A deep learning model for brain segmentation across pediatric and adult populations

Automated quantification of brain tissues on MR images has greatly contributed to the diagnosis and follow-up of neurological pathologies across various life stages. However, existing solutions are specifically designed for certain age ranges, limiting their applicability in monitoring brain development from infancy to late adulthood. This retrospective study aims to develop and validate a brain segmentation model across pediatric and adult populations. First, we trained a deep learning model to segment tissues and brain structures using T1-weighted MR images from 390 patients (age range: 2-81 years) across four different datasets. Subsequently, the model was validated on a cohort of 280 patients from six distinct test datasets (age range: 4-90 years). In the initial experiment, the proposed deep learning-based pipeline, icobrain-dl, demonstrated segmentation accuracy comparable to both pediatric and adult-specific models across diverse age groups. Subsequently, we evaluated intra- and inter-scanner variability in measurements of various tissues and structures in both pediatric and adult populations computed by icobrain-dl. Results demonstrated significantly higher reproducibility compared to similar brain quantification tools, including childmetrix, FastSurfer, and the medical device icobrain v5.9 (p-value< 0.01). Finally, we explored the potential clinical applications of icobrain-dl measurements in diagnosing pediatric patients with Cerebral Visual Impairment and adult patients with Alzheimer's Disease.

Towards validation in clinical routine: a comparative analysis of visual MTA ratings versus the automated ratio between inferior lateral ventricle and hippocampal volumes in Alzheimer's disease diagnosis

PURPOSE

To assess the performance of the inferior lateral ventricle (ILV) to hippocampal (Hip) volume ratio on brain MRI, for Alzheimer's disease (AD) diagnostics, comparing it to individual automated ILV and hippocampal volumes, and visual medial temporal lobe atrophy (MTA) consensus ratings.

METHODS

One-hundred-twelve subjects (mean age ± SD, 66.85 ± 13.64 years) with varying degrees of cognitive decline underwent MRI using a Philips Ingenia 3T. The MTA scale by Scheltens, rated on coronal 3D T1-weighted images, was determined by three experienced radiologists, blinded to diagnosis and sex. Automated volumetry was computed by icobrain dm (v. 5.10) for total, left, right hippocampal, and ILV volumes. The ILV/Hip ratio, defined as the percentage ratio between ILV and hippocampal volumes, was calculated and compared against a normative reference population (n = 1903). Inter-rater agreement, association, classification accuracy, and clinical interpretability on patient level were reported.

RESULTS

Visual MTA scores showed excellent inter-rater agreement. Ordinal logistic regression and correlation analyses demonstrated robust associations between automated brain segmentations and visual MTA ratings, with the ILV/Hip ratio consistently outperforming individual hippocampal and ILV volumes. Pairwise classification accuracy showed good performance without statistically significant differences between the ILV/Hip ratio and visual MTA across disease stages, indicating potential interchangeability. Comparison to the normative population and clinical interpretability assessments showed commensurability in classifying MTA "severity" between visual MTA and ILV/Hip ratio measurements.

CONCLUSION

The ILV/Hip ratio shows the highest correlation to visual MTA, in comparison to automated individual ILV and hippocampal volumes, offering standardized measures for diagnostic support in different stages of cognitive decline.

Artificial Intelligence Assistive Software Tool for Automated Detection and Quantification of Amyloid-Related Imaging Abnormalities

Importance

Amyloid-related imaging abnormalities (ARIA) are brain magnetic resonance imaging (MRI) findings associated with the use of amyloid-β-directed monoclonal antibody therapies in Alzheimer disease (AD). ARIA monitoring is important to inform treatment dosing decisions and might be improved through assistive software.

Objective

To assess the clinical performance of an artificial intelligence (AI)-based software tool for assisting radiological interpretation of brain MRI scans in patients monitored for ARIA.

Design, Setting, and Participants

This diagnostic study used a multiple-reader multiple-case design to evaluate the diagnostic performance of radiologists assisted by the software vs unassisted. The study enrolled 16 US Board of Radiology-certified radiologists to perform radiological reading with (assisted) and without the software (unassisted). The study encompassed 199 retrospective cases, where each case consisted of a predosing baseline and a postdosing follow-up MRI of patients from aducanumab clinical trials PRIME, EMERGE, and ENGAGE. Statistical analysis was performed from April to July 2023.

Exposures

Use of icobrain aria, an AI-based assistive software for ARIA detection and quantification.

Main Outcomes and Measures

Coprimary end points were the difference in diagnostic accuracy between assisted and unassisted detection of ARIA-E (edema and/or sulcal effusion) and ARIA-H (microhemorrhage and/or superficial siderosis) independently, assessed with the area under the receiver operating characteristic curve (AUC).

Results

Among the 199 participants included in this study of radiological reading performance, mean (SD) age was 70.4 (7.2) years; 105 (52.8%) were female; 23 (11.6%) were Asian, 1 (0.5%) was Black, 157 (78.9%) were White, and 18 (9.0%) were other or unreported race and ethnicity. Among the 16 radiological readers included, 2 were specialized neuroradiologists (12.5%), 11 were male individuals (68.8%), 7 were individuals working in academic hospitals (43.8%), and they had a mean (SD) of 9.5 (5.1) years of experience. Radiologists assisted by the software were significantly superior in detecting ARIA than unassisted radiologists, with a mean assisted AUC of 0.87 (95% CI, 0.84-0.91) for ARIA-E detection (AUC improvement of 0.05 [95% CI, 0.02-0.08]; P = .001]) and 0.83 (95% CI, 0.78-0.87) for ARIA-H detection (AUC improvement of 0.04 [95% CI, 0.02-0.07]; P = .001). Sensitivity was significantly higher in assisted reading compared with unassisted reading (87% vs 71% for ARIA-E detection; 79% vs 69% for ARIA-H detection), while specificity remained above 80% for the detection of both ARIA types.

Conclusions and Relevance

This diagnostic study found that radiological reading performance for ARIA detection and diagnosis was significantly better when using the AI-based assistive software. Hence, the software has the potential to be a clinically important tool to improve safety monitoring and management of patients with AD treated with amyloid-β-directed monoclonal antibody therapies.

The Finger Dexterity Test: Validation study of a smartphone-based manual dexterity assessment

BACKGROUND

The Nine-Hole Peg Test (9HPT) is the golden standard to measure manual dexterity in people with multiple sclerosis (MS). However, administration requires trained personnel and dedicated time during a clinical visit.

OBJECTIVES

The objective of this study is to validate a smartphone-based test for remote manual dexterity assessment, the icompanion Finger Dexterity Test (FDT), to be included into the icompanion application.

METHODS

A total of 65 MS and 81 healthy subjects were tested, and 20 healthy subjects were retested 2 weeks later.

RESULTS

The FDT significantly correlated with the 9HPT (dominant: ρ = 0.62, p < 0.001; non-dominant: ρ = 0.52, p < 0.001). MS subjects had significantly higher FDT scores than healthy subjects (dominant: p = 0.015; non-dominant: p = 0.013), which was not the case for the 9HPT. A significant correlation with age (dominant: ρ = 0.46, p < 0.001; non-dominant: ρ = 0.40, p = 0.002), Expanded Disability Status Scale (EDSS, dominant: ρ = 0.36, p = 0.005; non-dominant: ρ = 0.31, p = 0.024), and disease duration for the non-dominant hand (ρ = 0.31, p = 0.016) was observed. There was a good test-retest reliability in healthy subjects (dominant: r = 0.69, p = 0.001; non-dominant: r = 0.87, p < 0.001).

CONCLUSIONS

The icompanion FDT shows a moderate-to-good concurrent validity and test-retest reliability, differentiates between the MS subjects and healthy controls, and correlates with clinical parameters. This test can be implemented into routine MS care for remote follow-up of manual dexterity.

Deep learning pipeline for quality filtering of MRSI spectra

With the rise of novel 3D magnetic resonance spectroscopy imaging (MRSI) acquisition protocols in clinical practice, which are capable of capturing a large number of spectra from a subject's brain, there is a need for an automated preprocessing pipeline that filters out bad-quality spectra and identifies contaminated but salvageable spectra prior to the metabolite quantification step. This work introduces such a pipeline based on an ensemble of deep-learning classifiers. The dataset consists of 36,338 spectra from one healthy subject and five brain tumor patients, acquired with an EPSI variant, which implemented a novel type of spectral editing named SLOtboom-Weng (SLOW) editing on a 7T MR scanner. The spectra were labeled manually by an expert into four classes of spectral quality as follows: (i) noise, (ii) spectra greatly influenced by lipid-related artifacts (deemed not to contain clinical information), (iii) spectra containing metabolic information slightly contaminated by lipid signals, and (iv) good-quality spectra. The AI model consists of three pairs of networks, each comprising a convolutional autoencoder and a multilayer perceptron network. In the classification step, the encoding half of the autoencoder is kept as a dimensionality reduction tool, while the fully connected layers are added to its output. Each of the three pairs of networks is trained on different representations of spectra (real, imaginary, or both), aiming at robust decision-making. The final class is assigned via a majority voting scheme. The F1 scores obtained on the test dataset for the four previously defined classes are 0.96, 0.93, 0.82, and 0.90, respectively. The arguably lower value of 0.82 was reached for the least represented class of spectra mildly influenced by lipids. Not only does the proposed model minimise the required user interaction, but it also greatly reduces the computation time at the metabolite quantification step (by selecting a subset of spectra worth quantifying) and enforces the display of only clinically relevant information.

Post-acquisition water-signal removal in 3D water-unsuppressed 1 H-MR spectroscopic imaging of the prostate

PURPOSE

To develop a robust processing procedure of raw signals from water-unsuppressed MRSI of the prostate for the mapping of absolute tissue concentrations of metabolites.

METHODS

Water-unsuppressed 3D MRSI data were acquired from a phantom, from healthy volunteers, and a patient with prostate cancer. Signal processing included sequential computation of the modulus of the FID to remove water sidebands, a Hilbert transformation, and k-space Hamming filtering. For the removal of the water signal, we compared Löwner tensor-based blind source separation (BSS) and Hankel Lanczos singular value decomposition techniques. Absolute metabolite levels were quantified with LCModel and the results were statistically analyzed to compare the water removal methods and conventional water-suppressed MRSI.

RESULTS

The post-processing algorithms successfully removed the water signal and its sidebands without affecting metabolite signals. The best water removal performance was achieved by Löwner tensor-based BSS. Absolute tissue concentrations of citrate in the peripheral zone derived from water-suppressed and unsuppressed ¹ H MRSI were the same and as expected from the known physiology of the healthy prostate. Maps for citrate and choline from water-unsuppressed 3D ¹ H-MRSI of the prostate showed expected spatial variations in metabolite levels.

CONCLUSION

We developed a robust relatively simple post-processing method of water-unsuppressed MRSI of the prostate to remove the water signal. Absolute quantification using the water signal, originating from the same location as the metabolite signals, avoids the acquisition of additional reference data.

Detecting CTP truncation artifacts in acute stroke imaging from the arterial input and the vascular output functions

BACKGROUND

Current guidelines for CT perfusion (CTP) in acute stroke suggest acquiring scans with a minimal duration of 60-70 s. But even then, CTP analysis can be affected by truncation artifacts. Conversely, shorter acquisitions are still widely used in clinical practice and may, sometimes, be sufficient to reliably estimate lesion volumes. We aim to devise an automatic method that detects scans affected by truncation artifacts.

METHODS

Shorter scan durations are simulated from the ISLES'18 dataset by consecutively removing the last CTP time-point until reaching a 10 s duration. For each truncated series, perfusion lesion volumes are quantified and used to label the series as unreliable if the lesion volumes considerably deviate from the original untruncated ones. Afterwards, nine features from the arterial input function (AIF) and the vascular output function (VOF) are derived and used to fit machine-learning models with the goal of detecting unreliably truncated scans. Methods are compared against a baseline classifier solely based on the scan duration, which is the current clinical standard. The ROC-AUC, precision-recall AUC and the F1-score are measured in a 5-fold cross-validation setting.

RESULTS

The best performing classifier obtained an ROC-AUC of 0.982, precision-recall AUC of 0.985 and F1-score of 0.938. The most important feature was the AIFcoverage, measured as the time difference between the scan duration and the AIF peak. When using the AIFcoverage to build a single feature classifier, an ROC-AUC of 0.981, precision-recall AUC of 0.984 and F1-score of 0.932 were obtained. In comparison, the baseline classifier obtained an ROC-AUC of 0.954, precision-recall AUC of 0.958 and F1-Score of 0.875.

CONCLUSIONS

Machine learning models fed with AIF and VOF features accurately detected unreliable stroke lesion measurements due to insufficient acquisition duration. The AIFcoverage was the most predictive feature of truncation and identified unreliable short scans almost as good as machine learning. We conclude that AIF/VOF based classifiers are more accurate than the scans' duration for detecting truncation. These methods could be transferred to perfusion analysis software in order to increase the interpretability of CTP outputs.

Brain age as a surrogate marker for cognitive performance in multiple sclerosis

Background and purpose

Data from neuro‐imaging techniques allow us to estimate a brain's age. Brain age is easily interpretable as ‘how old the brain looks’ and could therefore be an attractive communication tool for brain health in clinical practice. This study aimed to investigate its clinical utility by investigating the relationship between brain age and cognitive performance in multiple sclerosis (MS).

Methods

A linear regression model was trained to predict age from brain magnetic resonance imaging volumetric features and sex in a healthy control dataset (HC_train, n = 1673). This model was used to predict brain age in two test sets: HC_test (n = 50) and MS_test (n = 201). Brain‐predicted age difference (BPAD) was calculated as BPAD = brain age minus chronological age. Cognitive performance was assessed by the Symbol Digit Modalities Test (SDMT).

Results

Brain age was significantly related to SDMT scores in the MS_test dataset (r = −0.46, p < 0.001) and contributed uniquely to variance in SDMT beyond chronological age, reflected by a significant correlation between BPAD and SDMT (r = −0.24, p < 0.001) and a significant weight (−0.25, p = 0.002) in a multivariate regression equation with age.

Conclusions

Brain age is a candidate biomarker for cognitive dysfunction in MS and an easy to grasp metric for brain health.

Morphometric evaluation of traumatic axonal injury and the correlation with post-traumatic cerebral atrophy and functional outcome

INTRODUCTION

Imaging plays a crucial role in the diagnosis, prognosis and follow-up of traumatic brain injury. Whereas computed tomography plays a pivotal role in the acute setting, magnetic resonance imaging is best suited to detect the true extent of traumatic brain injury, and more specifically diffuse axonal injury. Post-traumatic brain atrophy is a well-known complication of traumatic brain injury.

PURPOSE

This study investigated the correlation between diffuse axonal injury detected with fluid-attenuated inversion recovery and susceptibility-weighted imaging magnetic resonance imaging, post-traumatic brain atrophy and functional outcome (Glasgow outcome scale - extended).

MATERIALS AND METHODS

Twenty patients with a closed head injury and diffuse axonal injury detected with fluid-attenuated inversion recovery and susceptibility-weighted imaging were included. The total volumes of the diffuse axonal injury fluid-attenuated inversion recovery lesions were determined for each subject's initial (<14 days) and follow-up magnetic resonance scan (average: day 303 ± 83 standard deviation). The different brain volumes were automatically quantified using a validated and both US Food and Drug Administration-cleared and CE-marked machine learning algorithm (icobrain). The number of susceptibility-weighted imaging lesions and functional outcome scores (Glasgow outcome scale - extended) were retrieved from the Collaborative European NeuroTrauma Effectiveness Research Traumatic Brain Injury dataset.

RESULTS

The volumetric fluid-attenuated inversion recovery diffuse axonal injury lesion load showed a significant inverse correlation with functional outcome (Glasgow outcome scale - extended) (r = -0.57; P = 0.0094) and white matter volume change (r = -0.50; P = 0.027). In addition, white matter volume change correlated significantly with the Glasgow outcome scale - extended score (P = 0.0072; r = 0.58). Moreover, there was a strong inverse correlation between longitudinal fluid-attenuated inversion recovery lesion volume change and whole brain volume change (r = -0.63; P = 0.0028). No significant correlation existed between the number of diffuse axonal injury susceptibility-weighted imaging lesions, brain atrophy and functional outcome.

CONCLUSIONS

Volumetric analysis of diffuse axonal injury on fluid-attenuated inversion recovery imaging and automated brain atrophy calculation are potentially useful tools in the clinical management and follow-up of traumatic brain injury patients with diffuse axonal injury.

A Contrast Augmentation Approach to Improve Multi-Scanner Generalization in MRI

Most data-driven methods are very susceptible to data variability. This problem is particularly apparent when applying Deep Learning (DL) to brain Magnetic Resonance Imaging (MRI), where intensities and contrasts vary due to acquisition protocol, scanner- and center-specific factors. Most publicly available brain MRI datasets originate from the same center and are homogeneous in terms of scanner and used protocol. As such, devising robust methods that generalize to multi-scanner and multi-center data is crucial for transferring these techniques into clinical practice. We propose a novel data augmentation approach based on Gaussian Mixture Models (GMM-DA) with the goal of increasing the variability of a given dataset in terms of intensities and contrasts. The approach allows to augment the training dataset such that the variability in the training set compares to what is seen in real world clinical data, while preserving anatomical information. We compare the performance of a state-of-the-art U-Net model trained for segmenting brain structures with and without the addition of GMM-DA. The models are trained and evaluated on single- and multi-scanner datasets. Additionally, we verify the consistency of test-retest results on same-patient images (same and different scanners). Finally, we investigate how the presence of bias field influences the performance of a model trained with GMM-DA. We found that the addition of the GMM-DA improves the generalization capability of the DL model to other scanners not present in the training data, even when the train set is already multi-scanner. Besides, the consistency between same-patient segmentation predictions is improved, both for same-scanner and different-scanner repetitions. We conclude that GMM-DA could increase the transferability of DL models into clinical scenarios.

A Novel Digital Care Management Platform to Monitor Clinical and Subclinical Disease Activity in Multiple Sclerosis

In multiple sclerosis (MS), the early detection of disease activity or progression is key to inform treatment changes and could be supported by digital tools. We present a novel CE-marked and FDA-cleared digital care management platform consisting of (1) a patient phone/web application and healthcare professional portal (icompanion) including validated symptom, disability, cognition, and fatigue patient-reported outcomes; and (2) clinical brain magnetic resonance imaging (MRI) quantifications (icobrain ms). We validate both tools using their ability to detect (sub)clinical disease activity (known-groups validity) and real-world data insights. Surveys showed that 95.6% of people with MS (PwMS) were interested in using an MS app, and 98.2% were interested in knowing about MRI changes. The icompanion measures of disability (p < 0.001) and symptoms (p = 0.005) and icobrain ms MRI parameters were sensitive to (sub)clinical differences between MS subtypes. icobrain ms also decreased intra- and inter-rater lesion count variability and increased sensitivity for detecting disease activity/progression from 24% to 76% compared to standard radiological reading. This evidence shows PwMS’ interest, the digital care platform’s potential to improve the detection of (sub)clinical disease activity and care management, and the feasibility of linking different digital tools into one overarching MS care pathway.

AIFNet: Automatic vascular function estimation for perfusion analysis using deep learning

Perfusion imaging is crucial in acute ischemic stroke for quantifying the salvageable penumbra and irreversibly damaged core lesions. As such, it helps clinicians to decide on the optimal reperfusion treatment. In perfusion CT imaging, deconvolution methods are used to obtain clinically interpretable perfusion parameters that allow identifying brain tissue abnormalities. Deconvolution methods require the selection of two reference vascular functions as inputs to the model: the arterial input function (AIF) and the venous output function, with the AIF as the most critical model input. When manually performed, the vascular function selection is time demanding, suffers from poor reproducibility and is subject to the professionals' experience. This leads to potentially unreliable quantification of the penumbra and core lesions and, hence, might harm the treatment decision process. In this work we automatize the perfusion analysis with AIFNet, a fully automatic and end-to-end trainable deep learning approach for estimating the vascular functions. Unlike previous methods using clustering or segmentation techniques to select vascular voxels, AIFNet is directly optimized at the vascular function estimation, which allows to better recognise the time-curve profiles. Validation on the public ISLES18 stroke database shows that AIFNet almost reaches inter-rater performance for the vascular function estimation and, subsequently, for the parameter maps and core lesion quantification obtained through deconvolution. We conclude that AIFNet has potential for clinical transfer and could be incorporated in perfusion deconvolution software.

icobrain ms 5.1: Combining unsupervised and supervised approaches for improving the detection of multiple sclerosis lesions

Multiple sclerosis (MS) is a chronic autoimmune, inflammatory neurological disease of the central nervous system. Its diagnosis nowadays commonly includes performing an MRI scan, as it is the most sensitive imaging test for MS. MS plaques are commonly identified from fluid-attenuated inversion recovery (FLAIR) images as hyperintense regions that are highly varying in terms of their shapes, sizes and locations, and are routinely classified in accordance to the McDonald criteria. Recent years have seen an increase in works that aimed at development of various semi-automatic and automatic methods for detection, segmentation and classification of MS plaques. In this paper, we present an automatic combined method, based on two pipelines: a traditional unsupervised machine learning technique and a deep-learning attention-gate 3D U-net network. The deep-learning network is specifically trained to address the weaker points of the traditional approach, namely difficulties in segmenting infratentorial and juxtacortical plaques in real-world clinical MRIs. It was trained and validated on a multi-center multi-scanner dataset that contains 159 cases, each with T1 weighted (T1w) and FLAIR images, as well as manual delineations of the MS plaques, segmented and validated by a panel of raters. The detection rate was quantified using lesion-wise Dice score. A simple label fusion is implemented to combine the output segmentations of the two pipelines. This combined method improves the detection of infratentorial and juxtacortical lesions by 14% and 31% respectively, in comparison to the unsupervised machine learning pipeline that was used as a performance assessment baseline.

The association between MRI brain volumes and computerized cognitive scores of people with multiple sclerosis

BACKGROUND

Computerized cognitive assessment facilitates the incorporation of multi-domain cognitive monitoring into routine clinical care. The predictive validity of computerized cognitive assessment among people with multiple sclerosis (PwMS) has scarcely been investigated.

OBJECTIVE

To explore the associations between brain volumes and cognitive scores from a computerized cognitive assessment battery (CAB, NeuroTrax) among PwMS.

METHODS

PwMS were evaluated with the CAB and underwent brain MRI within 40 days. Cognitive assessment yielded age- and education-adjusted scores in 9 cognitive domains: memory, executive function, attention, information processing speed, visual spatial, verbal function, motor skills, problem solving, and working memory. The global cognitive score (GCS) is the average of all domain scores. MRI brain and lesion volumes were assessed with icobrain ms, a fully automated tissue and lesion segmentation and quantification software.

RESULTS

91 PwMS were included [Age: 52.1 ± 11.7 years, 64 (70%) female, EDSS: 3.4 ± 2.0, 79 (87%) with a relapsing remitting course]. Significant correlations were found between the GCS and whole brain, white matter, grey matter, thalamic, lateral ventricles, hippocampal and lesion volumes (Correlation coefficients: 0.46, 0.40, 0.25, 0.42, -0.36, 0.21, -0.3, respectively). Regression analysis revealed that lateral ventricles and thalamic volumes were the most consistent predictors of all cognitive domain scores.

CONCLUSION

Computerized cognitive scores were significantly associated with quantified MRI. These findings support the predictive validity of multi-domain computerized cognitive assessment for people with multiple sclerosis.

Sensorimotor cortex neurometabolite levels as correlate of motor performance in normal aging: evidence from a 1H-MRS study

Aging is associated with gradual alterations in the neurochemical characteristics of the brain, which can be assessed in-vivo with proton-magnetic resonance spectroscopy (¹H-MRS). However, the impact of these age-related neurochemical changes on functional motor behavior is still poorly understood. Here, we address this knowledge gap and specifically focus on the neurochemical integrity of the left sensorimotor cortex (SM1) and the occipital lobe (OCC), as both regions are main nodes of the visuomotor network underlying bimanual control. ¹H-MRS data and performance on a set of bimanual tasks were collected from a lifespan (20-75 years) sample of 86 healthy adults. Results indicated that aging was accompanied by decreased levels of N-acetylaspartate (NAA), glutamate-glutamine (Glx), creatine ​+ ​phosphocreatine (Cr) and myo-inositol (mI) in both regions, and decreased Choline (Cho) in the OCC region. Lower NAA and Glx levels in the SM1 and lower NAA levels in the OCC were related to poorer performance on a visuomotor bimanual coordination task, suggesting that NAA could serve as a potential biomarker for the integrity of the motor system supporting bimanual control. In addition, lower NAA, Glx, and mI levels in the SM1 were found to be correlates of poorer dexterous performance on a bimanual dexterity task. These findings highlight the role for ¹H-MRS to study neurochemical correlates of motor performance across the adult lifespan.

Non-invasive assessment of disease progression and neuroprotective effects of dietary coconut oil supplementation in the ALS SOD1G93A mouse model: A 1H-magnetic resonance spectroscopic study

Amyotrophic Lateral Sclerosis (ALS) is an incurable neurodegenerative disease primarily characterized by progressive degeneration of motor neurons in the motor cortex, brainstem and spinal cord. Due to relatively fast progression of ALS, early diagnosis is essential for possible therapeutic intervention and disease management. To identify potential diagnostic markers, we investigated age-dependent effects of disease onset and progression on regional neurochemistry in the SOD1^G93A ALS mouse model using localized in vivo magnetic resonance spectroscopy (MRS). We focused mainly on the brainstem region since brainstem motor nuclei are the primarily affected regions in SOD1^G93A mice and ALS patients. In addition, metabolite profiles of the motor cortex were also assessed. In the brainstem, a gradual decrease in creatine levels were detected starting from the pre-symptomatic age of 70 days postpartum. During the early symptomatic phase (day 90), a significant increase in the levels of the inhibitory neurotransmitter γ- aminobutyric acid (GABA) was measured. At later time points, alterations in the form of decreased NAA, glutamate, glutamine and increased myo-inositol were observed. Also, decreased glutamate, NAA and increased taurine levels were seen at late stages in the motor cortex. A proof-of-concept (PoC) study was conducted to assess the effects of coconut oil supplementation in SOD^G93A mice. The PoC revealed that the coconut oil supplementation together with the regular diet delayed disease symptoms, enhanced motor performance, and prolonged survival in the SOD1^G93A mouse model. Furthermore, MRS data showed stable metabolic profile at day 120 in the coconut oil diet group compared to the group receiving a standard diet without coconut oil supplementation. In addition, a positive correlation between survival and the neuronal marker NAA was found. To the best of our knowledge, this is the first study that reports metabolic changes in the brainstem using in vivo MRS and effects of coconut oil supplementation as a prophylactic treatment in SOD1^G93A mice.

Tensor-Based Method for Residual Water Suppression in 1H Magnetic Resonance Spectroscopic Imaging

OBJECTIVE

Magnetic resonance spectroscopic imaging (MRSI) signals are often corrupted by residual water and artifacts. Residual water suppression plays an important role in accurate and efficient quantification of metabolites from MRSI. A tensor-based method for suppressing residual water is proposed.

METHODS

A third-order tensor is constructed by stacking the Löwner matrices corresponding to each MRSI voxel spectrum along the third mode. A canonical polyadic decomposition is applied on the tensor to extract the water component and to, subsequently, remove it from the original MRSI signals.

RESULTS

The proposed method applied on both simulated and in-vivo MRSI signals showed good water suppression performance.

CONCLUSION

The tensor-based Löwner method has better performance in suppressing residual water in MRSI signals as compared to the widely used subspace-based Hankel singular value decomposition method.

SIGNIFICANCE

A tensor method suppresses residual water simultaneously from all the voxels in the MRSI grid and helps in preventing the failure of the water suppression in single voxels.

Evaluation of methods for volumetric analysis of pediatric brain data: The child pipeline versus adult-based approaches

Pediatric brain volumetric analysis based on Magnetic Resonance Imaging (MRI) is of particular interest in order to understand the typical brain development and to characterize neurodevelopmental disorders at an early age. However, it has been shown that the results can be biased due to head motion, inherent to pediatric data, and due to the use of methods based on adult brain data that are not able to accurately model the anatomical disparity of pediatric brains. To overcome these issues, we proposed childmetrix, a tool developed for the analysis of pediatric neuroimaging data that uses an age-specific atlas and a probabilistic model-based approach in order to segment the gray matter (GM) and white matter (WM). The tool was extensively validated on 55 scans of children between 5 and 6 years old (including 13 children with developmental dyslexia) and 10 pairs of test-retest scans of children between 6 and 8 years old and compared with two state-of-the-art methods using an adult atlas, namely icobrain (applying a probabilistic model-based segmentation) and Freesurfer (applying a surface model-based segmentation). The results obtained with childmetrix showed a better reproducibility of GM and WM segmentations and a better robustness to head motion in the estimation of GM volume compared to Freesurfer. Evaluated on two subjects, childmetrix showed good accuracy with 82-84% overlap with manual segmentation for both GM and WM, thereby outperforming the adult-based methods (icobrain and Freesurfer), especially for the subject with poor quality data. We also demonstrated that the adult-based methods needed double the number of subjects to detect significant morphological differences between dyslexics and typical readers. Once further developed and validated, we believe that childmetrix would provide appropriate and reliable measures for the examination of children's brain.

The successive projection algorithm as an initialization method for brain tumor segmentation using non-negative matrix factorization

Non-negative matrix factorization (NMF) has become a widely used tool for additive parts-based analysis in a wide range of applications. As NMF is a non-convex problem, the quality of the solution will depend on the initialization of the factor matrices. In this study, the successive projection algorithm (SPA) is proposed as an initialization method for NMF. SPA builds on convex geometry and allocates endmembers based on successive orthogonal subspace projections of the input data. SPA is a fast and reproducible method, and it aligns well with the assumptions made in near-separable NMF analyses. SPA was applied to multi-parametric magnetic resonance imaging (MRI) datasets for brain tumor segmentation using different NMF algorithms. Comparison with common initialization methods shows that SPA achieves similar segmentation quality and it is competitive in terms of convergence rate. Whereas SPA was previously applied as a direct endmember extraction tool, we have shown improved segmentation results when using SPA as an initialization method, as it allows further enhancement of the sources during the NMF iterative procedure.

Machine Learning Approach for Classifying Multiple Sclerosis Courses by Combining Clinical Data with Lesion Loads and Magnetic Resonance Metabolic Features

Purpose: The purpose of this study is classifying multiple sclerosis (MS) patients in the four clinical forms as defined by the McDonald criteria using machine learning algorithms trained on clinical data combined with lesion loads and magnetic resonance metabolic features.

Materials and Methods: Eighty-seven MS patients [12 Clinically Isolated Syndrome (CIS), 30 Relapse Remitting (RR), 17 Primary Progressive (PP), and 28 Secondary Progressive (SP)] and 18 healthy controls were included in this study. Longitudinal data available for each MS patient included clinical (e.g., age, disease duration, Expanded Disability Status Scale), conventional magnetic resonance imaging and spectroscopic imaging. We extract N-acetyl-aspartate (NAA), Choline (Cho), and Creatine (Cre) concentrations, and we compute three features for each spectroscopic grid by averaging metabolite ratios (NAA/Cho, NAA/Cre, Cho/Cre) over good quality voxels. We built linear mixed-effects models to test for statistically significant differences between MS forms. We test nine binary classification tasks on clinical data, lesion loads, and metabolic features, using a leave-one-patient-out cross-validation method based on 100 random patient-based bootstrap selections. We compute F1-scores and BAR values after tuning Linear Discriminant Analysis (LDA), Support Vector Machines with gaussian kernel (SVM-rbf), and Random Forests.

Results: Statistically significant differences were found between the disease starting points of each MS form using four different response variables: Lesion Load, NAA/Cre, NAA/Cho, and Cho/Cre ratios. Training SVM-rbf on clinical and lesion loads yields F1-scores of 71–72% for CIS vs. RR and CIS vs. RR+SP, respectively. For RR vs. PP we obtained good classification results (maximum F1-score of 85%) after training LDA on clinical and metabolic features, while for RR vs. SP we obtained slightly higher classification results (maximum F1-score of 87%) after training LDA and SVM-rbf on clinical, lesion loads and metabolic features.

Conclusions: Our results suggest that metabolic features are better at differentiating between relapsing-remitting and primary progressive forms, while lesion loads are better at differentiating between relapsing-remitting and secondary progressive forms. Therefore, combining clinical data with magnetic resonance lesion loads and metabolic features can improve the discrimination between relapsing-remitting and progressive forms.

Semi-automated brain tumor segmentation on multi-parametric MRI using regularized non-negative matrix factorization

Background

Segmentation of gliomas in multi-parametric (MP-)MR images is challenging due to their heterogeneous nature in terms of size, appearance and location. Manual tumor segmentation is a time-consuming task and clinical practice would benefit from (semi-) automated segmentation of the different tumor compartments.

Methods

We present a semi-automated framework for brain tumor segmentation based on non-negative matrix factorization (NMF) that does not require prior training of the method. L1-regularization is incorporated into the NMF objective function to promote spatial consistency and sparseness of the tissue abundance maps. The pathological sources are initialized through user-defined voxel selection. Knowledge about the spatial location of the selected voxels is combined with tissue adjacency constraints in a post-processing step to enhance segmentation quality. The method is applied to an MP-MRI dataset of 21 high-grade glioma patients, including conventional, perfusion-weighted and diffusion-weighted MRI. To assess the effect of using MP-MRI data and the L1-regularization term, analyses are also run using only conventional MRI and without L1-regularization. Robustness against user input variability is verified by considering the statistical distribution of the segmentation results when repeatedly analyzing each patient’s dataset with a different set of random seeding points.

Results

Using L1-regularized semi-automated NMF segmentation, mean Dice-scores of 65%, 74 and 80% are found for active tumor, the tumor core and the whole tumor region. Mean Hausdorff distances of 6.1 mm, 7.4 mm and 8.2 mm are found for active tumor, the tumor core and the whole tumor region. Lower Dice-scores and higher Hausdorff distances are found without L1-regularization and when only considering conventional MRI data.

Conclusions

Based on the mean Dice-scores and Hausdorff distances, segmentation results are competitive with state-of-the-art in literature. Robust results were found for most patients, although careful voxel selection is mandatory to avoid sub-optimal segmentation.

Longitudinal multiple sclerosis lesion segmentation: Resource and challenge

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.

Patch-Based Super-Resolution of MR Spectroscopic Images: Application to Multiple Sclerosis

Purpose: Magnetic resonance spectroscopic imaging (MRSI) provides complementary information to conventional magnetic resonance imaging. Acquiring high resolution MRSI is time consuming and requires complex reconstruction techniques.

Methods: In this paper, a patch-based super-resolution method is presented to increase the spatial resolution of metabolite maps computed from MRSI. The proposed method uses high resolution anatomical MR images (T1-weighted and Fluid-attenuated inversion recovery) to regularize the super-resolution process. The accuracy of the method is validated against conventional interpolation techniques using a phantom, as well as simulated and in vivo acquired human brain images of multiple sclerosis subjects.

Results: The method preserves tissue contrast and structural information, and matches well with the trend of acquired high resolution MRSI.

Conclusions: These results suggest that the method has potential for clinically relevant neuroimaging applications.

Classifying Glioblastoma Multiforme Follow-Up Progressive vs. Responsive Forms Using Multi-Parametric MRI Features

Purpose: The purpose of this paper is discriminating between tumor progression and response to treatment based on follow-up multi-parametric magnetic resonance imaging (MRI) data retrieved from glioblastoma multiforme (GBM) patients.

Materials and Methods: Multi-parametric MRI data consisting of conventional MRI (cMRI) and advanced MRI [i.e., perfusion weighted MRI (PWI) and diffusion kurtosis MRI (DKI)] were acquired from 29 GBM patients treated with adjuvant therapy after surgery. We propose an automatic pipeline for processing advanced MRI data and extracting intensity-based histogram features and 3-D texture features using manually and semi-manually delineated regions of interest (ROIs). Classifiers are trained using a leave-one-patient-out cross validation scheme on complete MRI data. Balanced accuracy rate (BAR)–values are computed and compared between different ROIs, MR modalities, and classifiers, using non-parametric multiple comparison tests.

Results: Maximum BAR–values using manual delineations are 0.956, 0.85, 0.879, and 0.932, for cMRI, PWI, DKI, and all three MRI modalities combined, respectively. Maximum BAR–values using semi-manual delineations are 0.932, 0.894, 0.885, and 0.947, for cMRI, PWI, DKI, and all three MR modalities combined, respectively. After statistical testing using Kruskal-Wallis and post-hoc Dunn-Šidák analysis we conclude that training a RUSBoost classifier on features extracted using semi-manual delineations on cMRI or on all MRI modalities combined performs best.

Conclusions: We present two main conclusions: (1) using T1 post-contrast (T1pc) features extracted from manual total delineations, AdaBoost achieves the highest BAR–value, 0.956; (2) using T1pc-average, T1pc-90th percentile, and Cerebral Blood Volume (CBV) 90th percentile extracted from semi-manually delineated contrast enhancing ROIs, SVM-rbf, and RUSBoost achieve BAR–values of 0.947 and 0.932, respectively. Our findings show that AdaBoost, SVM-rbf, and RUSBoost trained on T1pc and CBV features can differentiate progressive from responsive GBM patients with very high accuracy.

Two Time Point MS Lesion Segmentation in Brain MRI: An Expectation-Maximization Framework

Purpose: Lesion volume is a meaningful measure in multiple sclerosis (MS) prognosis. Manual lesion segmentation for computing volume in a single or multiple time points is time consuming and suffers from intra and inter-observer variability. Methods: In this paper, we present MSmetrix-long: a joint expectation-maximization (EM) framework for two time point white matter (WM) lesion segmentation. MSmetrix-long takes as input a 3D T1-weighted and a 3D FLAIR MR image and segments lesions in three steps: (1) cross-sectional lesion segmentation of the two time points; (2) creation of difference image, which is used to model the lesion evolution; (3) a joint EM lesion segmentation framework that uses output of step (1) and step (2) to provide the final lesion segmentation. The accuracy (Dice score) and reproducibility (absolute lesion volume difference) of MSmetrix-long is evaluated using two datasets. Results: On the first dataset, the median Dice score between MSmetrix-long and expert lesion segmentation was 0.63 and the Pearson correlation coefficient (PCC) was equal to 0.96. On the second dataset, the median absolute volume difference was 0.11 ml. Conclusions: MSmetrix-long is accurate and consistent in segmenting MS lesions. Also, MSmetrix-long compares favorably with the publicly available longitudinal MS lesion segmentation algorithm of Lesion Segmentation Toolbox.

Comparison of unsupervised classification methods for brain tumor segmentation using multi-parametric MRI

Tumor segmentation is a particularly challenging task in high-grade gliomas (HGGs), as they are among the most heterogeneous tumors in oncology. An accurate delineation of the lesion and its main subcomponents contributes to optimal treatment planning, prognosis and follow-up. Conventional MRI (cMRI) is the imaging modality of choice for manual segmentation, and is also considered in the vast majority of automated segmentation studies. Advanced MRI modalities such as perfusion-weighted imaging (PWI), diffusion-weighted imaging (DWI) and magnetic resonance spectroscopic imaging (MRSI) have already shown their added value in tumor tissue characterization, hence there have been recent suggestions of combining different MRI modalities into a multi-parametric MRI (MP-MRI) approach for brain tumor segmentation. In this paper, we compare the performance of several unsupervised classification methods for HGG segmentation based on MP-MRI data including cMRI, DWI, MRSI and PWI. Two independent MP-MRI datasets with a different acquisition protocol were available from different hospitals. We demonstrate that a hierarchical non-negative matrix factorization variant which was previously introduced for MP-MRI tumor segmentation gives the best performance in terms of mean Dice-scores for the pathologic tissue classes on both datasets.

•

Unsupervised classification algorithms are applied for brain tumor segmentation on multi-parametric MRI datasets.

•

Reported mean Dice-scores are in the range of state-of-the-art segmentation algorithms.

•

Hierarchical NMF obtained the best segmentation results in terms of mean Dice-scores for most of the tissue classes.

Reliable measurements of brain atrophy in individual patients with multiple sclerosis

INTRODUCTION

As neurodegeneration is recognized as a major contributor to disability in multiple sclerosis (MS), brain atrophy quantification could have a high added value in clinical practice to assess treatment efficacy and disease progression, provided that it has a sufficiently low measurement error to draw meaningful conclusions for an individual patient.

METHOD

In this paper, we present an automated longitudinal method based on Jacobian integration for measuring whole-brain and gray matter atrophy based on anatomical magnetic resonance images (MRI), named MSmetrix. MSmetrix is specifically designed to measure atrophy in patients with MS, by including iterative lesion segmentation and lesion filling based on FLAIR and T1-weighted MRI scans.

RESULTS

MS metrix is compared with SIENA with respect to test-retest error and consistency, resulting in an average test-retest error on an MS data set of 0.13% (MS metrix) and 0.17% (SIENA) and a consistency error of 0.07% (MS metrix) and 0.05% (SIENA). On a healthy subject data set including physiological variability the test-retest is 0.19% (MS metrix) and 0.31% (SIENA).

CONCLUSION

Therefore, we can conclude that MSmetrix could be of added value in clinical practice for the follow-up of treatment and disease progression in MS patients.

Nonnegative Canonical Polyadic Decomposition for Tissue-Type Differentiation in Gliomas

Magnetic resonance spectroscopic imaging (MRSI) reveals chemical information that characterizes different tissue types in brain tumors. Blind source separation techniques are used to extract the tissue-specific profiles and their corresponding distribution from the MRSI data. We focus on automatic detection of the tumor, necrotic and normal brain tissue types by constructing a 3D MRSI tensor from in vivo 2D-MRSI data of individual glioma patients. Nonnegative canonical polyadic decomposition (NCPD) is applied to the MRSI tensor to differentiate various tissue types. An in vivo study shows that NCPD has better performance in identifying tumor and necrotic tissue type in glioma patients compared to previous matrix-based decompositions, such as nonnegative matrix factorization and hierarchical nonnegative matrix factorization.

Hierarchical non-negative matrix factorization applied to three-dimensional 3 T MRSI data for automatic tissue characterization of the prostate

In this study non-negative matrix factorization (NMF) was hierarchically applied to simulated and in vivo three-dimensional 3 T MRSI data of the prostate to extract patterns for tumour and benign tissue and to visualize their spatial distribution. Our studies show that the hierarchical scheme provides more reliable tissue patterns than those obtained by performing only one NMF level. We compared the performance of three different NMF implementations in terms of pattern detection accuracy and efficiency when embedded into the same kind of hierarchical scheme. The simulation and in vivo results show that the three implementations perform similarly, although one of them is more robust and better pinpoints the most aggressive tumour voxel(s) in the dataset. Furthermore, they are able to detect tumour and benign tissue patterns even in spectra with lipid artefacts. Copyright © 2016 John Wiley & Sons, Ltd.

Tensor based tumor tissue type differentiation using magnetic resonance spectroscopic imaging

Magnetic resonance spectroscopic imaging (MRSI) has the potential to characterise different tissue types in brain tumors. Blind source separation techniques are used to extract the specific tissue profiles and their corresponding distribution from the MRSI data. A 3-dimensional MRSI tensor is constructed from in vivo 2D-MRSI data of individual tumor patients. Non-negative canonical polyadic decomposition (NCPD) with common factor in mode-1 and mode-2 and l(1) regularization on mode-3 is applied on the MRSI tensor to differentiate various tissue types. Initial in vivo study shows that NCPD has better performance in identifying tumor and necrotic tissue type in high grade glioma patients compared to previous matrix-based decompositions, such as non-negative matrix factorization and hierarchical non-negative matrix factorization.

Hierarchical non-negative matrix factorization to characterize brain tumor heterogeneity using multi-parametric MRI

Tissue characterization in brain tumors and, in particular, in high-grade gliomas is challenging as a result of the co-existence of several intra-tumoral tissue types within the same region and the high spatial heterogeneity. This study presents a method for the detection of the relevant tumor substructures (i.e. viable tumor, necrosis and edema), which could be of added value for the diagnosis, treatment planning and follow-up of individual patients. Twenty-four patients with glioma [10 low-grade gliomas (LGGs), 14 high-grade gliomas (HGGs)] underwent a multi-parametric MRI (MP-MRI) scheme, including conventional MRI (cMRI), perfusion-weighted imaging (PWI), diffusion kurtosis imaging (DKI) and short-TE (1)H MRSI. MP-MRI parameters were derived: T2, T1 + contrast, fluid-attenuated inversion recovery (FLAIR), relative cerebral blood volume (rCBV), mean diffusivity (MD), fractional anisotropy (FA), mean kurtosis (MK) and the principal metabolites lipids (Lip), lactate (Lac), N-acetyl-aspartate (NAA), total choline (Cho), etc. Hierarchical non-negative matrix factorization (hNMF) was applied to the MP-MRI parameters, providing tissue characterization on a patient-by-patient and voxel-by-voxel basis. Tissue-specific patterns were obtained and the spatial distribution of each tissue type was visualized by means of abundance maps. Dice scores were calculated by comparing tissue segmentation derived from hNMF with the manual segmentation by a radiologist. Correlation coefficients were calculated between each pathologic tissue source and the average feature vector within the corresponding tissue region. For the patients with HGG, mean Dice scores of 78%, 85% and 83% were obtained for viable tumor, the tumor core and the complete tumor region. The mean correlation coefficients were 0.91 for tumor, 0.97 for necrosis and 0.96 for edema. For the patients with LGG, a mean Dice score of 85% and mean correlation coefficient of 0.95 were found for the tumor region. hNMF was also applied to reduced MRI datasets, showing the added value of individual MRI modalities.

Integrating diffusion kurtosis imaging, dynamic susceptibility-weighted contrast-enhanced MRI, and short echo time chemical shift imaging for grading gliomas

BACKGROUND

We assessed the diagnostic accuracy of diffusion kurtosis imaging (DKI), dynamic susceptibility-weighted contrast-enhanced (DSC) MRI, and short echo time chemical shift imaging (CSI) for grading gliomas.

METHODS

In this prospective study, 35 patients with cerebral gliomas underwent DKI, DSC, and CSI on a 3 T MR scanner. Diffusion parameters were mean diffusivity (MD), fractional anisotropy, and mean kurtosis (MK). Perfusion parameters were mean relative regional cerebral blood volume (rrCBV), mean relative regional cerebral blood flow (rrCBF), mean transit time, and relative decrease ratio (rDR). The diffusion and perfusion parameters along with 12 CSI metabolite ratios were compared among 22 high-grade gliomas and 14 low-grade gliomas (Mann-Whitney U-test, P < .05). Classification accuracy was determined with a linear discriminant analysis for each MR modality independently. Furthermore, the performance of a multimodal analysis is reported, using a decision-tree rule combining the statistically significant DKI, DSC-MRI, and CSI parameters with the lowest P-value. The proposed classifiers were validated on a set of subsequently acquired data from 19 clinical patients.

RESULTS

Statistically significant differences among tumor grades were shown for MK, MD, mean rrCBV, mean rrCBF, rDR, lipids over total choline, lipids over creatine, sum of myo-inositol, and sum of creatine. DSC-MRI proved to be the modality with the best performance when comparing modalities individually, while the multimodal decision tree proved to be most accurate in predicting tumor grade, with a performance of 86%.

CONCLUSIONS

Combining information from DKI, DSC-MRI, and CSI increases diagnostic accuracy to differentiate low- from high-grade gliomas, possibly providing diagnosis for the individual patient.

Automatic segmentation and volumetry of multiple sclerosis brain lesions from MR images

The location and extent of white matter lesions on magnetic resonance imaging (MRI) are important criteria for diagnosis, follow-up and prognosis of multiple sclerosis (MS). Clinical trials have shown that quantitative values, such as lesion volumes, are meaningful in MS prognosis. Manual lesion delineation for the segmentation of lesions is, however, time-consuming and suffers from observer variability. In this paper, we propose MSmetrix, an accurate and reliable automatic method for lesion segmentation based on MRI, independent of scanner or acquisition protocol and without requiring any training data. In MSmetrix, 3D T1-weighted and FLAIR MR images are used in a probabilistic model to detect white matter (WM) lesions as an outlier to normal brain while segmenting the brain tissue into grey matter, WM and cerebrospinal fluid. The actual lesion segmentation is performed based on prior knowledge about the location (within WM) and the appearance (hyperintense on FLAIR) of lesions. The accuracy of MSmetrix is evaluated by comparing its output with expert reference segmentations of 20 MRI datasets of MS patients. Spatial overlap (Dice) between the MSmetrix and the expert lesion segmentation is 0.67 ± 0.11. The intraclass correlation coefficient (ICC) equals 0.8 indicating a good volumetric agreement between the MSmetrix and expert labelling. The reproducibility of MSmetrix' lesion volumes is evaluated based on 10 MS patients, scanned twice with a short interval on three different scanners. The agreement between the first and the second scan on each scanner is evaluated through the spatial overlap and absolute lesion volume difference between them. The spatial overlap was 0.69 ± 0.14 and absolute total lesion volume difference between the two scans was 0.54 ± 0.58 ml. Finally, the accuracy and reproducibility of MSmetrix compare favourably with other publicly available MS lesion segmentation algorithms, applied on the same data using default parameter settings.

Different quantification algorithms may lead to different results: a comparison using proton MRS lipid signals

Proton magnetic resonance spectroscopy (MRS) is a sensitive method for investigating the biochemical compounds in a tissue. The interpretation of the data relies on the quantification algorithms applied to MR spectra. Each of these algorithms has certain underlying assumptions and may allow one to incorporate prior knowledge, which could influence the quality of the fit. The most commonly considered types of prior knowledge include the line-shape model (Lorentzian, Gaussian, Voigt), knowledge of the resonating frequencies, modeling of the baseline, constraints on the damping factors and phase, etc. In this article, we study whether the statistical outcome of a biological investigation can be influenced by the quantification method used. We chose to study lipid signals because of their emerging role in the investigation of metabolic disorders. Lipid spectra, in particular, are characterized by peaks that are in most cases not Lorentzian, because measurements are often performed in difficult body locations, e.g. in visceral fats close to peristaltic movements in humans or very small areas close to different tissues in animals. This leads to spectra with several peak distortions. Linear combination of Model spectra (LCModel), Advanced Method for Accurate Robust and Efficient Spectral fitting (AMARES), quantitation based on QUantum ESTimation (QUEST), Automated Quantification of Short Echo-time MRS (AQSES)-Lineshape and Integration were applied to simulated spectra, and area under the curve (AUC) values, which are proportional to the quantity of the resonating molecules in the tissue, were compared with true values. A comparison between techniques was also carried out on lipid signals from obese and lean Zucker rats, for which the polyunsaturation value expressed in white adipose tissue should be statistically different, as confirmed by high-resolution NMR measurements (considered the gold standard) on the same animals. LCModel, AQSES-Lineshape, QUEST and Integration gave the best results in at least one of the considered groups of simulated or in vivo lipid signals. These outcomes highlight the fact that quantification methods can influence the final result and its statistical significance.

Hierarchical non-negative matrix factorization (hNMF): a tissue pattern differentiation method for glioblastoma multiforme diagnosis using MRSI

MRSI has shown potential in the diagnosis and prognosis of glioblastoma multiforme (GBM) brain tumors, but its use is limited by difficult data interpretation. When the analyzed MRSI data present more than two tissue patterns, conventional non-negative matrix factorization (NMF) implementation may lead to a non-robust estimation. The aim of this article is to introduce an effective approach for the differentiation of GBM tissue patterns using MRSI data. A hierarchical non-negative matrix factorization (hNMF) method that can blindly separate the most important spectral sources in short-TE ¹H MRSI data is proposed. This algorithm consists of several levels of NMF, where only two tissue patterns are computed at each level. The method is demonstrated on both simulated and in vivo short-TE ¹H MRSI data in patients with GBM. For the in vivo study, the accuracy of the recovered spectral sources was validated using expert knowledge. Results show that hNMF is able to accurately estimate the three tissue patterns present in the tumoral and peritumoral area of a GBM, i.e. normal, tumor and necrosis, thus providing additional useful information that can help in the diagnosis of GBM. Moreover, the hNMF results can be displayed as easily interpretable maps showing the contribution of each tissue pattern to each voxel.

Unsupervised nosologic imaging for glioma diagnosis

In this letter a novel approach to create nosologic images of the brain using magnetic resonance spectroscopic imaging (MRSI) data in an unsupervised way is presented. Different tissue patterns are identified from the MRSI data using nonnegative matrix factorization and are then coded as different primary colors (i.e. red, green, and blue) in an RGB image, so that mixed tissue regions are automatically visualized as mixtures of primary colors. The approach is useful in assisting glioma diagnosis, where several tissue patterns such as normal, tumor, and necrotic tissue can be present in the same voxel/spectrum. Error-maps based on linear least squares estimation are computed for each nosologic image to provide additional reliability information, which may help clinicians in decision making. Tests on in vivo MRSI data show the potential of this new approach.

Reproducibility of rapid short echo time CSI at 3 tesla for clinical applications

PURPOSE

To validate the reproducibility of a chemical shift imaging (CSI) acquisition protocol with parallel imaging, using automated repositioning software.

MATERIALS AND METHODS

Ten volunteers were imaged three times on two different 3 Tesla (T) MRI scanners, receiving anatomical imaging and two identical CSI measurements, using automated repositioning software for consistent repositioning of the CSI grid. Offcenter parameters of the CSI plane were analyzed. Coefficients of variation (CoV), Cramér-Rao lower bounds (CRLB), intraclass correlation coefficients (ICC), and coefficients of repeatability (CoR) for immediate repetition and between scanners were calculated for N-acetylaspartate, total choline, creatine, myo-inositol (Myo) and glutamine+glutamate (Glx). Proportions of variance reflecting the effect of voxel location, volunteer, repetition, time instance and scanner were calculated from an analysis of variance analysis.

RESULTS

The offcenter vector and angulations of the CSI grid differed less than 1 mm and 2° between all measurements. The mean CoV and CRLB were less than 30% for all metabolites, except for Myo. The variance due to voxel location in the volume of interest and the error represent the largest contributions in variability. The ICC is the lowest for Myo and Glx. CoR for immediate repetition and between scanners display values between 22 and 83%.

CONCLUSION

We propose a CSI protocol with acceptable reproducibility, applicable in clinical routine.

Exploiting spatial information to estimate metabolite levels in two-dimensional MRSI of heterogeneous brain lesions

MRSI provides MR spectra from multiple adjacent voxels within a body volume represented as a two- or three-dimensional matrix, allowing the measurement of the distribution of metabolites over this volume. The spectra of these voxels are usually analyzed one by one, without exploiting their spatial context. In this article, we present an advanced metabolite quantification method for MRSI data, in which the available spatial information is considered. A nonlinear least-squares algorithm is proposed in which prior knowledge is included in the form of proximity constraints on the spectral parameters within a grid and optimized starting values. A penalty term that promotes a spatially smooth spectral parameter map is added to the fitting algorithm. This method is adaptive, in the sense that several sweeps through the grid are performed and each solution may tune some hyperparameters at run-time. Simulation studies of MRSI data showed significantly improved metabolite estimates after the inclusion of spatial information. Improved metabolite maps were also demonstrated by applying the method to in vivo MRSI data. Overlapping peaks or peaks of compounds present at low concentration can be better quantified with the proposed method than with single-voxel approaches. The new approach compares favorably against the multivoxel approach embedded in the well-known quantification software LCModel.

Non-negative blind source separation techniques for tumor tissue typing using HR-MAS signals

Given High Resolution Magic Angle Spinning (HR-MAS) signals from several glioblastoma tumor subjects, the goal is to differentiate between tumor tissue types by separating the different sources that contribute to the profile of each spectrum. Blind source separation techniques are applied for obtaining characteristic profiles for necrosis, high cellular tumor and border tumor tissue, and providing the contribution (abundance) of each tumor tissue to the profile of the spectra. The problem is formulated as a non-negative source separation problem. We illustrate the effectiveness of the proposed methods and we analyze to which extent the dimension of the input space could influence the performance by comparing the results on the full magnitude signals and on dimensionally reduced spaces.

Investigation of adipose tissues in Zucker rats using in vivo and ex vivo magnetic resonance spectroscopy

In vivo single-voxel magnetic resonance spectroscopy (MRS) at 4.7T and ex vivo high-resolution proton magnetic resonance spectroscopy (HR-NMR) at 500 MHz were used to study the composition of adipose tissues in Zucker obese and Zucker lean rats. Lipid composition was characterized by unsaturation and polyunsaturation indexes and mean chain lengths. In vitro experiments were conducted in known mixtures of triglycerides and oils in order to validate the method. To avoid inaccuracies due to partial peak overlapping in MRS, peak quantification was performed after fitting of spectral peaks by using the QUEST algorithm. The intensity of different spectral lines was also corrected for T2 relaxation. Albeit with different sensitivity and accuracy, both techniques revealed that white adipose tissue is characterized by lower unsaturation and polyunsaturation indexes in obese rats compared with controls. HR-NMR revealed similar differences in brown adipose tissue. The present findings confirm the hypothesis that obese and lean Zucker rats have different adipose tissue composition.