Search

Background: The “central vein sign” (CVS), a linear hypointensity on T2*-weighted imaging corresponding to a central vein/venule, is associated with multiple sclerosis (MS) lesions. The effect of lesion-size exclusion criteria on MS diagnostic accuracy has not been extensively studied. Objective: Investigate the optimal lesion-size exclusion criteria for CVS use in MS diagnosis. Methods: Cross-sectional study of 163 MS and 51 non-MS, and radiological/histopathological correlation of 5 MS and 1 control autopsy cases. The effects of lesion-size exclusion on MS diagnosis using the CVS, and intralesional vein detection on histopathology were evaluated. Results: CVS+ lesions were larger compared to CVS− lesions, with effect modification by MS diagnosis (mean difference +7.7 mm3, p = 0.004). CVS percentage-based criteria with no lesion-size exclusion showed the highest diagnostic accuracy in differentiating MS cases. However, a simple count of three or more CVS+ lesions greater than 3.5 mm is highly accurate and can be rapidly implemented (sensitivity 93%; specificity 88%). On magnetic resonance imaging (MRI)-histopathological correlation, the CVS had high specificity for identifying intralesional veins (0/7 false positives). Conclusion: Lesion-size measures add important information when using CVS+ lesion counts for MS diagnosis. The CVS is a specific biomarker corresponding to intralesional veins on histopathology.

Remyelination is crucial to recover from inflammatory demyelination in multiple sclerosis (MS). Investigating remyelination in vivo using magnetic resonance imaging (MRI) is difficult in MS, where collecting serial short-interval scans is challenging. Using experimental autoimmune encephalomyelitis (EAE) in common marmosets, a model of MS that recapitulates focal cerebral inflammatory demyelinating lesions, we investigated whether MRI is sensitive to, and can characterize, remyelination. In six animals followed with multisequence 7 T MRI, 31 focal lesions, predicted to be demyelinated or remyelinated based on signal intensity on proton density-weighted images, were subsequently assessed with histopathology. Remyelination occurred in four of six marmosets and 45% of lesions. Radiological-pathological comparison showed that MRI had high statistical sensitivity (100%) and specificity (90%) for detecting remyelination. This study demonstrates the prevalence of spontaneous remyelination in marmoset EAE and the ability of in vivo MRI to detect it, with implications for preclinical testing of pro-remyelinating agents.

The Sørensen-Dice index (SDI) is a widely used measure for evaluating medical image segmentation algorithms. It offers a standardized measure of segmentation accuracy which has proven useful. However, it offers diminishing insight when the number of objects is unknown, such as in white matter lesion segmentation of multiple sclerosis (MS) patients. We present a refinement for finer grained parsing of SDI results in situations where the number of objects is unknown. We explore these ideas with two case studies showing what can be learned from our two presented studies. Our first study explores an inter-rater comparison, showing that smaller lesions cannot be reliably identified. In our second case study, we demonstrate fusing multiple MS lesion segmentation algorithms based on the insights into the algorithms provided by our analysis to generate a segmentation that exhibits improved performance. This work demonstrates the wealth of information that can be learned from refined analysis of medical image segmentations.

Remyelination is crucial for recovery from inflammatory demyelination in multiple sclerosis (MS). Investigating remyelination in vivo using magnetic resonance imaging (MRI) is difficult in MS, where collecting serial short-interval scans is challenging. Using experimental autoimmune encephalomyelitis (EAE) in common marmosets, a model of MS that recapitulates focal cerebral MS lesions, we investigated whether remyelination can be detected and characterized noninvasively. In 6 animals followed with multisequence 7-tesla MRI, 36 focal lesions, classified as demyelinated or remyelinated based on signal intensity on proton density-weighted images, were subsequently assessed with histopathology. Remyelination occurred in 5 of 6 marmosets and 51% of lesions. Radiological-pathological comparison showed high sensitivity (88%) and specificity (90%) for detecting remyelination by in vivo MRI. This study demonstrates the prevalence of spontaneous remyelination in marmoset EAE and the ability of in vivo MRI to detect it, with implications for preclinical testing of pro-remyelinating agents and translation to clinical practice.

Background and ObjectivesThe central vein sign (CVS), a central linear hypointensity within lesions on T2*-weighted imaging, has been established as a sensitive and specific biomarker for the diagnosis of multiple sclerosis (MS). However, the CVS has not yet been comprehensively studied in newly developing MS lesions. We aimed to identify the CVS profiles of new white matter lesions in patients with MS followed over time and investigate demographic and clinical risk factors associated with new CVS+ or CVS− lesion development.MethodsIn this retrospective longitudinal cohort study, adults from the NIH MS Natural History Study were considered for inclusion. Participants with new T2 or enhancing lesions were identified through review of the radiology report and/or longitudinal subtraction imaging. Each new lesion was evaluated for the CVS. Clinical characteristics were identified through chart review.ResultsA total of 153 adults (95 relapsing-remitting MS, 27 secondary progressive MS, 16 primary progressive MS, 5 clinically isolated syndrome, and 10 healthy; 67% female) were included. Of this cohort, 96 had at least 1 new T2 or contrast-enhancing lesion during median 3.1 years (Q1–Q3: 0.7–6.3) of follow-up; lesions eligible for CVS evaluation were found in 62 (65%). Of 233 new CVS-eligible lesions, 159 (68%) were CVS+, with 30 (48%) individuals having only CVS+, 12 (19%) only CVS−, and 20 (32%) both CVS+ and CVS− lesions. In gadolinium-enhancing (Gd+) lesions, the CVS+ percentage increased from 102/152 (67%) at the first time point where the lesion was observed, to 92/114 (82%) after a median follow-up of 2.8 years. Younger age (OR = 0.5 per 10-year increase, 95% CI = 0.3–0.8) and higher CVS+ percentage at baseline (OR = 1.4 per 10% increase, 95% CI = 1.1–1.9) were associated with increased likelihood of new CVS+ lesion development.DiscussionIn a cohort of adults with MS followed over a median duration of 3 years, most newly developing T2 or enhancing lesions were CVS+ (68%), and nearly half (48%) developed new CVS+ lesions only. Importantly, the effects of edema and T2 signal changes can obscure small veins in Gd+ lesions; therefore, caution and follow-up is necessary when determining their CVS status.Trial Registration InformationClinical trial registration number NCT00001248.Classification of EvidenceThis study provides Class III evidence that younger age and higher CVS+ percentage at baseline are associated with new CVS+ lesion development.

SummaryIdentifying neural substrates of behavior requires defining actions in terms that map onto brain activity. Brain and muscle activity naturally correlate via the output of motor neurons, but apart from simple movements it has been difficult to define behavior in terms of muscle contractions. By mapping the musculature of the pupal fruit fly and comprehensively imaging muscle activation at single cell resolution, we here describe a multiphasic behavioral sequence in Drosophila. Our characterization identifies a previously undescribed behavioral phase and permits extraction of major movements by a convolutional neural network. We deconstruct movements into a syllabary of co-active muscles and identify specific syllables that are sensitive to neuromodulatory manipulations. We find that muscle activity shows considerable variability, which reduces upon neuromodulation. Our work provides a platform for studying whole-animal behavior, quantifying its variability across multiple spatiotemporal scales, and analyzing its neuromodulatory regulation at cellular resolution.

Highlights • PML has characteristic dynamic changes in brain and lesion volume on MRI. • JCnet is an automated method for brain atrophy and lesion segmentation in PML. • JCnet improves PML lesion segmentation accuracy compared to conventional methods. • JCnet can accurately track PML lesion changes over time., Progressive multifocal leukoencephalopathy (PML) is a rare opportunistic brain infection caused by the JC virus and associated with substantial morbidity and mortality. Accurate MRI assessment of PML lesion burden and brain parenchymal atrophy is of decisive value in monitoring the disease course and response to therapy. However, there are currently no validated automatic methods for quantification of PML lesion burden or associated parenchymal volume loss. Furthermore, manual brain or lesion delineations can be tedious, require the use of valuable time resources by radiologists or trained experts, and are often subjective. In this work, we introduce JCnet (named after the causative viral agent), an end-to-end, fully automated method for brain parenchymal and lesion segmentation in PML using consecutive 3D patch-based convolutional neural networks. The network architecture consists of multi-view feature pyramid networks with hierarchical residual learning blocks containing embedded batch normalization and nonlinear activation functions. The feature maps across the bottom-up and top-down pathways of the feature pyramids are merged, and an output probability membership generated through convolutional pathways, thus rendering the method fully convolutional. Our results show that this approach outperforms and improves longitudinal consistency compared to conventional, state-of-the-art methods of healthy brain and multiple sclerosis lesion segmentation, utilized here as comparators given the lack of available methods validated for use in PML. The ability to produce robust and accurate automated measures of brain atrophy and lesion segmentation in PML is not only valuable clinically but holds promise toward including standardized quantitative MRI measures in clinical trials of targeted therapies. Code is available at: https://github.com/omarallouz/JCnet.

Multiple instance learning (MIL) is a supervised learning methodology that aims to allow models to learn instance class labels from bag class labels, where a bag is defined to contain multiple instances. MIL is gaining traction for learning from weak labels but has not been widely applied to 3D medical imaging. MIL is well-suited to clinical CT acquisitions since (1) the highly anisotropic voxels hinder application of traditional 3D networks and (2) patch-based networks have limited ability to learn whole volume labels. In this work, we apply MIL with a deep convolutional neural network to identify whether clinical CT head image volumes possess one or more large hemorrhages (> 20cm$^3$), resulting in a learned 2D model without the need for 2D slice annotations. Individual image volumes are considered separate bags, and the slices in each volume are instances. Such a framework sets the stage for incorporating information obtained in clinical reports to help train a 2D segmentation approach. Within this context, we evaluate the data requirements to enable generalization of MIL by varying the amount of training data. Our results show that a training size of at least 400 patient image volumes was needed to achieve accurate per-slice hemorrhage detection. Over a five-fold cross-validation, the leading model, which made use of the maximum number of training volumes, had an average true positive rate of 98.10%, an average true negative rate of 99.36%, and an average precision of 0.9698. The models have been made available along with source code to enabled continued exploration and adaption of MIL in CT neuroimaging.

Deep learning approaches to the segmentation of magnetic resonance images have shown significant promise in automating the quantitative analysis of brain images. However, a continuing challenge has been its sensitivity to the variability of acquisition protocols. Attempting to segment images that have different contrast properties from those within the training data generally leads to significantly reduced performance. Furthermore, heterogeneous data sets cannot be easily evaluated because the quantitative variation due to acquisition differences often dwarfs the variation due to the biological differences that one seeks to measure. In this work, we describe an approach using alternating segmentation and synthesis steps that adapts the contrast properties of the training data to the input image. This allows input images that do not resemble the training data to be more consistently segmented. A notable advantage of this approach is that only a single example of the acquisition protocol is required to adapt to its contrast properties. We demonstrate the efficacy of our approaching using brain images from a set of human subjects scanned with two different T1-weighted volumetric protocols.

Purpose To explore (i) the variability of upper cervical cord area (UCCA) measurements from volumetric brain 3D T1-weighted scans related to gradient nonlinearity (GNL) and subject positioning; (ii) the effect of vendor-implemented GNL corrections; and (iii) easily applicable methods that can be used to retrospectively correct data. Methods A multiple sclerosis patient was scanned at seven sites using 3T MRI scanners with the same 3D T1-weighted protocol without GNL-distortion correction. Two healthy subjects and a phantom were additionally scanned at a single site with varying table positions. The 2D and 3D vendor-implemented GNL-correction algorithms and retrospective methods based on (i) phantom data fit, (ii) normalization with C2 vertebral body diameters, and (iii) the Jacobian determinant of nonlinear registrations to a template were tested. Results Depending on the positioning of the subject, GNL introduced up to 15% variability in UCCA measurements from volumetric brain T1-weighted scans when no distortion corrections were used. The 3D vendor-implemented correction methods and the three proposed methods reduced this variability to less than 3%. Conclusions Our results raise awareness of the significant impact that GNL can have on quantitative UCCA studies, and point the way to prospectively and retrospectively managing GNL distortions in a variety of settings, including clinical environments. Magn Reson Med, 2017. © 2017 International Society for Magnetic Resonance in Medicine.

Multi-modal deformable registration is important for many medical image analysis tasks such as atlas alignment, image fusion, and distortion correction. Whereas a conventional method would register images with different modalities using modality independent features or information theoretic metrics such as mutual information, this paper presents a new framework that addresses the problem using a two-channel registration algorithm capable of using mono-modal similarity measures such as sum of squared differences or cross-correlation. To make it possible to use these same-modality measures, image synthesis is used to create proxy images for the opposite modality as well as intensity-normalized images from each of the two available images. The new deformable registration framework was evaluated by performing intra-subject deformation recovery, intra-subject boundary alignment, and inter-subject label transfer experiments using multi-contrast magnetic resonance brain imaging data. Three different multi-channel registration algorithms were evaluated, revealing that the framework is robust to the multi-channel deformable registration algorithm that is used. With a single exception, all results demonstrated improvements when compared against single channel registrations using the same algorithm with mutual information.

PURPOSE: As deep neural networks achieve more success in the wide field of computer vision, greater emphasis is being placed on the generalizations of these models for production deployment. With sufficiently large training datasets, models can typically avoid overfitting their data; however, for medical imaging it is often difficult to obtain enough data from a single site. Sharing data between institutions is also frequently nonviable or prohibited due to security measures and research compliance constraints, enforced to guard protected health information (PHI) and patient anonymity. METHODS: In this paper, we implement cyclic weight transfer with independent datasets from multiple geographically disparate sites without compromising PHI. We compare results between single-site learning (SSL) and multi-site learning models (MSL) on testing data drawn from each of the training sites as well as two other institutions. RESULTS: The MSL model attains an average Dice Similarity Coefficient (DSC) of 0.690 on the holdout institution datasets with a volume correlation of 0.914, respectively corresponding to a 7% and 5% statistically significant improvement over the average of both SSL models, which attained an average DSC of 0.646 and average correlation of 0.871. CONCLUSIONS: We show that a neural network can be efficiently trained on data from two physically remote sites without consolidating patient data to a single location. The resulting network improves model generalization and achieves higher average DSCs on external datasets than neural networks trained on data from a single source.

Machine learning models are becoming commonplace in the domain of medical imaging, and with these methods comes an ever-increasing need for more data. However, to preserve patient anonymity it is frequently impractical or prohibited to transfer protected health information (PHI) between institutions. Additionally, due to the nature of some studies, there may not be a large public dataset available on which to train models. To address this conundrum, we analyze the efficacy of transferring the model itself in lieu of data between different sites. By doing so we accomplish two goals: 1) the model gains access to training on a larger dataset that it could not normally obtain and 2) the model better generalizes, having trained on data from separate locations. In this paper, we implement multi-site learning with disparate datasets from the National Institutes of Health (NIH) and Vanderbilt University Medical Center (VUMC) without compromising PHI. Three neural networks are trained to convergence on a computed tomography (CT) brain hematoma segmentation task: one only with NIH data, one only with VUMC data, and one multi-site model alternating between NIH and VUMC data. Resultant lesion masks with the multi-site model attain an average Dice similarity coefficient of 0.64 and the automatically segmented hematoma volumes correlate to those done manually with a Pearson correlation coefficient of 0.87, corresponding to an 8% and 5% improvement, respectively, over the single-site model counterparts.

Numerous brain disorders are associated with ventriculomegaly; normal pressure hydrocephalus (NPH) is one example. NPH presents with dementia-like symptoms and is often misdiagnosed as Alzheimer’s due to its chronic nature and nonspecific presenting symptoms. However, unlike other forms of dementia NPH can be treated surgically with an over 80% success rate on appropriately selected patients. Accurate assessment of the ventricles, in particular its sub-compartments, is required to diagnose the condition. Existing segmentation algorithms fail to accurately identify the ventricles in patients with such extreme pathology. We present an improvement to a whole brain segmentation approach that accurately identifies the ventricles and parcellates them into four sub-compartments. Our work is a combination of patch-based tissue segmentation and multi-atlas registration-based labeling. We include a validation on NPH patients, demonstrating superior performance against state-of-the-art methods.

The subarachnoid space is a layer in the meninges that surrounds the brain and is filled with trabeculae and cerebrospinal fluid. Quantifying the volume and thickness of the subarachnoid space is of interest in order to study the pathogenesis of neurodegenerative diseases and compare with healthy subjects. We present an automatic method to reconstruct the subarachnoid space with subvoxel accuracy using a nested deformable model. The method initializes the deformable model using the convex hull of the union of the outer surfaces of the cerebrum, cerebellum and brainstem. A region force is derived from the subject’s T1-weighted and T2-weighted MRI to drive the deformable model to the outer surface of the subarachnoid space. The proposed method is compared to a semi-automatic delineation from the subject’s T2-weighted MRI and an existing multi-atlas-based method. A small pilot study comparing the volume and thickness measurements in a set of age-matched subjects with normal pressure hydrocephalus and healthy controls is presented to show the efficacy of the proposed method.

Traumatic brain injury (TBI) is caused by a sudden trauma to the head that may result in hematomas and contusions and can lead to stroke or chronic disability. An accurate quantification of the lesion volumes and their locations is essential to understand the pathophysiology of TBI and its progression. In this paper, we propose a fully convolutional neural network (CNN) model to segment contusions and lesions from brain magnetic resonance (MR) images of patients with TBI. The CNN architecture proposed here was based on a state of the art CNN architecture from Google, called Inception. Using a 3-layer Inception network, lesions are segmented from multi-contrast MR images. When compared with two recent TBI lesion segmentation methods, one based on CNN (called DeepMedic) and another based on random forests, the proposed algorithm showed improved segmentation accuracy on images of 18 patients with mild to severe TBI. Using a leave-one-out cross validation, the proposed model achieved a median Dice of 0.75, which was significantly better (p, https://ieeexplore.ieee.org/abstract/document/8363545/, IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)

Magnetic Resonance (MR) imaging allows the acquisition of images with different contrast properties depending on the acquisition protocol and the magnetic properties of tissues. Many MR brain image processing techniques, such as tissue segmentation, require multiple MR contrasts as inputs, and each contrast is treated differently. Thus it is advantageous to automate the identification of image contrasts for various purposes, such as facilitating image processing pipelines, and managing and maintaining large databases via content-based image retrieval (CBIR). Most automated CBIR techniques focus on a two-step process: extracting features from data and classifying the image based on these features. We present a novel 3D deep convolutional neural network (CNN)-based method for MR image contrast classification. The proposed CNN automatically identifies the MR contrast of an input brain image volume. Specifically, we explored three classification problems: (1) identify T1-weighted (T1-w), T2-weighted (T2-w), and fluid-attenuated inversion recovery (FLAIR) contrasts, (2) identify pre vs post-contrast T1, (3) identify pre vs post-contrast FLAIR. A total of 3418 image volumes acquired from multiple sites and multiple scanners were used. To evaluate each task, the proposed model was trained on 2137 images and tested on the remaining 1281 images. Results showed that image volumes were correctly classified with 97.57% accuracy., Comment: Github: https://github.com/sremedios/phinet

We propose a new approach to Multiple Sclerosis lesion segmentation that utilizes synthesized images. A new method of image synthesis is considered: joint intensity fusion (JIF). JIF synthesizes an image from a library of deformably registered and intensity normalized atlases. Each location in the synthesized image is a weighted average of the registered atlases; atlas weights vary spatially. The weights are determined using the joint label fusion (JLF) framework. The primary methodological contribution is the application of JLF to MRI signal directly rather than labels. Synthesized images are then used as additional features in a lesion segmentation task using the OASIS classifier, a logistic regression model on intensities from multiple modalities. The addition of JIF synthesized images improved the Dice-Sorensen coefficient (relative to manually drawn gold standards) of lesion segmentations over the standard model segmentations by \(0.0462 \pm 0.0050\) (mean ± standard deviation) at optimal threshold over all subjects and 10 separate training/testing folds.

A key feature of magnetic resonance (MR) imaging is its ability to manipulate how the intrinsic tissue parameters of the anatomy ultimately contribute to the contrast properties of the final, acquired image. This flexibility, however, can lead to substantial challenges for segmentation algorithms, particularly supervised methods. These methods require atlases or training data, which are composed of MR image and labeled image pairs. In most cases, the training data are obtained with a fixed acquisition protocol, leading to suboptimal performance when an input data set that requires segmentation has differing contrast properties. This drawback is increasingly significant with the recent movement towards multi-center research studies involving multiple scanners and acquisition protocols. In this work, we propose a new framework for supervised segmentation approaches that is robust to contrast differences between the training MR image and the input image. Our approach uses a generative simulation model within the segmentation process to compensate for the contrast differences. We allow the contrast of the MR image in the training data to vary by simulating a new contrast from the corresponding label image. The model parameters are optimized by a cost function measuring the consistency between the input MR image and its simulation based on a current estimate of the segmentation labels. We provide a proof of concept of this approach by combining a supervised classifier with a simple simulation model, and apply the resulting algorithm to synthetic images and actual MR images., Comment: Proceedings Volume 10578, Medical Imaging 2018: Biomedical Applications in Molecular, Structural, and Functional Imaging; SPIE Medical Imaging 2018

The Dice overlap ratio is commonly used to evaluate the performance of image segmentation algorithms. While Dice overlap is very useful as a standardized quantitative measure of segmentation accuracy in many applications, it offers a very limited picture of segmentation quality in complex segmentation tasks where the number of target objects is not known a priori, such as the segmentation of white matter lesions or lung nodules. While Dice overlap can still be used in these applications, segmentation algorithms may perform quite differently in ways not reflected by differences in their Dice score. Here we propose a new set of evaluation techniques that offer new insights into the behavior of segmentation algorithms. We illustrate these techniques with a case study comparing two popular multiple sclerosis (MS) lesion segmentation algorithms: OASIS and LesionTOADS.

Objective: Pathology in both cortex and deep gray matter contribute to disability in multiple sclerosis (MS). We used the increased signal-to-noise ratio of 7-tesla (7T) MRI to visualize small lesions within the thalamus and to relate this to clinical information and cortical lesions. Methods: We obtained 7T MRI scans on 34 MS cases and 15 healthy volunteers. Thalamic lesion number and volume were related to demographic data, clinical disability measures, and lesions in cortical gray matter. Results: Thalamic lesions were found in 24/34 of MS cases. Two lesion subtypes were noted: discrete, ovoid lesions, and more diffuse lesional areas lining the periventricular surface. The number of thalamic lesions was greater in progressive MS compared to relapsing–remitting (mean ±SD, 10.7 ±0.7 vs. 3.0 ±0.7, respectively, p < 0.001). Thalamic lesion burden (count and volume) correlated with EDSS score and measures of cortical lesion burden, but not with white matter lesion burden or white matter volume. Conclusions: Using 7T MRI allows identification of thalamic lesions in MS, which are associated with disability, progressive disease, and cortical lesions. Thalamic lesion analysis may be a simpler, more rapid estimate of overall gray matter lesion burden in MS.

The simulation of magnetic resonance (MR) images plays an important role in the validation of image analysis algorithms such as image segmentation, due to lack of sufficient ground truth in real MR images. Previous work on MRI simulation has focused on explicitly modeling the MR image formation process. However, because of the overwhelming complexity of MR acquisition these simulations must involve simplifications and approximations that can result in visually unrealistic simulated images. In this work, we describe an example-based simulation framework, which uses an “atlas” consisting of an MR image and its anatomical models derived from the hard segmentation. The relationships between the MR image intensities and its anatomical models are learned using a patch-based regression that implicitly models the physics of the MR image formation. Given the anatomical models of a new brain, a new MR image can be simulated using the learned regression. This approach has been extended to also simulate intensity inhomogeneity artifacts based on the statistical model of training data. Results show that the example based MRI simulation method is capable of simulating different image contrasts and is robust to different choices of atlas. The simulated images resemble real MR images more than simulations produced by a physics-based model.

Different magnetic resonance imaging pulse sequences are used to generate image contrasts based on physical properties of tissues, which provide different and often complementary information about them. Therefore multiple image contrasts are useful for multimodal analysis of medical images. Often, medical image processing algorithms are optimized for particular image contrasts. If a desirable contrast is unavailable, contrast synthesis (or modality synthesis) methods try to “synthesize” the unavailable constrasts from the available ones. Most of the recent image synthesis methods generate synthetic brain images, while whole head magnetic resonance (MR) images can also be useful for many applications. We propose an atlas based patch matching algorithm to synthesize \(T_2-\)w whole head (including brain, skull, eyes etc.) images from \(T_1-\)w images for the purpose of distortion correction of diffusion weighted MR images. The geometric distortion in diffusion MR images due to inhomogeneous \(B_0\) magnetic field are often corrected by non-linearly registering the corresponding \(b=0\) image with zero diffusion gradient to an undistorted \(T_2-\)w image. We show that our synthetic \(T_2-\)w images can be used as a template in absence of a real \(T_2-\)w image. Our patch based method requires multiple atlases with \(T_1\) and \(T_2\) to be registered to a given target \(T_1\). Then for every patch on the target, multiple similar looking matching patches are found on the atlas \(T_1\) images and corresponding patches on the atlas \(T_2\) images are combined to generate a synthetic \(T_2\) of the target. We experimented on image data obtained from 44 patients with traumatic brain injury (TBI), and showed that our synthesized \(T_2\) images produce more accurate distortion correction than a state-of-the-art registration based image synthesis method.

PURPOSE: To explore: (1) the variability of upper cervical cord area (UCCA) measurements from volumetric brain 3D T1-weighted scans related to gradient nonlinearity (GNL) and subject positioning; (2) the effect of vendor-implemented GNL-corrections; and (3) easily applicable methods that can be used to retrospectively correct data. METHODS: A multiple sclerosis patient was scanned at 7 sites using 3T MRI scanners with the same 3D T1-weighted protocol without GNL-distortion correction. Two healthy subjects and a phantom were additionally scanned at a single site with varying table positions. 2D and 3D vendor-implemented GNL-correction algorithms and retrospective methods based on: (1) phantom data fit; (2) normalization with C2 vertebral body diameters; and (3) the Jacobian determinant of non-linear registrations to a template, were tested. RESULTS: Depending on positioning of the subject, GNL introduced up to 15% variability in UCCA measurements from volumetric brain T1-weighted scans when no distortion corrections were utilized. 3D vendor-implemented correction methods and the three proposed methods reduced this variability to less than 3%. CONCLUSION: Our results raise awareness of the significant impact that GNL can have on quantitative UCCA studies and point the way to prospectively and retrospectively managing GNL-distortions in a variety of settings, including clinical environments.

BACKGROUND AND PURPOSE: MR imaging can be used to measure structural changes in the brains of individuals with multiple sclerosis and is essential for diagnosis, longitudinal monitoring, and therapy evaluation. The North American Imaging in Multiple Sclerosis Cooperative steering committee developed a uniform high-resolution 3T MR imaging protocol relevant to the quantification of cerebral lesions and atrophy and implemented it at 7 sites across the United States. To assess intersite variability in scan data, we imaged a volunteer with relapsing-remitting MS with a scan-rescan at each site. MATERIALS AND METHODS: All imaging was acquired on Siemens scanners (4 Skyra, 2 Tim Trio, and 1 Verio). Expert segmentations were manually obtained for T1-hypointense and T2 (FLAIR) hyperintense lesions. Several automated lesion-detection and whole-brain, cortical, and deep gray matter volumetric pipelines were applied. Statistical analyses were conducted to assess variability across sites, as well as systematic biases in the volumetric measurements that were site-related. RESULTS: Systematic biases due to site differences in expert-traced lesion measurements were significant (P 90% of the variation (range, 13.0–16.4 mL in T1 and 15.9–20.1 mL in T2) in lesion volumes. Site also explained >80% of the variation in most automated volumetric measurements. Output measures clustered according to scanner models, with similar results from the Skyra versus the other 2 units. CONCLUSIONS: Even in multicenter studies with consistent scanner field strength and manufacturer after protocol harmonization, systematic differences can lead to severe biases in volumetric analyses.

With the increasing popularity of PET-MR scanners in clinical applications, synthesis of CT images from MR has been an important research topic. Accurate PET image reconstruction requires attenuation correction, which is based on the electron density of tissues and can be obtained from CT images. While CT measures electron density information for x-ray photons, MR images convey information about the magnetic properties of tissues. Therefore, with the advent of PET-MR systems, the attenuation coefficients need to be indirectly estimated from MR images. In this paper, we propose a fully convolutional neural network (CNN) based method to synthesize head CT from ultra-short echo-time (UTE) dual-echo MR images. Unlike traditional $T_1$-w images which do not have any bone signal, UTE images show some signal for bone, which makes it a good candidate for MR to CT synthesis. A notable advantage of our approach is that accurate results were achieved with a small training data set. Using an atlas of a single CT and dual-echo UTE pair, we train a deep neural network model to learn the transform of MR intensities to CT using patches. We compared our CNN based model with a state-of-the-art registration based as well as a Bayesian model based CT synthesis method, and showed that the proposed CNN model outperforms both of them. We also compared the proposed model when only $T_1$-w images are available instead of UTE, and show that UTE images produce better synthesis than using just $T_1$-w images.

Integrated PET/MR systems are becoming increasingly popular in clinical and research applications. Quantitative PET reconstruction requires correction for γ-photon attenuations using an attenuation coefficient map (μ map) that is a measure of the electron density. One challenge of PET/MR, in contrast to PET/CT, lies in the accurate computation of μ maps. Unlike CT, MR imaging measures physical properties not directly related to electron density. Previous approaches have computed the attenuation coefficients using a segmentation of MR images or using deformable registration of atlas CT images to the space of the subject MR images. Methods: In this work, we propose a patch-based method to generate whole-head μ maps from ultrashort echo-time (UTE) MR imaging sequences. UTE images are preferred to other MR sequences because of the increased signal from bone. To generate a synthetic CT image, we use patches from a reference dataset, which consists of dual-echo UTE images and a coregistered CT scan from the same subject. Matching of patches between the reference and target images allows corresponding patches from the reference CT scan to be combined via a Bayesian framework. No registration or segmentation is required. Results: For evaluation, UTE, CT, and PET data acquired from 5 patients under an institutional review board–approved protocol were used. Another patient (with UTE and CT data only) was selected to be the reference to generate synthetic CT images for these 5 patients. PET reconstructions were attenuation-corrected using the original CT, our synthetic CT, Siemens Dixon-based μ maps, Siemens UTE-based μ maps, and deformable registration-based CT. Our synthetic CT–based PET reconstruction showed higher correlation (average ρ = 0.996, R2 = 0.991) to the original CT-based PET, as compared with the segmentation- and registration-based methods. Synthetic CT–based reconstruction had minimal bias (regression slope, 0.990), as compared with the segmentation-based methods (regression slope, 0.905). A peak signal-to-noise ratio of 35.98 dB in the reconstructed PET activity was observed, compared with 29.767, 29.34, and 27.43 dB for the Siemens Dixon-, UTE-, and registration-based μ maps. Conclusion: A patch-matching approach to synthesize CT images from dual-echo UTE images leads to significantly improved accuracy of PET reconstruction as compared with actual CT scans. The PET reconstruction is improved over segmentation- (Dixon and Siemens UTE) and registration-based methods, even in subjects with pathologic findings.

The performance of image analysis algorithms applied to magnetic resonance images is strongly influenced by the pulse sequences used to acquire the images. Algorithms are typically optimized for a targeted tissue contrast obtained from a particular implementation of a pulse sequence on a specific scanner. There are many practical situations, including multi-institution trials, rapid emergency scans, and scientific use of historical data, where the images are not acquired according to an optimal protocol or the desired tissue contrast is entirely missing. This paper introduces an image restoration technique that recovers images with both the desired tissue contrast and a normalized intensity profile. This is done using patches in the acquired images and an atlas containing patches of the acquired and desired tissue contrasts. The method is an example-based approach relying on sparse reconstruction from image patches. Its performance in demonstrated using several examples, including image intensity normalization, missing tissue contrast recovery, automatic segmentation, and multimodal registration. These examples demonstrate potential practical uses and also illustrate limitations of our approach.

BACKGROUND Multiple sclerosis (MS) is characterized by physical and mental impairments that often result in pain and reduced quality of life. OBJECTIVE To understand the relationship of pain, quality of life, and cognition to structural measures of brain volume. METHODS Behavioral measures were assessed in a single session using standardized questionnaires and rating scales. Brain volume measures were assessed with structural magnetic resonance imaging (MRI). RESULTS Twenty-nine individuals with relapsing-remitting MS and 29 age-matched controls participated in this study. Pain, quality of life, and cognition were significantly interrelated. Higher fluid attenuation inversion recovery weighted lesion volume was significantly associated with increased reports of pain (p = 0.01), lower physical quality of life (p

Segmenting $$T_2$$-weighted white matter lesions from longitudinal MR images is essential in understanding progression of multiple sclerosis. Most lesion segmentation techniques find lesions independently at each time point, even though there are different noise and image contrast variations at each point in the time series. In this paper, we present a patch based 4D lesion segmentation method that takes advantage of the temporal component of longitudinal data. For each subject with multiple time-points, 4D patches are constructed from the $$T_1$$-w and FLAIR scans of all time-points. For every 4D patch from a subject, a few relevant matching 4D patches are found from a reference, such that their convex combination reconstructs the subject's 4D patch. Then corresponding manual segmentation patches of the reference are combined in a similar manner to generate a 4D membership of lesions of the subject patch. We compare our 4D patch-based segmentation with independent 3D voxel-based and patch-based lesion segmentation algorithms. Based on ground truth segmentations from 30 data sets, we show that the mean Dice coefficients between manual and automated segmentations improve after using the 4D approach compared to two state-of-the-art 3D segmentation algorithms.

Contains fulltext : 173122.pdf (Publisher’s version ) (Closed access) In conjunction with the ISBI 2015 conference, we organized a longitudinal lesion segmentation challenge providing training and test data to registered participants. The training data consisted of five subjects with a mean of 4.4 time-points, and test data of fourteen subjects with a mean of 4.4 time-points. All 82 data sets had the white matter lesions associated with multiple sclerosis delineated by two human expert raters. Eleven teams submitted results using state-of-the-art lesion segmentation algorithms to the challenge, with ten teams presenting their results at the conference. We present a quantitative evaluation comparing the consistency of the two raters as well as exploring the performance of the eleven submitted results in addition to three other lesion segmentation algorithms. The challenge presented three unique opportunities: (1) the sharing of a rich data set; (2) collaboration and comparison of the various avenues of research being pursued in the community; and (3) a review and refinement of the evaluation metrics currently in use. We report on the performance of the challenge participants, as well as the construction and evaluation of a consensus delineation. The image data and manual delineations will continue to be available for download, through an evaluation website2 as a resource for future researchers in the area. This data resource provides a platform to compare existing methods in a fair and consistent manner to each other and multiple manual raters.

Normal pressure hydrocephalus (NPH) affects older adults and is thought to be caused by obstruction of the normal flow of cerebrospinal fluid (CSF). NPH typically presents with cognitive impairment, gait dysfunction, and urinary incontinence, and may account for more than five percent of all cases of dementia. Unlike most other causes of dementia, NPH can potentially be treated and the neurological dysfunction reversed by shunt surgery or endoscopic third ventriculostomy (ETV), which drain excess CSF. However, a major diagnostic challenge remains to robustly identify shunt-responsive NPH patients from patients with enlarged ventricles due to other neurodegenerative diseases. Currently, radiologists grade the severity of NPH by detailed examination and measurement of the ventricles based on stacks of 2D magnetic resonance images (MRIs). Here we propose a new method to automatically segment and label different compartments of the ventricles in NPH patients from MRIs. While this task has been achieved in healthy subjects, the ventricles in NPH are both enlarged and deformed, causing current algorithms to fail. Here we combine a patch-based tissue classification method with a registration-based multi-atlas labeling method to generate a novel algorithm that labels the lateral, third, and fourth ventricles in subjects with ventriculomegaly. The method is also applicable to other neurodegenerative diseases such as Alzheimer's disease; a condition considered in the differential diagnosis of NPH. Comparison with state of the art segmentation techniques demonstrate substantial improvements in labeling the enlarged ventricles, indicating that this strategy may be a viable option for the diagnosis and characterization of NPH.

Mapping brain structure in relation to neurological development, function, plasticity, and disease is widely considered to be one of the most essential challenges for opening new lines of neuro-scientific inquiry. Recent developments with MRI analysis of structural connectivity, anatomical brain segmentation, cortical surface parcellation, and functional imaging have yielded fantastic advances in our ability to probe the neurological structure-function relationship in vivo. To date, the image analysis efforts in each of these areas have typically focused on a single modality. Here, we extend the cortical reconstruction using implicit surface evolution (CRUISE) methodology to perform efficient, consistent, and topologically correct analyses in a natively multi-parametric manner. This effort combines and extends state-of-the-art techniques to simultaneously consider and analyze structural and diffusion information alongside quantitative and functional imaging data. Robust and consistent estimates of the cortical surface extraction, cortical labeling, diffusion-inferred contrasts, diffusion tractography, and subcortical parcellation are demonstrated in a scan-rescan paradigm. Accompanying this demonstration, we present a fully automated software system complete with validation data.

Several popular classification algorithms used to segment magnetic resonance brain images assume that the image intensities, or log-transformed intensities, satisfy a finite Gaussian mixture model. In these methods, the parameters of the mixture model are estimated and the posterior probabilities for each tissue class are used directly as soft segmentations or combined to form a hard segmentation. It is suggested and shown in this paper that a Rician mixture model fits the observed data better than a Gaussian model. Accordingly, a Rician mixture model is formulated and used within an expectation maximization (EM) framework to yield a new tissue classification algorithm called RiCE (Rician Classifier using EM). It is shown using both simulated and real data that RiCE yields comparable or better performance to that of algorithms based on the finite Gaussian mixture model. As well, we show that RiCE yields more consistent segmentation results when used on images of the same individual acquired with different T1-weighted pulse sequences. Therefore, RiCE has the potential to stabilize segmentation results in brain studies involving heterogeneous acquisition sources as is typically found in both multi-center and longitudinal studies.

Importance Cortical lesions (CLs) contribute to physical and cognitive disability in multiple sclerosis (MS). Accurate methods for visualization of CLs are necessary for future clinical studies and therapeutic trials in MS. Objective To evaluate the clinical relevance of measures of CL burden derived from high-field magnetic resonance imaging (MRI) in MS. Design, Setting, and Participants An observational clinical imaging study was conducted at an academic MS center. Participants included 36 individuals with MS (30 relapsing-remitting, 6 secondary or primary progressive) and 15 healthy individuals serving as controls. The study was conducted from March 10, 2010, to November 23, 2012, and analysis was performed from June 1, 2011, to September 30, 2014. Seven-Tesla MRI of the brain was performed with 0.5-mm isotropic resolution magnetization-prepared rapid acquisition gradient echo (MPRAGE) and whole-brain, 3-dimensional, 1.0-mm isotropic resolution magnetization–prepared, fluid-attenuated inversion recovery (MPFLAIR). Cortical lesions, seen as hypointensities on MPRAGE, were manually segmented. Lesions were classified as leukocortical, intracortical, or subpial. Images were segmented using the Lesion-TOADS (Topology-Preserving Anatomical Segmentation) algorithm, and brain structure volumes and white matter (WM) lesion volume were reported. Volumes were normalized to intracranial volume. Main Outcomes and Measures Physical disability was measured by the Expanded Disability Status Scale (EDSS). Cognitive disability was measured with the Minimal Assessment of Cognitive Function in MS battery. Results Cortical lesions were noted in 35 of 36 participants (97%), with a median of 16 lesions per participant (range, 0-99). Leukocortical lesion volume correlated with WM lesion volume (ρ = 0.50; P = .003) but not with cortical volume; subpial lesion volume inversely correlated with cortical volume (ρ = −0.36; P = .04) but not with WM lesion volume. Total CL count and volume, measured as median (range), were significantly increased in participants with EDSS scores of 5.0 or more vs those with scores less than 5.0 (count: 29 [11-99] vs 13 [0-51]; volume: 2.81 × 10 −4 [1.30 × 10 −4 to 7.90 × 10 −4 ] vs 1.50 × 10 −4 [0 to 1.01 × 10 −3 ]) and in cognitively impaired vs unimpaired individuals (count: 21 [0-99] vs 13 [1-54]; volume: 3.51 × 10 −4 [0 to 1.01 × 10 −4 ] vs 1.19 × 10 −4 [0 to 7.17 × 10 −4 ]). Cortical lesion volume correlated with EDSS scores more robustly than did WM lesion volume (ρ = 0.59 vs 0.36). Increasing log[CL volume] conferred a 3-fold increase in the odds of cognitive impairment (odds ratio [OR], 3.36; 95% CI, 1.07-10.59; P = .04) after adjustment for age and sex and a 14-fold increase in odds after adjustment for WM lesion volume and atrophy (OR, 14.26; 95% CI, 1.06-192.37; P = .045). Leukocortical lesions had the greatest effect on cognition (OR for log [leukocortical lesion volume], 9.65; 95% CI, 1.70-54.59, P = .01). Conclusions and Relevance This study provides in vivo evidence that CLs are associated with cognitive and physical disability in MS and that leukocortical and subpial lesion subtypes have differing clinical relevance. Quantitative assessments of CL burden on high-field MRI may further our understanding of the development of disability and progression in MS and lead to more effective treatments.

The aim of this work was to determine whether atrophy of specific retinal layers and brain substructures are associated over time, in order to further validate the utility of optical coherence tomography (OCT) as an indicator of neuronal tissue damage in patients with multiple sclerosis (MS).Cirrus high-definition OCT (including automated macular segmentation) was performed in 107 MS patients biannually (median follow-up: 46 months). Three-Tesla magnetic resonance imaging brain scans (including brain-substructure volumetrics) were performed annually. Individual-specific rates of change in retinal and brain measures (estimated with linear regression) were correlated, adjusting for age, sex, disease duration, and optic neuritis (ON) history.Rates of ganglion cell + inner plexiform layer (GCIP) and whole-brain (r = 0.45; p 0.001), gray matter (GM; r = 0.37; p 0.001), white matter (WM; r = 0.28; p = 0.007), and thalamic (r = 0.38; p 0.001) atrophy were associated. GCIP and whole-brain (as well as GM and WM) atrophy rates were more strongly associated in progressive MS (r = 0.67; p 0.001) than relapsing-remitting MS (RRMS; r = 0.33; p = 0.007). However, correlation between rates of GCIP and whole-brain (and additionally GM and WM) atrophy in RRMS increased incrementally with step-wise refinement to exclude ON effects; excluding eyes and then patients (to account for a phenotype effect), the correlation increased to 0.45 and 0.60, respectively, consistent with effect modification. In RRMS, lesion accumulation rate was associated with GCIP (r = -0.30; p = 0.02) and inner nuclear layer (r = -0.25; p = 0.04) atrophy rates.Over time GCIP atrophy appears to mirror whole-brain, and particularly GM, atrophy, especially in progressive MS, thereby reflecting underlying disease progression. Our findings support OCT for clinical monitoring and as an outcome in investigative trials.

Quantitative measurements from segmentations of soft tissues from magnetic resonance images (MRI) of human brains provide important biomarkers for normal aging, as well as disease progression. In this paper, we propose a patch-based tissue classification method from MR images using sparse dictionary learning from an atlas. Unlike most atlas-based classification methods, deformable registration from the atlas to the subject is not required. An “atlas” consists of an MR image, its tissue probabilities, and the hard segmentation. The “subject” consists of the MR image and the corresponding affine registered atlas probabilities (or priors). A subject specific patch dictionary is created by learning relevant patches from the atlas. Then the subject patches are modeled as sparse combinations of learned atlas patches. The same sparse combination is applied to the segmentation patches of the atlas to generate tissue memberships of the subject. The novel combination of prior probabilities in the example patches enables us to distinguish tissues having similar intensities but having different spatial location. We show that our method outperforms two state-of-the-art whole brain tissue segmentation methods. We experimented on 12 subjects having manual tissue delineations, obtaining mean Dice coefficients of 0.91 and 0.87 for cortical gray matter and cerebral white matter, respectively. In addition, experiments on subjects with ventriculomegaly shows significantly better segmentation using our approach than the competing methods.

Automatic processing of magnetic resonance images is a vital part of neuroscience research. Yet even the best and most widely used medical image processing methods will not produce consistent results when their input images are acquired with different pulse sequences. Although intensity standardization and image synthesis methods have been introduced to address this problem, their performance remains dependent on knowledge and consistency of the pulse sequences used to acquire the images. In this paper, an image synthesis approach that first estimates the pulse sequence parameters of the subject image is presented. The estimated parameters are then used with a collection of atlas or training images to generate a new atlas image having the same contrast as the subject image. This additional image provides an ideal source from which to synthesize any other target pulse sequence image contained in the atlas. In particular, a nonlinear regression intensity mapping is trained from the new atlas image to the target atlas image and then applied to the subject image to yield the particular target pulse sequence within the atlas. Both intensity standardization and synthesis of missing tissue contrasts can be achieved using this framework. The approach was evaluated on both simulated and real data, and shown to be superior in both intensity standardization and synthesis to other established methods.

This paper proposes a longitudinal intensity normalization algorithm for T1-weighted magnetic resonance images of human brains in the presence of multiple sclerosis lesions, aiming towards stable and consistent longitudinal segmentations. Unlike previous longitudinal segmentation methods, we propose a 4D intensity normalization that can be used as a preprocessing step to any segmentation method. The variability in intensities arising from the relapsing and remitting nature of the multiple sclerosis lesions is modeled into an otherwise smooth intensity transform based on first order autoregressive models, resulting in smooth changes in segmentation statistics of normal tissues, while keeping the lesion information unaffected. We validated our method on both simulated and real longitudinal normal subjects and on multiple sclerosis subjects.

Computed tomography (CT) is the standard imaging modality for patient dose calculation for radiation therapy. Magnetic resonance (MR) imaging (MRI) is used along with CT to identify brain structures due to its superior soft tissue contrast. Registration of MR and CT is necessary for accurate delineation of the tumor and other structures, and is critical in radiotherapy planning. Mutual information (MI) or its variants are typically used as a similarity metric to register MRI to CT. However, unlike CT, MRI intensity does not have an accepted calibrated intensity scale. Therefore, MI-based MR-CT registration may vary from scan to scan as MI depends on the joint histogram of the images. In this paper, we propose a fully automatic framework for MR-CT registration by synthesizing a synthetic CT image from MRI using a co-registered pair of MR and CT images as an atlas. Patches of the subject MRI are matched to the atlas and the synthetic CT patches are estimated in a probabilistic framework. The synthetic CT is registered to the original CT using a deformable registration and the computed deformation is applied to the MRI. In contrast to most existing methods, we do not need any manual intervention such as picking landmarks or regions of interests. The proposed method was validated on ten brain cancer patient cases, showing 25% improvement in MI and correlation between MR and CT images after registration compared to state-of-the-art registration methods.

Automatic and accurate detection of white matter lesions is a significant step toward understanding the progression of many diseases, like Alzheimer’s disease or multiple sclerosis. Multi-modal MR images are often used to segment T2 white matter lesions that can represent regions of demyelination or ischemia. Some automated lesion segmentation methods describe the lesion intensities using generative models, and then classify the lesions with some combination of heuristics and cost minimization. In contrast, we propose a patch-based method, in which lesions are found using examples from an atlas containing multi-modal MR images and corresponding manual delineations of lesions. Patches from subject MR images are matched to patches from the atlas and lesion memberships are found based on patch similarity weights. We experiment on 43 subjects with MS, whose scans show various levels of lesion-load. We demonstrate significant improvement in Dice coefficient and total lesion volume compared to a state of the art model-based lesion segmentation method, indicating more accurate delineation of lesions.

Magnetic resonance (MR) imaging (MRI) is widely used to study the structure of human brains. Unlike computed tomography (CT), MR image intensities do not have a tissue specific interpretation. Thus images of the same subject obtained with either the same imaging sequence on different scanners or with differing parameters have widely varying intensity scales. This inconsistency introduces errors in segmentation, and other image processing tasks, thus necessitating image intensity standardization. Compared to previous intensity normalization methods using histogram transformations-which try to find a global one-to-one intensity mapping based on histograms-we propose a patch based generative model for intensity normalization between images acquired under different scanners or different pulse sequence parameters. Our method outperforms histogram based methods when normalizing phantoms simulated with various parameters. Additionally, experiments on real data, acquired under a variety of scanners and acquisition parameters, have more consistent segmentations after our normalization.

Segmentation of the human cerebrum from magnetic resonance images (MRI) into its component tissues has been a defining problem in medical imaging. Until recently, this has been solved as the tissue classification of the T1-weighted (T1-w) MRI, with numerous solutions for this problem having appeared in the literature. The clinical demands of understanding lesions, which are indistinguishable from gray matter in T1-w images, has necessitated the incorporation of T2-weighted Fluid Attenuated Inversion Recovery (FLAIR) images to improve segmentation of the cerebrum. Many of the existing methods fail to handle the second data channel gracefully, because of assumptions about their model. In our new approach, we explore a model free algorithm which uses a classification technique based on ensembles of decision trees to learn the mapping from an image feature to the corresponding tissue label. We use corresponding image patches from a registered set of T1-w and FLAIR images with a manual segmentation to construct our decision tree ensembles. Our method is efficient, taking less than two minutes on a 240x240x48 volume. We conduct experiments on five training sets in a leave-one-out fashion, as well as validation on an additional twelve subjects, and a landmark validation experiment on another cohort of five subjects.