Tests of cortical parcellation based on white matter connectivity using diffusion tensor imaging.

The cerebral cortex is conventionally divided into a number of domains based on cytoarchitectural features. Diffusion tensor imaging (DTI) enables noninvasive parcellation of the cortex based on white matter connectivity patterns. However, the correspondence between DTI-connectivity-based and cytoarchitectural parcellation has not been systematically established. In this study, we compared histological parcellation of New World monkey neocortex to DTI- connectivity-based classification and clustering in the same brains. First, we used supervised classification to parcellate parieto-frontal cortex based on DTI tractograms and the cytoarchitectural prior (obtained using Nissl staining). We performed both within and across sample classification, showing reasonable classification performance in both conditions. Second, we used unsupervised clustering to parcellate the cortex and compared the clusters to the cytoarchitectonic standard. We then explored the similarities and differences with several post-hoc analyses, highlighting underlying principles that drive the DTI-connectivity-based parcellation. The differences in parcellation between DTI-connectivity and Nissl histology probably represent both DTI's bias toward easily-tracked bundles and true differences between cytoarchitectural and connectivity defined domains. DTI tractograms appear to cluster more according to functional networks, rather than mapping directly onto cytoarchitectonic domains. Our results show that caution should be used when DTI-tractography classification, based on data from another brain, is used as a surrogate for cytoarchitectural parcellation.

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

Total intracranial volume (TICV) is an essential covariate in brain volumetric analyses. The prevalent brain imaging software packages provide automatic TICV estimates. FreeSurfer and FSL estimate TICV using a scaling factor while SPM12 accumulates probabilities of brain tissues. None of the three provide explicit skull/CSF boundary (SCB) since it is challenging to distinguish these dark structures in a T1-weighted image. However, explicit SCB not only leads to a natural way of obtaining TICV (i.e., counting voxels inside the skull) but also allows sub-definition of TICV, for example, the posterior fossa volume (PFV). In this article, they proposed to use multi-atlas label fusion to obtain TICV and PFV simultaneously. The main contributions are: (1) TICV and PFV are simultaneously obtained with explicit SCB from a single T1-weighted image. (2) TICV and PFV labels are added to the widely used BrainCOLOR atlases. (3) Detailed mathematical derivation of non-local spatial STAPLE (NLSS) label fusion is presented. As the skull is clearly distinguished in CT images, we use a semi-manual procedure to obtain atlases with TICV and PFV labels using 20 subjects who both have a MR and CT scan. The proposed method provides simultaneous TICV and PFV estimation while achieving more accurate TICV estimation compared with FreeSurfer, FSL, SPM12, and the previously proposed STAPLE based approach. The newly developed TICV and PFV labels for the OASIS BrainCOLOR atlases provide acceptable performance, which enables simultaneous TICV and PFV estimation during whole brain segmentation. The NLSS method and the new atlases have been made freely available. Hum Brain Mapp 38:599-616, 2017. © 2016 Wiley Periodicals, Inc.

Consistent cortical reconstruction and multi-atlas brain segmentation.

Whole brain segmentation and cortical surface reconstruction are two essential techniques for investigating the human brain. Spatial inconsistences, which can hinder further integrated analyses of brain structure, can result due to these two tasks typically being conducted independently of each other. FreeSurfer obtains self-consistent whole brain segmentations and cortical surfaces. It starts with subcortical segmentation, then carries out cortical surface reconstruction, and ends with cortical segmentation and labeling. However, this "segmentation to surface to parcellation" strategy has shown limitations in various cohorts such as older populations with large ventricles. In this work, we propose a novel "multi-atlas segmentation to surface" method called Multi-atlas CRUISE (MaCRUISE), which achieves self-consistent whole brain segmentations and cortical surfaces by combining multi-atlas segmentation with the cortical reconstruction method CRUISE. A modification called MaCRUISE(+) is designed to perform well when white matter lesions are present. Comparing to the benchmarks CRUISE and FreeSurfer, the surface accuracy of MaCRUISE and MaCRUISE(+) is validated using two independent datasets with expertly placed cortical landmarks. A third independent dataset with expertly delineated volumetric labels is employed to compare segmentation performance. Finally, 200MR volumetric images from an older adult sample are used to assess the robustness of MaCRUISE and FreeSurfer. The advantages of MaCRUISE are: (1) MaCRUISE constructs self-consistent voxelwise segmentations and cortical surfaces, while MaCRUISE(+) is robust to white matter pathology. (2) MaCRUISE achieves more accurate whole brain segmentations than independently conducting the multi-atlas segmentation. (3) MaCRUISE is comparable in accuracy to FreeSurfer (when FreeSurfer does not exhibit global failures) while achieving greater robustness across an older adult population. MaCRUISE has been made freely available in open source.

Disambiguating the optic nerve from the surrounding cerebrospinal fluid: Application to MS-related atrophy.

PURPOSE: Our goal is to develop an accurate, automated tool to characterize the optic nerve (ON) and cerebrospinal fluid (CSF) to better understand ON changes in disease. METHODS: Multi-atlas segmentation is used to localize the ON and sheath on T2-weighted MRI (0.6 mm(3) resolution). A sum of Gaussian distributions is fit to coronal slice-wise intensities to extract six descriptive parameters, and a regression forest is used to map the model space to radii. The model is validated for consistency using tenfold cross-validation and for accuracy using a high resolution (0.4 mm(2) reconstructed to 0.15 mm(2)) in vivo sequence. We evaluated this model on 6 controls and 6 patients with multiple sclerosis (MS) and a history of optic neuritis. RESULTS: In simulation, the model was found to have an explanatory R-squared for both ON and sheath radii greater than 0.95. The accuracy of the method was within the measurement error on the highest possible in vivo resolution. Comparing healthy controls and patients with MS, significant structural differences were found near the ON head and the chiasm, and structural trends agreed with the literature. CONCLUSION: This is a first demonstration that the ON can be exclusively, quantitatively measured and separated from the surrounding CSF using MRI.

MiR-223 deficiency increases eosinophil progenitor proliferation.

Recently, microRNAs have been shown to be involved in hematopoietic cell development, but their role in eosinophilopoiesis has not yet been described. In this article, we show that miR-223 is upregulated during eosinophil differentiation in an ex vivo bone marrow-derived eosinophil culture system. Targeted ablation of miR-223 leads to an increased proliferation of eosinophil progenitors. We found upregulation of a miR-223 target gene, IGF1R, in the eosinophil progenitor cultures derived from miR-223(-/-) mice compared with miR-223(+/+) littermate controls. The increased proliferation of miR-223(-/-) eosinophil progenitors was reversed by treatment with an IGF1R inhibitor (picropodophyllin). Whole-genome microarray analysis of differentially regulated genes between miR-223(+/+) and miR-223(-/-) eosinophil progenitor cultures identified a specific enrichment in genes that regulate hematologic cell development. Indeed, miR-223(-/-) eosinophil progenitors had a delay in differentiation. Our results demonstrate that microRNAs regulate the development of eosinophils by influencing eosinophil progenitor growth and differentiation and identify a contributory role for miR-223 in this process.

MicroRNA signature in patients with eosinophilic esophagitis, reversibility with glucocorticoids, and assessment as disease biomarkers.

BACKGROUND: The role of microRNAs (miRNAs), a key class of regulators of mRNA expression and translation, in patients with eosinophilic esophagitis (EoE) has not been explored. OBJECTIVE: We aimed to identify miRNAs dysregulated in patients with EoE and assess the potential of these miRNAs as disease biomarkers. METHODS: Esophageal miRNA expression was profiled in patients with active EoE and those with glucocorticoid-induced disease remission. Expression profiles were compared with those of healthy control subjects and patients with chronic (noneosinophilic) esophagitis. Expression levels of the top differentially expressed miRNAs from the plasma of patients with active EoE and patients with EoE remission were compared with those of healthy control subjects. RESULTS: EoE was associated with 32 differentially regulated miRNAs and was distinguished from noneosinophilic forms of esophagitis. The expression levels of the most upregulated miRNAs (miR-21 and miR-223) and the most downregulated miRNA (miR-375) strongly correlated with esophageal eosinophil levels. Bioinformatic analysis predicted interplay of miR-21 and miR-223 with key roles in the polarization of adaptive immunity and regulation of eosinophilia, and indeed, these miRNAs correlated with key elements of the EoE transcriptome. The differentially expressed miRNAs were largely reversible in patients who responded to glucocorticoid treatment. EoE remission induced a single miRNA (miR-675) likely to be involved in DNA methylation. Plasma analysis of the most upregulated esophageal miRNAs identified miR-146a, miR-146b, and miR-223 as the most differentially expressed miRNAs in the plasma. CONCLUSIONS: We have identified a marked dysregulated expression of a select group of miRNAs in patients with EoE and defined their reversibility with glucocorticoid treatment and their potential value as invasive and noninvasive biomarkers.

Automated, open-source segmentation of the Hippocampus and amygdala with the open Vanderbilt archive of the temporal lobe.

Examining volumetric differences of the amygdala and anterior-posterior regions of the hippocampus is important for understanding cognition and clinical disorders. However, the gold standard manual segmentation of these structures is time and labor-intensive. Automated, accurate, and reproducible techniques to segment the hippocampus and amygdala are desirable. Here, we present a hierarchical approach to multi-atlas segmentation of the hippocampus head, body and tail and the amygdala based on atlases from 195 individuals. The Open Vanderbilt Archive of the temporal Lobe (OVAL) segmentation technique outperforms the commonly used FreeSurfer, FSL FIRST, and whole-brain multi-atlas segmentation approaches for the full hippocampus and amygdala and nears or exceeds inter-rater reproducibility for segmentation of the hippocampus head, body and tail. OVAL has been released in open-source and is freely available.

Multi-modal imaging with specialized sequences improves accuracy of the automated subcortical grey matter segmentation.

The basal ganglia and limbic system, particularly the thalamus, putamen, internal and external globus pallidus, substantia nigra, and sub-thalamic nucleus, comprise a clinically relevant signal network for Parkinson's disease. In order to manually trace these structures, a combination of high-resolution and specialized sequences at 7 T are used, but it is not feasible to routinely scan clinical patients in those scanners. Targeted imaging sequences at 3 T have been presented to enhance contrast in a select group of these structures. In this work, we show that a series of atlases generated at 7 T can be used to accurately segment these structures at 3 T using a combination of standard and optimized imaging sequences, though no one approach provided the best result across all structures. In the thalamus and putamen, a median Dice Similarity Coefficient (DSC) over 0.88 and a mean surface distance <1.0 mm were achieved using a combination of T1 and an optimized inversion recovery imaging sequences. In the internal and external globus pallidus a DSC over 0.75 and a mean surface distance <1.2 mm were achieved using a combination of T1 and inversion recovery imaging sequences. In the substantia nigra and sub-thalamic nucleus a DSC of over 0.6 and a mean surface distance of <1.0 mm were achieved using the inversion recovery imaging sequence. On average, using T1 and optimized inversion recovery together significantly improved segmentation results than over individual modality (p < 0.05 Wilcoxon sign-rank test).

Anatomical context improves deep learning on the brain age estimation task.

Deep learning has shown remarkable improvements in the analysis of medical images without the need for engineered features. In this work, we hypothesize that deep learning is complementary to traditional feature estimation. We propose a network design to include traditional structural imaging features alongside deep convolutional ones and illustrate this approach on the task of imaging-based age prediction in two separate contexts: T1-weighted brain magnetic resonance imaging (MRI) (N = 5121, ages 4-96, healthy controls) and computed tomography (CT) of the head (N = 1313, ages 1-97, healthy controls). In brain MRI, we can predict age with a mean absolute error of 4.08 years by combining raw images along with engineered structural features, compared to 5.00 years using image-derived features alone and 8.23 years using structural features alone. In head CT, we can predict age with a median absolute error of 9.99 years combining features, compared to 11.02 years with image-derived features alone and 13.28 years with structural features alone. These results show that we can complement traditional feature estimation using deep learning to improve prediction tasks. As the field of medical image processing continues to integrate deep learning, it will be important to use the new techniques to complement traditional imaging features instead of fully displacing them.

Using deep learning for a diffusion-based segmentation of the dentate nucleus and its benefits over atlas-based methods.

The dentate nucleus (DN) is a gray matter structure deep in the cerebellum involved in motor coordination, sensory input integration, executive planning, language, and visuospatial function. The DN is an emerging biomarker of disease, informing studies that advance pathophysiologic understanding of neurodegenerative and related disorders. The main challenge in defining the DN radiologically is that, like many deep gray matter structures, it has poor contrast in T1-weighted magnetic resonance (MR) images and therefore requires specialized MR acquisitions for visualization. Manual tracing of the DN across multiple acquisitions is resource-intensive and does not scale well to large datasets. We describe a technique that automatically segments the DN using deep learning (DL) on common imaging sequences, such as T1-weighted, T2-weighted, and diffusion MR imaging. We trained a DL algorithm that can automatically delineate the DN and provide an estimate of its volume. The automatic segmentation achieved higher agreement to the manual labels compared to template registration, which is the current common practice in DN segmentation or multiatlas segmentation of manual labels. Across all sequences, the FA maps achieved the highest mean Dice similarity coefficient (DSC) of 0.83 compared to T1 imaging ( DSC = 0.76 ), T2 imaging ( DSC = 0.79 ), or a multisequence approach ( DSC = 0.80 ). A single atlas registration approach using the spatially unbiased atlas template of the cerebellum and brainstem template achieved a DSC of 0.23, and multi-atlas segmentation achieved a DSC of 0.33. Overall, we propose a method of delineating the DN on clinical imaging that can reproduce manual labels with higher accuracy than current atlas-based tools.

Learning Implicit Brain MRI Manifolds with Deep Learning.

An important task in image processing and neuroimaging is to extract quantitative information from the acquired images in order to make observations about the presence of disease or markers of development in populations. Having a low-dimensional manifold of an image allows for easier statistical comparisons between groups and the synthesis of group representatives. Previous studies have sought to identify the best mapping of brain MRI to a low-dimensional manifold, but have been limited by assumptions of explicit similarity measures. In this work, we use deep learning techniques to investigate implicit manifolds of normal brains and generate new, high-quality images. We explore implicit manifolds by addressing the problems of image synthesis and image denoising as important tools in manifold learning. First, we propose the unsupervised synthesis of T1-weighted brain MRI using a Generative Adversarial Network (GAN) by learning from 528 examples of 2D axial slices of brain MRI. Synthesized images were first shown to be unique by performing a cross-correlation with the training set. Real and synthesized images were then assessed in a blinded manner by two imaging experts providing an image quality score of 1-5. The quality score of the synthetic image showed substantial overlap with that of the real images. Moreover, we use an autoencoder with skip connections for image denoising, showing that the proposed method results in higher PSNR than FSL SUSAN after denoising. This work shows the power of artificial networks to synthesize realistic imaging data, which can be used to improve image processing techniques and provide a quantitative framework to structural changes in the brain.

Fully Convolutional Neural Networks Improve Abdominal Organ Segmentation.

Abdominal image segmentation is a challenging, yet important clinical problem. Variations in body size, position, and relative organ positions greatly complicate the segmentation process. Historically, multi-atlas methods have achieved leading results across imaging modalities and anatomical targets. However, deep learning is rapidly overtaking classical approaches for image segmentation. Recently, Zhou et al. showed that fully convolutional networks produce excellent results in abdominal organ segmentation of computed tomography (CT) scans. Yet, deep learning approaches have not been applied to whole abdomen magnetic resonance imaging (MRI) segmentation. Herein, we evaluate the applicability of an existing fully convolutional neural network (FCNN) designed for CT imaging to segment abdominal organs on T2 weighted (T2w) MRI's with two examples. In the primary example, we compare a classical multi-atlas approach with FCNN on forty-five T2w MRI's acquired from splenomegaly patients with five organs labeled (liver, spleen, left kidney, right kidney, and stomach). Thirty-six images were used for training while nine were used for testing. The FCNN resulted in a Dice similarity coefficient (DSC) of 0.930 in spleens, 0.730 in left kidneys, 0.780 in right kidneys, 0.913 in livers, and 0.556 in stomachs. The performance measures for livers, spleens, right kidneys, and stomachs were significantly better than multi-atlas (p < 0.05, Wilcoxon rank-sum test). In a secondary example, we compare the multi-atlas approach with FCNN on 138 distinct T2w MRI's with manually labeled pancreases (one label). On the pancreas dataset, the FCNN resulted in a median DSC of 0.691 in pancreases versus 0.287 for multi-atlas. The results are highly promising given relatively limited training data and without specific training of the FCNN model and illustrate the potential of deep learning approaches to transcend imaging modalities.

Splenomegaly Segmentation using Global Convolutional Kernels and Conditional Generative Adversarial Networks.

Spleen volume estimation using automated image segmentation technique may be used to detect splenomegaly (abnormally enlarged spleen) on Magnetic Resonance Imaging (MRI) scans. In recent years, Deep Convolutional Neural Networks (DCNN) segmentation methods have demonstrated advantages for abdominal organ segmentation. However, variations in both size and shape of the spleen on MRI images may result in large false positive and false negative labeling when deploying DCNN based methods. In this paper, we propose the Splenomegaly Segmentation Network (SSNet) to address spatial variations when segmenting extraordinarily large spleens. SSNet was designed based on the framework of image-to-image conditional generative adversarial networks (cGAN). Specifically, the Global Convolutional Network (GCN) was used as the generator to reduce false negatives, while the Markovian discriminator (PatchGAN) was used to alleviate false positives. A cohort of clinically acquired 3D MRI scans (both T1 weighted and T2 weighted) from patients with splenomegaly were used to train and test the networks. The experimental results demonstrated that a mean Dice coefficient of 0.9260 and a median Dice coefficient of 0.9262 using SSNet on independently tested MRI volumes of patients with splenomegaly.

A Data Colocation Grid Framework for Big Data Medical Image Processing: Backend Design.

When processing large medical imaging studies, adopting high performance grid computing resources rapidly becomes important. We recently presented a "medical image processing-as-a-service" grid framework that offers promise in utilizing the Apache Hadoop ecosystem and HBase for data colocation by moving computation close to medical image storage. However, the framework has not yet proven to be easy to use in a heterogeneous hardware environment. Furthermore, the system has not yet validated when considering variety of multi-level analysis in medical imaging. Our target design criteria are (1) improving the framework's performance in a heterogeneous cluster, (2) performing population based summary statistics on large datasets, and (3) introducing a table design scheme for rapid NoSQL query. In this paper, we present a heuristic backend interface application program interface (API) design for Hadoop & HBase for Medical Image Processing (HadoopBase-MIP). The API includes: Upload, Retrieve, Remove, Load balancer (for heterogeneous cluster) and MapReduce templates. A dataset summary statistic model is discussed and implemented by MapReduce paradigm. We introduce a HBase table scheme for fast data query to better utilize the MapReduce model. Briefly, 5153 T1 images were retrieved from a university secure, shared web database and used to empirically access an in-house grid with 224 heterogeneous CPU cores. Three empirical experiments results are presented and discussed: (1) load balancer wall-time improvement of 1.5-fold compared with a framework with built-in data allocation strategy, (2) a summary statistic model is empirically verified on grid framework and is compared with the cluster when deployed with a standard Sun Grid Engine (SGE), which reduces 8-fold of wall clock time and 14-fold of resource time, and (3) the proposed HBase table scheme improves MapReduce computation with 7 fold reduction of wall time compare with a naïve scheme when datasets are relative small. The source code and interfaces have been made publicly available.

Right Fronto-Subcortical White Matter Microstructure Predicts Cognitive Control Ability on the Go/No-go Task in a Community Sample.

Go/no-go tasks are widely used to index cognitive control. This construct has been linked to white matter microstructure in a circuit connecting the right inferior frontal gyrus (IFG), subthalamic nucleus (STN), and pre-supplementary motor area. However, the specificity of this association has not been tested. A general factor of white matter has been identified that is related to processing speed. Given the strong processing speed component in successful performance on the go/no-go task, this general factor could contribute to task performance, but the general factor has often not been accounted for in past studies of cognitive control. Further, studies on cognitive control have generally employed small unrepresentative case-control designs. The present study examined the relationship between go/no-go performance and white matter microstructure in a large community sample of 378 subjects that included participants with a range of both clinical and subclinical nonpsychotic psychopathology. We found that white matter microstructure properties in the right IFG-STN tract significantly predicted task performance, and remained significant after controlling for dimensional psychopathology. The general factor of white matter only reached statistical significance when controlling for dimensional psychopathology. Although the IFG-STN and general factor tracts were highly correlated, when both were included in the model, only the IFG-STN remained a significant predictor of performance. Overall, these findings suggest that while a general factor of white matter can be identified in a young community sample, white matter microstructure properties in the right IFG-STN tract show a specific relationship to cognitive control. The findings highlight the importance of examining both specific and general correlates of cognition, especially in tasks with a speeded component.

Multiprotocol, multiatlas statistical fusion: theory and application.

Multiatlas segmentation offers an exceedingly convenient process by which image segmentation tools can be created from a series of labeled atlases (i.e., raters). However, creation of the atlases is exceedingly time consuming and prone to shifts in clinical/research demands as anatomical definitions are refined, combined, or subdivided. Hence, a process by which atlases from distinct, but complementary, anatomical "protocols" could be combined would allow for greater innovation in structural analysis and efficiency of data (re)use. Recent innovation in protocol fusion has shown that propagation of information across distinct protocols is feasible. However, how to effectively include this information in simultaneous truth and performance level estimation (STAPLE) has been elusive. We present a generalization of the STAPLE framework to account for multiprotocol rater performance (i.e., accuracy of registered atlases). This approach, multiset STAPLE (MS-STAPLE), provides a statistical framework for combining label information from atlases that have been labeled with distinct protocols (i.e., whole brain versus subcortical) and is compatible with the current local, nonlocal, probabilistic, log-odds, and hierarchical innovations in STAPLE theory. Using the MS-STAPLE approach, information from a broad range of datasets can be combined so that each available dataset contributes in a spatially dependent manner to local labels. We evaluate the model in simulations and in the context of an experiment where an existing set of whole-brain labels (14 structures) is refined to include parcellation of subcortical structures (26 structures). In the empirical results, we see significant improvement in the Dice similarity coefficient when comparing MS-STAPLE to STAPLE and nonlocal MS-STAPLE to nonlocal STAPLE.

Multi-Scale Hippocampal Parcellation Improves Atlas-Based Segmentation Accuracy.

Known for its distinct role in memory, the hippocampus is one of the most studied regions of the brain. Recent advances in magnetic resonance imaging have allowed for high-contrast, reproducible imaging of the hippocampus. Typically, a trained rater takes 45 minutes to manually trace the hippocampus and delineate the anterior from the posterior segment at millimeter resolution. As a result, there has been a significant desire for automated and robust segmentation of the hippocampus. In this work we use a population of 195 atlases based on T1-weighted MR images with the left and right hippocampus delineated into the head and body. We initialize the multi-atlas segmentation to a region directly around each lateralized hippocampus to both speed up and improve the accuracy of registration. This initialization allows for incorporation of nearly 200 atlases, an accomplishment which would typically involve hundreds of hours of computation per target image. The proposed segmentation results in a Dice similiarity coefficient over 0.9 for the full hippocampus. This result outperforms a multi-atlas segmentation using the BrainCOLOR atlases (Dice 0.85) and FreeSurfer (Dice 0.75). Furthermore, the head and body delineation resulted in a Dice coefficient over 0.87 for both structures. The head and body volume measurements also show high reproducibility on the Kirby 21 reproducibility population (R2 greater than 0.95, p < 0.05 for all structures). This work signifies the first result in an ongoing work to develop a robust tool for measurement of the hippocampus and other temporal lobe structures.

Cloud Engineering Principles and Technology Enablers for Medical Image Processing-as-a-Service.

Traditional in-house, laboratory-based medical imaging studies use hierarchical data structures (e.g., NFS file stores) or databases (e.g., COINS, XNAT) for storage and retrieval. The resulting performance from these approaches is, however, impeded by standard network switches since they can saturate network bandwidth during transfer from storage to processing nodes for even moderate-sized studies. To that end, a cloud-based "medical image processing-as-a-service" offers promise in utilizing the ecosystem of Apache Hadoop, which is a flexible framework providing distributed, scalable, fault tolerant storage and parallel computational modules, and HBase, which is a NoSQL database built atop Hadoop's distributed file system. Despite this promise, HBase's load distribution strategy of region split and merge is detrimental to the hierarchical organization of imaging data (e.g., project, subject, session, scan, slice). This paper makes two contributions to address these concerns by describing key cloud engineering principles and technology enhancements we made to the Apache Hadoop ecosystem for medical imaging applications. First, we propose a row-key design for HBase, which is a necessary step that is driven by the hierarchical organization of imaging data. Second, we propose a novel data allocation policy within HBase to strongly enforce collocation of hierarchically related imaging data. The proposed enhancements accelerate data processing by minimizing network usage and localizing processing to machines where the data already exist. Moreover, our approach is amenable to the traditional scan, subject, and project-level analysis procedures, and is compatible with standard command line/scriptable image processing software. Experimental results for an illustrative sample of imaging data reveals that our new HBase policy results in a three-fold time improvement in conversion of classic DICOM to NiFTI file formats when compared with the default HBase region split policy, and nearly a six-fold improvement over a commonly available network file system (NFS) approach even for relatively small file sets. Moreover, file access latency is lower than network attached storage.

Theoretical and Empirical Comparison of Big Data Image Processing with Apache Hadoop and Sun Grid Engine.

The field of big data is generally concerned with the scale of processing at which traditional computational paradigms break down. In medical imaging, traditional large scale processing uses a cluster computer that combines a group of workstation nodes into a functional unit that is controlled by a job scheduler. Typically, a shared-storage network file system (NFS) is used to host imaging data. However, data transfer from storage to processing nodes can saturate network bandwidth when data is frequently uploaded/retrieved from the NFS, e.g., "short" processing times and/or "large" datasets. Recently, an alternative approach using Hadoop and HBase was presented for medical imaging to enable co-location of data storage and computation while minimizing data transfer. The benefits of using such a framework must be formally evaluated against a traditional approach to characterize the point at which simply "large scale" processing transitions into "big data" and necessitates alternative computational frameworks. The proposed Hadoop system was implemented on a production lab-cluster alongside a standard Sun Grid Engine (SGE). Theoretical models for wall-clock time and resource time for both approaches are introduced and validated. To provide real example data, three T1 image archives were retrieved from a university secure, shared web database and used to empirically assess computational performance under three configurations of cluster hardware (using 72, 109, or 209 CPU cores) with differing job lengths. Empirical results match the theoretical models. Based on these data, a comparative analysis is presented for when the Hadoop framework will be relevant and non-relevant for medical imaging.

DAX - The Next Generation: Towards One Million Processes on Commodity Hardware.

Large scale image processing demands a standardized way of not only storage but also a method for job distribution and scheduling. The eXtensible Neuroimaging Archive Toolkit (XNAT) is one of several platforms that seeks to solve the storage issues. Distributed Automation for XNAT (DAX) is a job control and distribution manager. Recent massive data projects have revealed several bottlenecks for projects with >100,000 assessors (i.e., data processing pipelines in XNAT). In order to address these concerns, we have developed a new API, which exposes a direct connection to the database rather than REST API calls to accomplish the generation of assessors. This method, consistent with XNAT, keeps a full history for auditing purposes. Additionally, we have optimized DAX to keep track of processing status on disk (called DISKQ) rather than on XNAT, which greatly reduces load on XNAT by vastly dropping the number of API calls. Finally, we have integrated DAX into a Docker container with the idea of using it as a Docker controller to launch Docker containers of image processing pipelines. Using our new API, we reduced the time to create 1,000 assessors (a sub-cohort of our case project) from 65040 seconds to 229 seconds (a decrease of over 270 fold). DISKQ, using pyXnat, allows launching of 400 jobs in under 10 seconds which previously took 2,000 seconds. Together these updates position DAX to support projects with hundreds of thousands of scans and to run them in a time-efficient manner.