Simultaneous total intracranial volume and posterior fossa volume estimation using multi-atlas label fusion

Volumetric segmentation in the context of posterior fossa-related pathologies: a systematic review

BACKGROUND

Segmentation tools continue to advance, evolving from manual contouring to deep learning. Researchers have utilized segmentation to study a myriad of posterior fossa-related conditions, such as Chiari malformation, trigeminal neuralgia, post-operative pediatric cerebellar mutism syndrome, and Crouzon syndrome. Herein, we present a summary of the current literature on segmentation of the posterior fossa. The review highlights the various segmentation techniques, and their respective strengths and weaknesses, employed along with objectives and outcomes of the various studies reported in the literature.

METHODS

A literature search was conducted in PubMed, Embase, Cochrane, and Web of Science up to November 2023 for articles on segmentation techniques of posterior fossa. The two senior authors searched through databases based on the keywords of the article separately and then enrolled joint articles that met the inclusion and exclusion criteria.

RESULTS

The initial search identified 2205 articles. After applying inclusion and exclusion criteria, 77 articles were selected for full-text review after screening of titles/abstracts. 52 articles were ultimately included in the review. Segmentation techniques included manual, semi-automated, and fully automated (atlas-based, convolutional neural networks). The most common pathology investigated was Chiari malformation.

CONCLUSIONS

Various forms of segmentation techniques have been used to assess posterior fossa volumes/pathologies and each has its advantages and disadvantages. We discuss these nuances and summarize the current state of literature in the context of posterior fossa-associated pathologies.

Structural brain differences in essential tremor and Parkinson's disease deep brain stimulation patients

BACKGROUND

Essential tremor (ET) and Parkinson's disease (PD) are the most common tremor disorders and are common indications for deep brain stimulation (DBS). In some patients, PD and ET symptoms overlap and diagnosis can be challenging based on clinical criteria alone. The objective of this study was to identify structural brain differences between PD and ET DBS patients to help differentiate these disorders and improve our understanding of the different brain regions involved in these pathologic processes.

METHODS

We included ET and PD patients scheduled to undergo DBS surgery in this observational study. Patients underwent 3T brain MRI while under general anesthesia as part of their procedure. Cortical thicknesses and subcortical volumes were quantified from T1-weighted images using automated multi-atlas segmentation. We used logistic regression analysis to identify brain regions associated with diagnosis of ET or PD.

RESULTS

149 ET and 265 PD patients were included. Smaller volumes in the pallidum and thalamus and reduced thickness in the anterior orbital gyrus, lateral orbital gyrus, and medial precentral gyrus were associated with greater odds of ET diagnosis. Conversely, reduced volumes in the caudate, amygdala, putamen, and basal forebrain, and reduced thickness in the orbital part of the inferior frontal gyrus, supramarginal gyrus, and posterior cingulate were associated with greater odds of PD diagnosis.

CONCLUSIONS

These findings identify structural brain differences between PD and ET patients. These results expand our understanding of the different brain regions involved in these disorders and suggest that structural MRI may help to differentiate patients with these two disorders.

A comparison of intracranial volume estimation methods and their cross-sectional and longitudinal associations with age

Intracranial volume (ICV) is frequently used in volumetric magnetic resonance imaging (MRI) studies, both as a covariate and as a variable of interest. Findings of associations between ICV and age have varied, potentially due to differences in ICV estimation methods. Here, we compared five commonly used ICV estimation methods and their associations with age. T1-weighted cross-sectional MRI data was included for 651 healthy individuals recruited through the NORMENT Centre (mean age = 46.1 years, range = 12.0-85.8 years) and 2410 healthy individuals recruited through the UK Biobank study (UKB, mean age = 63.2 years, range = 47.0-80.3 years), where longitudinal data was also available. ICV was estimated with FreeSurfer (eTIV and sbTIV), SPM12, CAT12, and FSL. We found overall high correlations across ICV estimation method, with the lowest observed correlations between FSL and eTIV (r = .87) and between FSL and CAT12 (r = .89). Widespread proportional bias was found, indicating that the agreement between methods varied as a function of head size. Body weight, age, sex, and mean ICV across methods explained the most variance in the differences between ICV estimation methods, indicating possible confounding for some estimation methods. We found both positive and negative cross-sectional associations with age, depending on dataset and ICV estimation method. Longitudinal ICV reductions were found for all ICV estimation methods, with annual percentage change ranging from -0.293% to -0.416%. This convergence of longitudinal results across ICV estimation methods offers strong evidence for age-related ICV reductions in mid- to late adulthood.

Generalizing deep learning brain segmentation for skull removal and intracranial measurements

Total intracranial volume (TICV) and posterior fossa volume (PFV) are essential covariates for brain volumetric analyses with structural magnetic resonance imaging (MRI). Detailed whole brain segmentation provides a non-invasive way to measure brain regions. Furthermore, increasing neuroimaging data are distributed in a skull-stripped manner for privacy protection. Therefore, generalizing deep learning brain segmentation for skull removal and intracranial measurements is an appealing task. However, data availability is challenging due to a limited set of manually traced atlases with whole brain and TICV/PFV labels. In this paper, we employ U-Net tiles to achieve automatic TICV estimation and whole brain segmentation simultaneously on brains w/and w/o the skull. To overcome the scarcity of manually traced whole brain volumes, a transfer learning method is introduced to estimate additional TICV and PFV labels during whole brain segmentation in T1-weighted MRI. Specifically, U-Net tiles are first pre-trained using large-scale BrainCOLOR atlases without TICV and PFV labels, which are created by multi-atlas segmentation. Then the pre-trained models are refined by training the additional TICV and PFV labels using limited BrainCOLOR atlases. We also extend our method to handle skull-stripped brain MR images. From the results, our method provides promising whole brain segmentation and volume estimation results for both brains w/and w/o skull in terms of mean Dice similarity coefficients and mean surface distance and absolute volume similarity. This method has been made available in open source (https://github.com/MASILab/SLANTbrainSeg_skullstripped).

Multiple Sclerosis Recognition by Biorthogonal Wavelet Features and Fitness-Scaled Adaptive Genetic Algorithm

Aim: Multiple sclerosis (MS) is a disease, which can affect the brain and/or spinal cord, leading to a wide range of potential symptoms. This method aims to propose a novel MS recognition method. Methods: First, the bior4.4 wavelet is used to extract multiscale coefficients. Second, three types of biorthogonal wavelet features are proposed and calculated. Third, fitness-scaled adaptive genetic algorithm (FAGA)-a combination of standard genetic algorithm, adaptive mechanism, and power-rank fitness scaling-is harnessed as the optimization algorithm. Fourth, multiple-way data augmentation is utilized on the training set under the setting of 10 runs of 10-fold cross-validation. Our method is abbreviated as BWF-FAGA. Results: Our method achieves a sensitivity of 98.00 ± 0.95%, a specificity of 97.78 ± 0.95%, and an accuracy of 97.89 ± 0.94%. The area under the curve of our method is 0.9876. Conclusion: The results show that the proposed BWF-FAGA method is better than 10 state-of-the-art MS recognition methods, including eight artificial intelligence-based methods, and two deep learning-based methods.

Map3D: Registration-Based Multi-Object Tracking on 3D Serial Whole Slide Images

There has been a long pursuit for precise and reproducible glomerular quantification on renal pathology to leverage both research and practice. When digitizing the biopsy tissue samples using whole slide imaging (WSI), a set of serial sections from the same tissue can be acquired as a stack of images, similar to frames in a video. In radiology, the stack of images (e.g., computed tomography) are naturally used to provide 3D context for organs, tissues, and tumors. In pathology, it is appealing to do a similar 3D assessment. However, the 3D identification and association of large-scale glomeruli on renal pathology is challenging due to large tissue deformation, missing tissues, and artifacts from WSI. In this paper, we propose a novel Multi-object Association for Pathology in 3D (Map3D) method for automatically identifying and associating large-scale cross-sections of 3D objects from routine serial sectioning and WSI. The innovations of the Multi-Object Association for Pathology in 3D (Map3D) method are three-fold: (1) the large-scale glomerular association is formed as a new multi-object tracking (MOT) perspective; (2) the quality-aware whole series registration is proposed to not only provide affinity estimation but also offer automatic kidney-wise quality assurance (QA) for registration; (3) a dual-path association method is proposed to tackle the large deformation, missing tissues, and artifacts during tracking. To the best of our knowledge, the Map3D method is the first approach that enables automatic and large-scale glomerular association across 3D serial sectioning using WSI. Our proposed method Map3D achieved MOTA = 44.6, which is 12.1% higher than the non-deep learning benchmarks.

Structural volume and cortical thickness differences between males and females in cognitively normal, cognitively impaired and Alzheimer's dementia population

We investigated differences due to sex in brain structural volume and cortical thickness in older cognitively normal (N=742), cognitively impaired (MCI; N=540) and Alzheimer's Dementia (AD; N=402) individuals from the ADNI and AIBL datasets (861 Males and 823 Females). General linear models were used to control the effect of relevant covariates including age, intracranial volume, magnetic resonance imaging (MRI) scanner field strength and scanner types. Significant volumetric differences due to sex were observed within different cortical and subcortical regions of the cognitively normal group. The number of significantly different regions was reduced in the MCI group, and no region remained different in the AD group. Cortical thickness was overall thinner in males than females in the cognitively normal group, and likewise, the differences due to sex were reduced in the MCI and AD groups. These findings were sustained after including cerebrospinal fluid (CSF) Tau and phosphorylated tau (pTau) as additional covariates.

Improved Segmentation of the Intracranial and Ventricular Volumes in Populations with Cerebrovascular Lesions and Atrophy Using 3D CNNs

Successful segmentation of the total intracranial vault (ICV) and ventricles is of critical importance when studying neurodegeneration through neuroimaging. We present iCVMapper and VentMapper, robust algorithms that use a convolutional neural network (CNN) to segment the ICV and ventricles from both single and multi-contrast MRI data. Our models were trained on a large dataset from two multi-site studies (N = 528 subjects for ICV, N = 501 for ventricular segmentation) consisting of older adults with varying degrees of cerebrovascular lesions and atrophy, which pose significant challenges for most segmentation approaches. The models were tested on 238 participants, including subjects with vascular cognitive impairment and high white matter hyperintensity burden. Two of the three test sets came from studies not used in the training dataset. We assessed our algorithms relative to four state-of-the-art ICV extraction methods (MONSTR, BET, Deep Extraction, FreeSurfer, DeepMedic), as well as two ventricular segmentation tools (FreeSurfer, DeepMedic). Our multi-contrast models outperformed other methods across many of the evaluation metrics, with average Dice coefficients of 0.98 and 0.96 for ICV and ventricular segmentation respectively. Both models were also the most time efficient, segmenting the structures in orders of magnitude faster than some of the other available methods. Our networks showed an increased accuracy with the use of a conditional random field (CRF) as a post-processing step. We further validated both segmentation models, highlighting their robustness to images with lower resolution and signal-to-noise ratio, compared to tested techniques. The pipeline and models are available at: https://icvmapp3r.readthedocs.io and https://ventmapp3r.readthedocs.io to enable further investigation of the roles of ICV and ventricles in relation to normal aging and neurodegeneration in large multi-site studies.

A fully automated pipeline for brain structure segmentation in multiple sclerosis

Accurate volume measurements of the brain structures are important for treatment evaluation and disease follow-up in multiple sclerosis (MS) patients. With the aim of obtaining reproducible measurements and avoiding the intra-/inter-rater variability that manual delineations introduce, several automated brain structure segmentation strategies have been proposed in recent years. However, most of these strategies tend to be affected by the abnormal MS lesion intensities, which corrupt the structure segmentation result. To address this problem, we recently reformulated two label fusion strategies of the state of the art, improving their segmentation performance on the lesion areas. Here, we integrate these reformulated strategies in a completely automated pipeline that includes pre-processing (inhomogeneity correction and intensity normalization), atlas selection, masked registration and label fusion, and combine them with an automated lesion segmentation method of the state of the art. We study the effect of automating the lesion mask acquisition on the structure segmentation result, analyzing the output of the proposed pipeline when used in combination with manually and automatically segmented lesion masks. We further analyze the effect of those masks on the segmentation result of the original label fusion strategies when combined with the well-established pre-processing step of lesion filling. The experiments performed show that, when the original methods are used to segment the lesion-filled images, significant structure volume differences are observed in a comparison between manually and automatically segmented lesion masks. The results indicate a mean volume decrease of 1.13%±1.93 in the cerebrospinal fluid, and a mean volume increase of 0.13%±0.14 and 0.05%±0.08 in the cerebral white matter and cerebellar gray matter, respectively. On the other hand, no significant volume differences were found when the proposed automated pipeline was used for segmentation, which demonstrates its robustness against variations in the lesion mask used.

Structural Correlates of the Sensorimotor Cerebellum in Parkinson's Disease and Essential Tremor

BACKGROUND

Parkinson's disease (PD) and essential tremor (ET) are commonly encountered movement disorders. Pathophysiologic processes that localize to the cerebellum are described in both. There are limited studies investigating cerebellar structural changes in these conditions, largely because of inherent challenges in the efficiency of segmentation.

METHODS

We applied a novel multiatlas cerebellar segmentation method to T1-weighted images in 282 PD and 111 essential tremor patients to define 26 cerebellar lobule volumes. The severity of postural and resting tremor in both populations and gait and postural instability in PD patients were defined using subscores of the UPDRS and Washington Heights-Inwood Genetic Study motor scales. These clinical measurements were related to lobule volume size. Multiple comparisons were controlled using a false discovery rate method.

RESULTS

Group differences were identified between ET and PD patients, with reductions in deep cerebellar nucleus volume in ET versus reduced lobule VI volume in PD. In ET patients, lobule VIII was negatively correlated with the severity of postural tremor. In PD patients, lobule IV was positively correlated with resting tremor and total tremor severity. We observed differences in cerebellar structure that localized to sensorimotor lobules of the cerebellum. Lobule volumes appeared to differentially relate to clinical symptoms, suggesting important clinicopathologic distinctions between these conditions. These results emphasize the role of the cerebellum in tremor symptoms and should foster future clinical and pathologic investigations of the sensorimotor lobules of the cerebellum. © 2020 International Parkinson and Movement Disorder Society.

Generalizing Deep Whole Brain Segmentation for Pediatric and Post- Contrast MRI with Augmented Transfer Learning

Generalizability is an important problem in deep neural networks, especially in the context of the variability of data acquisition in clinical magnetic resonance imaging (MRI). Recently, the Spatially Localized Atlas Network Tiles (SLANT) approach has been shown to effectively segment whole brain non-contrast T1w MRI with 132 volumetric labels. Enhancing generalizability of SLANT would enable broader application of volumetric assessment in multi-site studies. Transfer learning (TL) is commonly to update neural network weights for local factors; yet, it is commonly recognized to risk degradation of performance on the original validation/test cohorts. Here, we explore TL by data augmentation to address these concerns in the context of adapting SLANT to anatomical variation (e.g., adults versus children) and scanning protocol (e.g., non-contrast research T1w MRI versus contrast-enhanced clinical T1w MRI). We consider two datasets: First, 30 T1w MRI of young children with manually corrected volumetric labels, and accuracy of automated segmentation defined relative to the manually provided truth. Second, 36 paired datasets of pre- and post-contrast clinically acquired T1w MRI, and accuracy of the post-contrast segmentations assessed relative to the pre-contrast automated assessment. For both studies, we augment the original TL step of SLANT with either only the new data or with both original and new data. Over baseline SLANT, both approaches yielded significantly improved performance (pediatric: 0.89 vs. 0.82 DSC, p<0.001; contrast: 0.80 vs 0.76, p<0.001). The performance on the original test set decreased with the new-data only transfer learning approach, so data augmentation was superior to strict transfer learning.

Towards Portable Large-Scale Image Processing with High-Performance Computing

High-throughput, large-scale medical image computing demands tight integration of high-performance computing (HPC) infrastructure for data storage, job distribution, and image processing. The Vanderbilt University Institute for Imaging Science (VUIIS) Center for Computational Imaging (CCI) has constructed a large-scale image storage and processing infrastructure that is composed of (1) a large-scale image database using the eXtensible Neuroimaging Archive Toolkit (XNAT), (2) a content-aware job scheduling platform using the Distributed Automation for XNAT pipeline automation tool (DAX), and (3) a wide variety of encapsulated image processing pipelines called “spiders.” The VUIIS CCI medical image data storage and processing infrastructure have housed and processed nearly half-million medical image volumes with Vanderbilt Advanced Computing Center for Research and Education (ACCRE), which is the HPC facility at the Vanderbilt University. The initial deployment was natively deployed (i.e., direct installations on a bare-metal server) within the ACCRE hardware and software environments, which lead to issues of portability and sustainability. First, it could be laborious to deploy the entire VUIIS CCI medical image data storage and processing infrastructure to another HPC center with varying hardware infrastructure, library availability, and software permission policies. Second, the spiders were not developed in an isolated manner, which has led to software dependency issues during system upgrades or remote software installation. To address such issues, herein, we describe recent innovations using containerization techniques with XNAT/DAX which are used to isolate the VUIIS CCI medical image data storage and processing infrastructure from the underlying hardware and software environments. The newly presented XNAT/DAX solution has the following new features: (1) multi-level portability from system level to the application level, (2) flexible and dynamic software development and expansion, and (3) scalable spider deployment compatible with HPC clusters and local workstations.

Acceleration of spleen segmentation with end-to-end deep learning method and automated pipeline

Delineation of Computed Tomography (CT) abdominal anatomical structure, specifically spleen segmentation, is useful for not only measuring tissue volume and biomarkers but also for monitoring interventions. Recently, segmentation algorithms using deep learning have been widely used to reduce time humans spend to label CT data. However, the computerized segmentation has two major difficulties: managing intermediate results (e.g., resampled scans, 2D sliced image for deep learning), and setting up the system environments and packages for autonomous execution. To overcome these issues, we propose an automated pipeline for the abdominal spleen segmentation. This pipeline provides an end-to-end synthesized process that allows users to avoid installing any packages and to deal with the intermediate results locally. The pipeline has three major stages: pre-processing of input data, segmentation of spleen using deep learning, 3D reconstruction with the generated labels by matching the segmentation results with the original image dimensions, which can then be used later and for display or demonstration. Given the same volume scan, the approach described here takes about 50 s on average whereas the manual segmentation takes about 30 min on the average. Even if it includes all subsidiary processes such as preprocessing and necessary setups, the whole pipeline process requires on the average 20 min from beginning to end.

Quantitative assessment of field strength, total intracranial volume, sex, and age effects on the goodness of harmonization for volumetric analysis on the ADNI database

When analyzing large multicenter databases, the effects of multiple confounding covariates increase the variability in the data and may reduce the ability to detect changes due to the actual effect of interest, for example, changes due to disease. Efficient ways to evaluate the effect of covariates toward the data harmonization are therefore important. In this article, we showcase techniques to assess the "goodness of harmonization" of covariates. We analyze 7,656 MR images in the multisite, multiscanner Alzheimer's Disease Neuroimaging Initiative (ADNI) database. We present a comparison of three methods for estimating total intracranial volume to assess their robustness and correct the brain structure volumes using the residual method and the proportional (normalization by division) method. We then evaluated the distribution of brain structure volumes over the entire ADNI database before and after accounting for multiple covariates such as total intracranial volume, scanner field strength, sex, and age using two techniques: (a) Zscapes, a panoramic visualization technique to analyze the entire database and (b) empirical cumulative distributions functions. The results from this study highlight the importance of assessing the goodness of data harmonization as a necessary preprocessing step when pooling large data set with multiple covariates, prior to further statistical data analysis.

Reproducibility Evaluation of SLANT Whole Brain Segmentation Across Clinical Magnetic Resonance Imaging Protocols

Whole brain segmentation on structural magnetic resonance imaging (MRI) is essential for understanding neuroanatomical-functional relationships. Traditionally, multi-atlas segmentation has been regarded as the standard method for whole brain segmentation. In past few years, deep convolutional neural network (DCNN) segmentation methods have demonstrated their advantages in both accuracy and computational efficiency. Recently, we proposed the spatially localized atlas network tiles (SLANT) method, which is able to segment a 3D MRI brain scan into 132 anatomical regions. Commonly, DCNN segmentation methods yield inferior performance under external validations, especially when the testing patterns were not presented in the training cohorts. Recently, we obtained a clinically acquired, multi-sequence MRI brain cohort with 1480 clinically acquired, de-identified brain MRI scans on 395 patients using seven different MRI protocols. Moreover, each subject has at least two scans from different MRI protocols. Herein, we assess the SLANT method's intra- and inter-protocol reproducibility. SLANT achieved less than 0.05 coefficient of variation (CV) for intra-protocol experiments and less than 0.15 CV for inter-protocol experiments. The results show that the SLANT method achieved high intra- and inter- protocol reproducibility.

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.

SynSeg-Net: Synthetic Segmentation Without Target Modality Ground Truth

A key limitation of deep convolutional neural networks (DCNN) based image segmentation methods is the lack of generalizability. Manually traced training images are typically required when segmenting organs in a new imaging modality or from distinct disease cohort. The manual efforts can be alleviated if the manually traced images in one imaging modality (e.g., MRI) are able to train a segmentation network for another imaging modality (e.g., CT). In this paper, we propose an end-to-end synthetic segmentation network (SynSeg-Net) to train a segmentation network for a target imaging modality without having manual labels. SynSeg-Net is trained by using (1) unpaired intensity images from source and target modalities, and (2) manual labels only from source modality. SynSeg-Net is enabled by the recent advances of cycle generative adversarial networks (CycleGAN) and DCNN. We evaluate the performance of the SynSeg-Net on two experiments: (1) MRI to CT splenomegaly synthetic segmentation for abdominal images, and (2) CT to MRI total intracranial volume synthetic segmentation (TICV) for brain images. The proposed end-to-end approach achieved superior performance to two stage methods. Moreover, the SynSeg-Net achieved comparable performance to the traditional segmentation network using target modality labels in certain scenarios. The source code of SynSeg-Net is publicly available 2.

Improved Stability of Whole Brain Surface Parcellation with Multi-Atlas Segmentation

Whole brain segmentation and cortical surface parcellation are essential in understanding the brain anatomical-functional relationship. Multi-atlas segmentation has been regarded as one of the leading segmentation methods for the whole brain segmentation. In our recent work, the multi-atlas technique has been adapted to surface reconstruction using a method called Multi-atlas CRUISE (MaCRUISE). The MaCRUISE method not only performed the consistent volume-surface analyses but also shown advantages on robustness compared with FreeSurfer method. However, a detailed surface parcellation was not provided by MaCRUISE, which hindered the region of interests (ROI) based analyses on surfaces. Herein, the MaCRUISE surface parcellation (MaCRUISEsp) method is proposed to perform the surface parcellation upon the inner, central and outer surfaces that are reconstructed from MaCRUISE. MaCRUISEsp parcellates inner, central and outer surfaces with 98 cortical labels respectively using a volume segmentation based surface parcellation (VSBSP), following a topological correction step. To validate the performance of MaCRUISEsp, 21 scan-rescan magnetic resonance imaging (MRI) T1 volume pairs from the Kirby21 dataset were used to perform a reproducibility analyses. MaCRUISEsp achieved 0.948 on median Dice Similarity Coefficient (DSC) for central surfaces. Meanwhile, FreeSurfer achieved 0.905 DSC for inner surfaces and 0.881 DSC for outer surfaces, while the proposed method achieved 0.929 DSC for inner surfaces and 0.835 DSC for outer surfaces. Qualitatively, the results are encouraging, but are not directly comparable as the two approaches use different definitions of cortical labels.

Dictionary-based fiber orientation estimation with improved spatial consistency

Diffusion magnetic resonance imaging (dMRI) has enabled in vivo investigation of white matter tracts. Fiber orientation (FO) estimation is a key step in tract reconstruction and has been a popular research topic in dMRI analysis. In particular, the sparsity assumption has been used in conjunction with a dictionary-based framework to achieve reliable FO estimation with a reduced number of gradient directions. Because image noise can have a deleterious effect on the accuracy of FO estimation, previous works have incorporated spatial consistency of FOs in the dictionary-based framework to improve the estimation. However, because FOs are only indirectly determined from the mixture fractions of dictionary atoms and not modeled as variables in the objective function, these methods do not incorporate FO smoothness directly, and their ability to produce smooth FOs could be limited. In this work, we propose an improvement to Fiber Orientation Reconstruction using Neighborhood Information (FORNI), which we call FORNI+; this method estimates FOs in a dictionary-based framework where FO smoothness is better enforced than in FORNI alone. We describe an objective function that explicitly models the actual FOs and the mixture fractions of dictionary atoms. Specifically, it consists of data fidelity between the observed signals and the signals represented by the dictionary, pairwise FO dissimilarity that encourages FO smoothness, and weighted ℓ1-norm terms that ensure the consistency between the actual FOs and the FO configuration suggested by the dictionary representation. The FOs and mixture fractions are then jointly estimated by minimizing the objective function using an iterative alternating optimization strategy. FORNI+ was evaluated on a simulation phantom, a physical phantom, and real brain dMRI data. In particular, in the real brain dMRI experiment, we have qualitatively and quantitatively evaluated the reproducibility of the proposed method. Results demonstrate that FORNI+ produces FOs with better quality compared with competing methods.

Delineation of two intracranial areas and the perpendicular intracranial width is sufficient for intracranial volume estimation

OBJECTIVES

The aim of the present study is to determine if the delineation of one or two optimally chosen intracranial areas (ICA) is enough to achieve adequate estimates of intracranial volume (ICV) in magnetic resonance imaging.

METHODS

The correlations of 62 fully delineated ICVs with four types of ICV estimates were calculated. The estimate types were: (1) a single midsagittal ICA, (2) single ICA multiplied by the intracranial width perpendicular to the ICA, (3) sum of two ICAs multiplied by the perpendicular intracranial width and (4) shape-preserving piecewise cubic interpolation using two ICAs. For methods 2-4, the fully delineated ICVs were randomly separated into an evaluation and a validation set of equal size. Method 1 was validated against all of the fully delineated ICVs.

RESULTS

Estimates from method 1 had a Pearson correlation of 0.904 with fully delineated ICV. For method 2, the correlation was 0.986 when delineating the sagittal ICA at 31% of the sagittal intracranial width. For methods 3 and 4, the correlations were both 0.997 when delineating the sagittal ICAs at 17.5 and 64% and at 12 and 64% respectively.

CONCLUSIONS

Delineation of two specific intracranial areas is sufficient for intracranial volume estimation.

MAIN MESSAGES

• Delineation of two specific intracranial areas is sufficient for intracranial volume estimation. • The estimates had a Pearson correlation of 0.997 with intracranial volume. • The estimation should take no more than 5 min.

4D Multi-atlas Label Fusion using Longitudinal Images

Longitudinal reproducibility is an essential concern in automated medical image segmentation, yet has proven to be an elusive objective as manual brain structure tracings have shown more than 10% variability. To improve reproducibility, longitudinal segmentation (4D) approaches have been investigated to reconcile temporal variations with traditional 3D approaches. In the past decade, multi-atlas label fusion has become a state-of-the-art segmentation technique for 3D image and many efforts have been made to adapt it to a 4D longitudinal fashion. However, the previous methods were either limited by using application specified energy function (e.g., surface fusion and multi model fusion) or only considered temporal smoothness on two consecutive time points (t and t+1) under sparsity assumption. Therefore, a 4D multi-atlas label fusion theory for general label fusion purpose and simultaneously considering temporal consistency on all time points is appealing. Herein, we propose a novel longitudinal label fusion algorithm, called 4D joint label fusion (4DJLF), to incorporate the temporal consistency modeling via non-local patch-intensity covariance models. The advantages of 4DJLF include: (1) 4DJLF is under the general label fusion framework by simultaneously incorporating the spatial and temporal covariance on all longitudinal time points. (2) The proposed algorithm is a longitudinal generalization of a leading joint label fusion method (JLF) that has proven adaptable to a wide variety of applications. (3) The spatial temporal consistency of atlases is modeled in a probabilistic model inspired from both voting based and statistical fusion. The proposed approach improves the consistency of the longitudinal segmentation while retaining sensitivity compared with original JLF approach using the same set of atlases. The method is available online in open-source.