measure the similarity between the target and training atlases, we propose a tensor-based kernel metric that also includes the training labeling set. We evaluate the proposed approach, adaptive Bayesian label fusion using kernel-based similarity metrics, in the specific case of hippocampus segmentation of five benchmark MRI collections, including ADNI dataset, resulting in an increased performance (assessed through the Dice index) as compared to other recent works.

Hippocampal subfields segmentation in brain MR images using generative adversarial networks

Background

Segmenting the hippocampal subfields accurately from brain magnetic resonance (MR) images is a challenging task in medical image analysis. Due to the small structural size and the morphological complexity of the hippocampal subfields, the traditional segmentation methods are hard to obtain the ideal segmentation result.

Methods

In this paper, we proposed a hippocampal subfields segmentation method using generative adversarial networks. The proposed method can achieve the pixel-level classification of brain MR images by building an UG-net model and an adversarial model and training the two models against each other alternately. UG-net extracts local information and retains the interrelationship features between pixels. Moreover, the adversarial training implements spatial consistency among the generated class labels and smoothens the edges of class labels on segmented region.

Results

The evaluation has performed on the dataset obtained from center for imaging of neurodegenerative diseases (CIND) for CA1, CA2, DG, CA3, Head, Tail, SUB, ERC and PHG in hippocampal subfields, resulting in the dice similarity coefficient (DSC) of 0.919, 0.648, 0.903, 0.673, 0.929, 0.913, 0.906, 0.884 and 0.889 respectively. For the large subfields, such as Head and CA1 of hippocampus, the DSC was increased by 3.9% and 9.03% than state-of-the-art approaches, while for the smaller subfields, such as ERC and PHG, the segmentation accuracy was significantly increased 20.93% and 16.30% respectively.

Conclusion

The results show the improvement in performance of the proposed method, compared with other methods, which include approaches based on multi-atlas, hierarchical multi-atlas, dictionary learning and sparse representation and CNN. In implementation, the proposed method provides better results in hippocampal subfields segmentation.

Resting-state network complexity and magnitude changes in neonates with severe hypoxic ischemic encephalopathy

Resting-state functional magnetic resonance imaging has revealed disrupted brain network connectivity in adults and teenagers with cerebral palsy. However, the specific brain networks implicated in neonatal cases remain poorly understood. In this study, we recruited 14 term-born infants with mild hypoxic ischemic encephalopathy and 14 term-born infants with severe hypoxic ischemic encephalopathy from Changzhou Children’s Hospital, China. Resting-state functional magnetic resonance imaging data showed efficient small-world organization in whole-brain networks in both the mild and severe hypoxic ischemic encephalopathy groups. However, compared with the mild hypoxic ischemic encephalopathy group, the severe hypoxic ischemic encephalopathy group exhibited decreased local efficiency and a low clustering coefficient. The distribution of hub regions in the functional networks had fewer nodes in the severe hypoxic ischemic encephalopathy group compared with the mild hypoxic ischemic encephalopathy group. Moreover, nodal efficiency was reduced in the left rolandic operculum, left supramarginal gyrus, bilateral superior temporal gyrus, and right middle temporal gyrus. These results suggest that the topological structure of the resting state functional network in children with severe hypoxic ischemic encephalopathy is clearly distinct from that in children with mild hypoxic ischemic encephalopathy, and may be associated with impaired language, motion, and cognition. These data indicate that it may be possible to make early predictions regarding brain development in children with severe hypoxic ischemic encephalopathy, enabling early interventions targeting brain function. This study was approved by the Regional Ethics Review Boards of the Changzhou Children’s Hospital (approval No. 2013-001) on January 31, 2013. Informed consent was obtained from the family members of the children. The trial was registered with the Chinese Clinical Trial Registry (registration number: ChiCTR1800016409) and the protocol version is 1.0.

Automatic Deep Feature Learning via Patch-Based Deep Belief Network for Vertebrae Segmentation in CT Images

Precise automatic vertebra segmentation in computed tomography (CT) images is important for the quantitative analysis of vertebrae-related diseases but remains a challenging task due to high variation in spinal anatomy among patients. In this paper, we propose a deep learning approach for automatic CT vertebra segmentation named patch-based deep belief networks (PaDBNs). Our proposed PaDBN model automatically selects the features from image patches and then measures the differences between classes and investigates performance. The region of interest (ROI) is obtained from CT images. Unsupervised feature reduction contrastive divergence algorithm is applied for weight initialization, and the weights are optimized by layers in a supervised fine-tuning procedure. The discriminative learning features obtained from the steps above are used as input of a classifier to obtain the likelihood of the vertebrae. Experimental results demonstrate that the proposed PaDBN model can considerably reduce computational cost and produce an excellent performance in vertebra segmentation in terms of accuracy compared with state-of-the-art methods.

Patch spaces and fusion strategies in patch-based label fusion

In the field of multi-atlas segmentation, patch-based approaches have shown promising results in the segmentation of biomedical images. In the most common approach, registration is used to warp the atlases to the target space and then the warped atlas labelmaps are fused into a consensus segmentation based on local appearance information encoded in form of patches. The registration step establishes spatial correspondence, which is important to obtain anatomical priors. Patch-based label fusion in the target space has shown to produce very accurate segmentations although at the expense of registering all atlases to each target image. Moreover, appearance (i.e., patches) and label information used by label fusion is extracted from the warped atlases, which are subject to interpolation errors. In this work, we revisit and extend the patch-based label fusion framework, exploring the role of extracting this information from the native space of both atlases and target images, thus avoiding interpolation artifacts, but at the same time, we do it in a way that it does not sacrifice the anatomical priors derived by registration. We further propose a common formulation for two widely-used label fusion strategies, i.e., similarity-based and a particular type of learning-based label fusion. The proposed framework is evaluated on subcortical structure segmentation in adult brains and tissue segmentation in fetal brain MRI. Our results indicate that using atlas patches in their native space yields superior performance than warping the atlases to the target image. The learning-based approach tends to outperform the similarity-based approach, with the particularity that using patches in native space lessens the computational requirements of learning. As conclusion, the combination of learning-based label fusion and native atlas patches yields the best performance with reduced test times than conventional similarity-based approaches.

Comparing fully automated state-of-the-art cerebellum parcellation from magnetic resonance images

The human cerebellum plays an essential role in motor control, is involved in cognitive function (i.e., attention, working memory, and language), and helps to regulate emotional responses. Quantitative in-vivo assessment of the cerebellum is important in the study of several neurological diseases including cerebellar ataxia, autism, and schizophrenia. Different structural subdivisions of the cerebellum have been shown to correlate with differing pathologies. To further understand these pathologies, it is helpful to automatically parcellate the cerebellum at the highest fidelity possible. In this paper, we coordinated with colleagues around the world to evaluate automated cerebellum parcellation algorithms on two clinical cohorts showing that the cerebellum can be parcellated to a high accuracy by newer methods. We characterize these various methods at four hierarchical levels: coarse (i.e., whole cerebellum and gross structures), lobe, subdivisions of the vermis, and the lobules. Due to the number of labels, the hierarchy of labels, the number of algorithms, and the two cohorts, we have restricted our analyses to the Dice measure of overlap. Under these conditions, machine learning based methods provide a collection of strategies that are efficient and deliver parcellations of a high standard across both cohorts, surpassing previous work in the area. In conjunction with the rank-sum computation, we identified an overall winning method.

Current State of Image Guidance in Radiation Oncology: Implications for PTV Margin Expansion and Adaptive Therapy

Image guidance technology has evolved and seen widespread application in the past several decades. Advancements in the diagnostic imaging field have found new applications in radiation oncology and promoted the development of therapeutic devices with advanced imaging capabilities. A recent example is the development of linear accelerators that offer magnetic resonance imaging for real-time imaging and online adaptive planning. Volumetric imaging, in particular, offers more precise localization of soft tissue targets and critical organs which reduces setup uncertainty and permit the use of smaller setup margins. We present a review of the status of current imaging modalities available for radiation oncology and its impact on target margins and use for adaptive therapy.

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.

Differential Gray Matter Vulnerability in the 1 Year Following a Clinically Isolated Syndrome

Background and purpose: Whether some gray matter (GM) regions are differentially vulnerable at the early stages of MS is still unknown. The objective of this study is to investigate whether deep and cortical GM are differentially vulnerable after a clinically isolated syndrome (CIS) suggestive of multiple sclerosis (MS).

Methods: Fifty-six patients with CIS (PwCIS) and 38 healthy controls (HC) had conventional and diffusion tensor imaging (DTI) at baseline and 46 PwCIS and 20 HC were rescanned after 1 year. Deep GM (DGM) volumes, cortical thickness (CTh), and DTI metrics (FA: fractional anisotropy; MD: mean diffusivity) within these structures were calculated for each participant at each time-point and compared between PwCIS and HC. Linear regression models were used to investigate whether baseline DTI parameters could predict GM volume loss over time.

Results: At baseline, GM volumes did not differ between PwCIS and HC, but hippocampal MD was higher in PwCIS than HC (p < 0.01). Over 1 year, GM alterations became more widespread with putamen and hippocampus volumes decreasing in PwCIS (p < 0.01), and cortical thinning in different parts of the cortex along with a significant increase of MD. Hippocampus MD at baseline could predict its volume loss (R² = 0.159; p < 0.05) and cortical thinning was associated to microstructural damage (Spearman's rho ranging from −0.424 to −0.603 with p < 0.003).

Conclusion: Along with MS being a diffuse inflammatory disease, GM showed a differential vulnerability at the early stage spreading from hippocampus to the cortex. Hippocampus volume loss could be predicted by its MD at baseline.

Integrating Semi-supervised and Supervised Learning Methods for Label Fusion in Multi-Atlas Based Image Segmentation

A novel label fusion method for multi-atlas based image segmentation method is developed by integrating semi-supervised and supervised machine learning techniques. Particularly, our method is developed in a pattern recognition based multi-atlas label fusion framework. We build random forests classification models for each image voxel to be segmented based on its corresponding image patches of atlas images that have been registered to the image to be segmented. The voxelwise random forests classification models are then applied to the image to be segmented to obtain a probabilistic segmentation map. Finally, a semi-supervised label propagation method is adapted to refine the probabilistic segmentation map by propagating its reliable voxelwise segmentation labels, taking into consideration consistency of local and global image appearance of the image to be segmented. The proposed method has been evaluated for segmenting the hippocampus in MR images and compared with alternative machine learning based multi-atlas based image segmentation methods. The experiment results have demonstrated that our method could obtain competitive segmentation performance (average Dice index > 0.88), compared with alternative multi-atlas based image segmentation methods under comparison. Source codes of the methods under comparison are publicly available at www.nitrc.org/frs/?group_id=1242.

Iterative spatial fuzzy clustering for 3D brain magnetic resonance image supervoxel segmentation

BACKGROUND

Although supervoxel segmentation methods have been employed for brain Magnetic Resonance Image (MRI) processing and analysis, due to the specific features of the brain, including complex-shaped internal structures and partial volume effect, their performance remains unsatisfactory.

NEW METHODS

To address these issues, this paper presents a novel iterative spatial fuzzy clustering (ISFC) algorithm to generate 3D supervoxels for brain MRI volume based on prior knowledge. This work makes use of the common topology among the human brains to obtain a set of seed templates from a population-based brain template MRI image. After selecting the number of supervoxels, the corresponding seed template is projected onto the considered individual brain for generating reliable seeds. Then, to deal with the influence of partial volume effect, an efficient iterative spatial fuzzy clustering algorithm is proposed to allocate voxels to the seeds and to generate the supervoxels for the overall brain MRI volume.

RESULTS

The performance of the proposed algorithm is evaluated on two widely used public brain MRI datasets and compared with three other up-to-date methods.

CONCLUSIONS

The proposed algorithm can be utilized for several brain MRI processing and analysis, including tissue segmentation, tumor detection and segmentation, functional parcellation and registration.

Clinical validation of automated hippocampal segmentation in temporal lobe epilepsy

OBJECTIVE

To provide a multi-atlas framework for automated hippocampus segmentation in temporal lobe epilepsy (TLE) and clinically validate the results with respect to surgical lateralization and post-surgical outcome.

METHODS

We retrospectively identified 47 TLE patients who underwent surgical resection and 12 healthy controls. T1-weighted 3 T MRI scans were acquired for all subjects, and patients were identified by a neuroradiologist with regards to lateralization and degree of hippocampal sclerosis (HS). Automated segmentation was implemented through the Joint Label Fusion/Corrective Learning (JLF/CL) method. Gold standard lateralization was determined from the surgically resected side in Engel I (seizure-free) patients at the two-year timepoint. ROC curves were used to identify appropriate thresholds for hippocampal asymmetry ratios, which were then used to analyze JLF/CL lateralization.

RESULTS

The optimal template atlas based on subject images with varying appearances, from normal-appearing to severe HS, was demonstrated to be composed entirely of normal-appearing subjects, with good agreement between automated and manual segmentations. In applying this atlas to 26 surgically resected seizure-free patients at a two-year timepoint, JLF/CL lateralized seizure onset 92% of the time. In comparison, neuroradiology reads lateralized 65% of patients, but correctly lateralized seizure onset in these patients 100% of the time. When compared to lateralized neuroradiology reads, JLF/CL was in agreement and correctly lateralized all 17 patients. When compared to nonlateralized radiology reads, JLF/CL correctly lateralized 78% of the nine patients.

SIGNIFICANCE

While a neuroradiologist's interpretation of MR imaging is a key, albeit imperfect, diagnostic tool for seizure localization in medically-refractory TLE patients, automated hippocampal segmentation may provide more efficient and accurate epileptic foci localization. These promising findings demonstrate the clinical utility of automated segmentation in the TLE MR imaging pipeline prior to surgical resection, and suggest that further investigation into JLF/CL-assisted MRI reading could improve clinical outcomes. Our JLF/CL software is publicly available at https://www.nitrc.org/projects/ashs/.

Spatially Consistent Supervoxel Correspondences of Cone-Beam Computed Tomography Images

Establishing dense correspondences of cone-beam computed tomography (CBCT) images is a crucial step for the attribute transfer and morphological variation assessment in clinical orthodontics. In this paper, a novel method, unsupervised spatially consistent clustering forest, is proposed to tackle the challenges for automatic supervoxel-wise correspondences of CBCT images. A complexity analysis of the proposed method with respect to the clustering hypotheses is provided with a data-dependent learning guarantee. The learning bound considers both the sequential tree traversals determined by questions stored in branch nodes and the clustering compactness of leaf nodes. A novel tree-pruning algorithm, guided by the learning bound, is also proposed to remove locally inconsistent leaf nodes. The resulting forest yields spatially consistent affinity estimations, thanks to the pruning penalizing trees with inconsistent leaf assignments and the combinational contextual feature channels used to learn the forest. A forest-based metric is utilized to derive the pairwise affinities and dense correspondences of CBCT images. The proposed method has been applied to the label propagation of clinically captured CBCT images. In the experiments, the method outperforms variants of both supervised and unsupervised forest-based methods and state-of-the-art label-propagation methods, achieving the mean dice similarity coefficients of 0.92, 0.89, 0.94, and 0.93 for the mandible, the maxilla, the zygoma arch, and the teeth data, respectively.

An iterative multi-atlas patch-based approach for cortex segmentation from neonatal MRI

Brain structure analysis in the newborn is a major health issue. This is especially the case for preterm neonates, in order to obtain predictive information related to the child development. In particular, the cortex is a structure of interest, that can be observed in magnetic resonance imaging (MRI). However, neonatal MRI data present specific properties that make them challenging to process. In this context, multi-atlas approaches constitute an efficient strategy, taking advantage of images processed beforehand. The method proposed in this article relies on such a multi-atlas strategy. More precisely, it uses two paradigms: first, a non-local model based on patches; second, an iterative optimization scheme. Coupling both concepts allows us to consider patches related not only to the image information, but also to the current segmentation. This strategy is compared to other multi-atlas methods proposed in the literature. Experiments on dHCP datasets show that the proposed approach provides robust cortex segmentation results.

Adaptive fusion of texture-based grading for Alzheimer's disease classification

Alzheimer's disease is a neurodegenerative process leading to irreversible mental dysfunctions. To date, diagnosis is established after incurable brain structure alterations. The development of new biomarkers is crucial to perform an early detection of this disease. With the recent improvement of magnetic resonance imaging, numerous methods were proposed to improve computer-aided detection. Among these methods, patch-based grading framework demonstrated state-of-the-art performance. Usually, methods based on this framework use intensity or grey matter maps. However, it has been shown that texture filters improve classification performance in many cases. The aim of this work is to improve performance of patch-based grading framework with the development of a novel texture-based grading method. In this paper, we study the potential of multi-directional texture maps extracted with 3D Gabor filters to improve patch-based grading method. We also proposed a novel patch-based fusion scheme to efficiently combine multiple grading maps. To validate our approach, we study the optimal set of filters and compare the proposed method with different fusion schemes. In addition, we also compare our new texture-based grading biomarker with state-of-the-art methods. Experiments show an improvement of AD detection and prediction accuracy. Moreover, our method obtains competitive performance with 91.3% of accuracy and 94.6% of area under a curve for AD detection.

Learning to combine complementary segmentation methods for fetal and 6-month infant brain MRI segmentation

Segmentation of brain structures during the pre-natal and early post-natal periods is the first step for subsequent analysis of brain development. Segmentation techniques can be roughly divided into two families. The first, which we denote as registration-based techniques, rely on initial estimates derived by registration to one (or several) templates. The second family, denoted as learning-based techniques, relate imaging (and spatial) features to their corresponding anatomical labels. Each approach has its own qualities and both are complementary to each other. In this paper, we explore two ensembling strategies, namely, stacking and cascading to combine the strengths of both families. We present experiments on segmentation of 6-month infant brains and a cohort of fetuses with isolated non-severe ventriculomegaly (INSVM). INSVM is diagnosed when ventricles are mildly enlarged and no other anomalies are apparent. Prognosis is difficult based solely on the degree of ventricular enlargement. In order to find markers for a more reliable prognosis, we use the resulting segmentations to find abnormalities in the cortical folding of INSVM fetuses. Segmentation results show that either combination strategy outperform all of the individual methods, thus demonstrating the capability of learning systematic combinations that lead to an overall improvement. In particular, the cascading strategy outperforms the ensembling one, the former one obtaining top 5, 7 and 13 results (out of 21 teams) in the segmentation of white matter, gray matter and cerebro-spinal fluid in the iSeg2017 MICCAI Segmentation Challenge. The resulting segmentations reveal that INSVM fetuses have a less convoluted cortex. This points to cortical folding abnormalities as potential markers of later neurodevelopmental outcomes.

Validation of prognostic biomarker scores for predicting progression of dementia in patients with amnestic mild cognitive impairment

Objective

The objective of this study was to develop and validate a practical computerized prognostic model that uses baseline psychometric and imaging data, including results of PET imaging of amyloid deposition, to predict the progression to dementia in patients at risk for Alzheimer’s disease (AD).

Patients and methods

Data from patients in a phase II trial of [¹⁸F]flutemetamol for PET imaging of brain amyloid and from the Alzheimer’s Disease Neuroimaging Initiative were used to train the prognostic model to yield a disease state index (DSI), a measure of the similarity of an individual patient’s data to data from patients in specific diagnostic groups. Inputs to the model included amyloid PET results, MRI measurements of hippocampal volume, and the results of psychometric tests. The model was subsequently validated by using data from a prospective study of an independent cohort of patients with mild cognitive impairment.

Results

In total, data from 223 patients of the 233 enroled were suitable for analysis. The DSI predicted by the model and the risk of progression to AD dementia within 3 years were higher for patients with amyloid deposition and neurodegeneration than for patients with amyloid deposition without neurodegeneration. Rates of non-AD dementia among patients with neurodegeneration at baseline were consistent with the results of other studies. The results were consistent with the Jack model of AD progression.

Conclusion

The DSI from the model that included psychometric, MRI, and PET amyloid data provides useful prognostic information in cases of mild cognitive impairment.